What Causes Image Intensity Changes?
|
|
- Madeline Brown
- 5 years ago
- Views:
Transcription
1 Ede Detection l Why Detect Edes? u Information reduction l Replace imae by a cartoon in which objects and surface markins are outlined create line drawin description l These are the most informative parts of the imae u Bioloical plausibility l Initial staes of mammalian vision systems involve detection of edes and local features u Applications l Object reconition, stereo, texture analysis, motion analysis, imae enhancement, imae compression 1 What Causes Imae Intensity Chanes? l Many types of physical events cause intensity chanes u Surface reflectance discontinuity - chane in the fraction of liht incident on the surface that is reflected to viewer u Illumination discontinuity - shadow u Surface orientation (normal) discontinuity u Depth discontinuity - at occludin contour, where surface orientation is perpendicular to line of siht 2 1
2 What type of real-world ede is this contrast border? 3 Need lobal information too 4 2
3 What Does an Ede Look Like? l Step l Ramp l Roof l Line (bar) 5 6 3
4 fine scale hih threshold 7 coarse scale, hih threshold 8 4
5 coarse scale low threshold 9 Ede Detectors in the HVS Simple (border) Complex l Sum activity from an array of oriented simple cells 10 5
6 Orientation Columns in V1 l A hypercolum = complete set of orientations 11 Craik-O Brien-Cornsweet Illusion 12 6
7 Koffka Rin 13 Luminance Differences Affect our Perceptions l Artists use the technique of equiluminance to blur outlines and suest motion. We cannot perceive the edes of objects where object and backround have the same luminance. If parts of a paintin are equiluminant, their positions become ambiuous. They may seem to shift position or to float l Equiluminant colors have special properties, e.., they can make a paintin appear unstable 14 7
8 Equiluminant Colors l An object that can be seen by both subdivisions of the visual system will be perceived accurately. But if the two subdivisions are not balanced in their response to an object, it may look peculiar. l For example, an object defined by equiluminant colors can be seen by the What system but is invisible (or poorly seen) by the Where system. It may seem flat, it may seem to shift position, or it may seem to float ambiuously because there is too little luminance contrast to provide adequate information about its three-dimensional shape, its location in space, or its motion (or lack of it). l Conversely, somethin defined by very low contrast contours is seen by the Where system but not the What system and may seem to have depth and spatial oranization but no clear shape. 15 Detail from Richard Anuszkiewicz s Plus Reversed, 1960 The red and blue seem to move around because they are equiluminant 16 8
9 Ede Detection Goals l Good detection: Low false alarm rate and low false dismissal rate maximize sinal-to-noise (S/N) ratio l Good localization: Mark point closest to center of true ede minimize distance between marked point and center l Uniqueness: Only one response to a sinle ede l Good property measurement: Orientation, contrast, etc. 17 Ede Operator Properties l Shift invariant (translation invariant, position invariant) u If (x,y) = Op[f(x,y)] then (x-a, y-b) = Op[f(x-a, y-b)] l Isotropic (rotation invariant) vs. non-isotropic l Derivative order (if differentiation-based method) l Linear vs. non-linear u Op[a f 1 (x,y) + b f 2 (x,y)] = a Op[f 1 (x,y)] + b Op[f 2 (x,y)] = a 1 (x,y) + b 2 (x,y) l Scale (operator neihborhood size) u (x,y) = Op[f(x+a, y+b), -k < a, b < k ] l Convolution (linear and shift-invariant) 18 9
10 Ede and Local Feature Detection Methods l Gradient-based ede detection l Ede detection by function fittin l Second derivative ede detectors l Ede linkin and the construction of the chain raph 19 1D Ede Detection l An ideal ede is a step function I(x) x I (x) x 20 10
11 1D Ede Detection I (x) x l The first derivative of I(x) has a peak at the ede l The second derivative of I(x) has a zero crossin at the ede 21 1D Ede Detection l More realistically, imae edes are blurred and the reions that meet at those edes have noise or variations in intensity u Blur - hih first derivatives near edes u Noise - hih first derivatives within reions that meet at edes I(x) I (x) x x 22 11
12 Ede Detection in 2D l Let I(x,y) be the imae intensity function. It has derivatives in all directions u I(x, y)/ x = lim I(x+ x, y) - I(x, y) / x I(u+1, v) - I(u,v) u Gradient of I(x, y) is a vector I(x, y) = [ I/ x, I/ y] T specifyin the direction of reatest rate of chane in intensity (i.e., perpendicular to the ede s direction) u From radient can determine the direction in which the first derivative is hihest, and the manitude of the first derivative in that direction u Manitude = [( I/ x) 2 + ( I/ y) 2 ] 1/2 u Direction = tan -1 ( I/ y)/( I/ x) 23 Computin First Derivative l To compute first derivative in direction θ, calculate from linear combination of derivatives from any two non-collinear directions x = x cos θ - y sin θ y y θ x x y = x sin θ + y cos θ I/ x = I/ x x/ x + I/ y y/ y = I/ x cos θ + I/ y sin θ I/ y = - I/ x sin θ + I/ y cos θ ( I/ x ) 2 + ( I/ y ) 2 = ( I/ x) 2 + ( I/ y) 2 So, sum of squares of first derivative is isotropic, non-linear Similarly, all derivatives of odd ordcr raised to an even power are isotropic 24 12
13 Gradient l Gradient = [ I/ x, I/ y] T l What direction is first derivative a maximum? u Set / θ ( I/ x ) = 0, and solve for θ / θ ( I/ x cos θ + I/ y sin θ) = 0 θ = tan -1 ( I/ y / I/ x) l Gradient direction is perpendicular to ede direction l Gradient manitude is isotropic I = I x 2 I + y 2 25 Ede Detection in 2D l With a diital imae, the partial derivatives are replaced by finite differences: u x I = I(u+1, v) - I(u, v) u y I = I(u, v) - I(u, v+1) l An alternative (Sobel) u sobel_x I = I(u+1, v+1) + 2I(u+1, v) + I(u+1, v-1) - I(u-1, v+1) - 2I(u-1, v) - I(u-1, v-1) u sobel_y I = I(u-1, v-1) + 2I(u, v-1) + I(u+1, v-1) - I(u-1, v+1) - 2I(u, v+1) - I(u+1, v+1) l Roberts s Cross u + I = I(u, v) - I(u+1, v-1) u - I = I(u, v-1) - I(u+1, v) v u 26 13
14 Gradient Operator Example l I = l x = -1 1 l x I = *
15 15 30 Directional Ede Operators l Kirsch 8-direction masks l Gradient manitude = l Gradient direction = 45 armax k n = k = k = k = k k n n max =0,...7
16 Directional Ede Operators l Robinson masks r 0 1 = r 2 7 = l Nevatia and Babu used 6 5x5 masks, detectin orientations at multiples of Ede Detection in 2D l How do we combine the directional derivatives to compute the radient manitude? u Use the root mean square (RMS) as in the continuous case u Sum of the absolute values of the directional derivatives u Maximum of the absolute values of the directional derivatives l Advantaes of the latter u Avoids computin square root (althouh this can be done usin table lookups) u Keeps result in the same rane as the oriinal imae u Gives a manitude that is invariant with respect to orientation of the ede in the imae ( sobel_x overestimates diaonal edes and + overestimates horizontal and vertical ede manitudes) 32 16
17 Finite Differences and Noise l Finite difference filters respond stronly to noise u obvious reason: imae noise results in pixels that look very different from their neihbors l Generally, the larer the noise the stroner the response l What is to be done? u intuitively, most pixels in imaes look quite a lot like their neihbors u this is true even at an ede; alon the ede they re similar, across the ede they re not u suests that smoothin the imae should help, by forcin pixels different from their neihbors (=noise pixels?) to look more like their neihbors 33 Finite Differences Respondin to Noise Increasin noise -> (this is zero mean additive aussian noise) 34 17
18 Combinin Smoothin and Differentiation - Fixed Scale l Local operators like the Roberts operator ive hih responses to any intensity variation u local surface texture u noise from the sensin process l If the picture is first smoothed by an averain process, then these local variations are removed and what remains are the prominent edes l Example: I 2x2 (u,v) = 1/4[I(u,v) + I(u+1,v) + I(u,v+1) + I(u+1,v+1)] 35 Smoothin - Basic Problems l What function should be used to smooth or averae the imae before differentiation? u Mean smoothin (aka box filters or uniform smoothin or averain) l easy to compute (linear) l for lare smoothin neihborhoods assins too much weiht to points far from an ede u Median smoothin l doesn t blur corners l unaffected by outliers u Gaussian smoothin l [1/(2πσ 2 )] e -(u2 + v 2 )/2σ
19 Example: Smoothin by Averain 38 19
20 Smoothin with a Gaussian 39 The Mystery of the Mona Lisa Smile l Mararet Livinstone has conjectured that the elusive smile is because of the differences in resolution in the fovea and the periphery of the retina Low-pass filtered Middle-pass Hih-pass 40 20
21 Chanin small details can affect the mood we perceive. A few pixels of chane switches her from happy to sad. Addin random noise also chanes our perception of her expression
22 Smoothin and Convolution l The convolution of two functions, f(x) and (x), is defined as h(x) = (x ) f(x-x ) dx = (x) * f(x) l When f and are discrete and when is nonzero only over a finite rane [-n, n], this interal is replaced by the summation h(u) = (i) f(u-i) 43 Example of 1D Convolution f h h(4) 12 2 = i= ( i) f (4 i) Note: Values in h have been divided by = 13 = ( 2) f (6) + ( 1) f (5) + (0) f (4) + (1) f (3) + (2) f (2) 44 22
23 Smoothin and Convolution l These interals and summations extend simply to functions of two variables: h(u,v) = (u,v) * f(u,v) = (i,j) f(u-i, v-j) l Convolution computes the weihted sum of the ray levels in each n x n neihborhood of the imae, f, usin the kernel matrix of weihts, l Convolution is a linear operator because u *(af 1 + bf 2 ) = a(*f 1 ) + b(*f 2 ) 45 Convolution 46 23
24 D Convolution (4,4) (1,1) (4,5) (1,0) (4,6) 1) (1, (5,4) (0,1) (5,5) (0,0) (5,6) 1) (0, (6,4) 1,1) ( (6,5) 1,0) ( (6,6) 1) 1, ( ),5 (5 ), ( (5,5) f f f f f f f f f j i f j i h i j = = = = 48 Smoothin and Convolution
25 Properties of Convolution l Commutative l Associative l Cascadable l Linear, shift-invariant l Any linear, shift-invariant operation can be implemented as a convolution l Convolution in spatial domain = multiplication in frequency domain. I.e., = f * h iff G = F H, where * denotes convolution and F = (f) l An alternative for computin : = -1 (F H) 49 Combinin Smoothin and Ede Detection l Let S = l x = -1 1 l Smooth, then differentiate: x * (S * I), where I is oriinal imae and * is convolution = ( x * S) * I l x * S = = Prewitt_x
26 Back to Smoothin Functions l To smooth an imae usin a Gaussian filter, e -(u2 + v 2 )/2σ 2, we must u Choose an appropriate value for σ, which controls how quickly the Gaussian falls to near 0 l Small σ produces filter which drops to near 0 quickly - can be implemented usin small diital array of weihts l Lare σ produces a filter which drops to near 0 slowly - will be implemented usin a larer size diital array of weihts u Determine the size weiht array needed to adequately represent that Gaussian l To represent 98.76% of the area under the Gaussian usin σ=σ 0 use a mask of size 5σ 0 x 5σ 0 l In practice, size of mask is often closer to size 3σ x 3σ l Weiht array needs to be of odd size (2k+1 x 2k+1) to allow for symmetry 51 Gaussian Smoothin l To smooth an imae usin a Gaussian filter we must u Sample the Gaussian by interatin it over the square pixels of the array of weihts and multiplyin by a scale factor to obtain inteer weihts u Because we have truncated the Gaussian, the weihts will not sum to 1.0 x scale factor l In flat areas of the imae we expect our smoothin filter to leave the imae unchaned l But if the filter weihts do not sum to 1.0 x scale factor, it will either amplify (> 1.0) or de-amplify (< 1.0) the imae 52 26
27 Gaussian Smoothin l Gaussian smoothin steps u Normalize the weiht array by dividin each entry by the sum of the all of the entries (interal equal to 1) u Convert to inteers l Advantaes of Gaussian filterin u Rotationally symmetric (for lare filters) u Filter weihts decrease monotonically from central peak, ivin most weiht to central pixels u Simple and intuitive relationship between size of σ and size of objects whose edes will be detected in imae. u The Gaussian is separable 53 Buildin Discrete Gaussian Kernels l Given σ and w, compute real-valued weihts for w x w kernel array l Divide all entries by minimum weiht and round result to nearest inteer, obtainin kernel G l Compute normalization factor n = weihts l I' = 1/n (G * I) 54 27
28 Separability l A function (x, y) is separable if (x, y) = 1 (x) 2 (y) l The Gaussian function is separable: e -[(x2 + y 2 )/2σ 2 ] = e -[x2 /2σ 2 ] * e -[y2 /2σ 2 ] l First convolve the imae with a 1D horizontal filter l Then convolve the result of the first convolution with a 1D vertical filter l For a k x k Gaussian filter, 2D convolution requires k 2 multiplications and k 2-1 additions per pixel l But usin the separable filters, we reduce this to 2k multiplications and 2k-1 additions per pixel 55 Separability I = = = x = = 11 2 = = = = =
29 Advantaes of Gaussians l Cascadin Gaussians: Convolution of a Gaussian with itself is another Gaussian u So, we can first smooth an imae with a small Gaussian u Then, we convolve that smoothed imae with another small Gaussian and the result is equivalent to smoother the oriinal imae with a larer Gaussian u If we smooth an imae with a Gaussian havin standard deviation σ twice, then we et the same result as smoothin the imae with a Gaussian havin standard deviation 2σ 57 Combinin Smoothin and Differentiation - Fixed Scale l Non-maxima suppression - Retain a point as an ede point if u its radient manitude is hiher than a threshold u its radient manitude is a local maximum in the radient direction l Lateral inhibition process 58 29
30 Summary of Basic Ede Detection Steps l Smooth the imae to reduce the effects of local intensity variations u Choice of smoothin operator practically important l Differentiate the smoothed imae usin a diital radient operator that assins a manitude and direction of the radient at each pixel u Mathematically, we can apply the diital radient operator to the diital smoothin filter, and then just convolve the differentiated smoothin filter to the imae u Requires usin a slihtly larer smoothin array to avoid border effects l Threshold the radient manitude to eliminate low contrast edes 59 Summary of Basic Ede Detection Steps l Apply a non-maximum suppression step to thin the edes to sinle pixel wide edes u Smoothin will produce an imae in which the contrast at an ede is spread out in the neihborhood of the ede u Thresholdin operation will produce thick edes 60 30
31 Canny Ede Operator l Desin operator that is optimal with respect to ood detection, ood localization, and unique response criteria l Good detection criterion: Maximize SNR, which is the ratio of the step size of a step ede over the standard deviation of the 0-mean, additive Gaussian noise l Good localization criterion: Maximize inverse distance of detected ede from true ede l Optimal 1D step-ede detector = detector that maximizes the product of the two terms above subject to third criterion l First derivative of a Gaussian is within 20% of optimal 61 Directional Derivatives l Isotropic operators smooth across edes Poor localization l Instead, averae pixels alon ede direction only Use a set of directional derivatives at a lare number of orientations etc
32 Canny Ede Operator l Gaussian smooth imae: G * I l Estimate radient direction (i.e., ede normal), n, at each pixel: ( G * I) n = ( G * I) l Compute first derivative in the radient direction, n. That is, G/ n * I l Suppress non-maxima u If value is not a local max in direction n, then chane value to 0 u Or, find zero-crossins in direction n. I.e., zero-crossins of ([ G/ n] * I)/ n = 2 (G * I)/ n 2 63 Canny Ede Operator l To et rid of spurious edes created by noise (false positives) and to fill in missin edes (false neatives) use hysteresis thresholdin: u Define two thresholds, t hih and t low u Mark all pixels with ede manitude > t hih as ede pixels u For each marked pixel, search in ede direction, both ways, markin all pixels with ede manitude > t low as ede pixels. Stop search when a pixel is reached with ede manitude < t low 64 32
33 Laplacian Ede Detectors l Directional second derivative in direction of radient has a zero crossin at radient maximum l Can approximate directional second derivative with Laplacian: 2 I = 2 I/ x I/ y 2 l Laplacian is lowest order linear isotropic operator l Diital approximation (2nd forward difference) is u 2 I(u,v) = [I(u+1,v) + I(u-1,v) + I(u,v+1) + I(u,v-1)] - 4I(u,v) = [I(u+1,v) - I(u,v)] - [I(u,v) - I(u-1,v)] + [I(u,v+1) - I(u,v)] - [I(u,v) - I(u,v-1)] Laplacian Examples l I = l 2 = I = l I = I =
34 Problems with Laplacian of Small Size l Responds most stronly at isolated points (spots) noise sensitive l Responds stronly at lines and endpoints of lines l Responds relatively less at edes l Ramp edes detected at two ends, not once at center 67 34
35 Usin Laplacian for Ede Enhancement l Given a blurred imae I = 1/5 (I * ) l 2 I I - I l - k 2 I - k(-1/5 (I - I )) = k/5 I + I (1 - k/5) I when k=5 l ==> Can deblur an imae by subtractin a multiple of its Laplacian l Simulates Mach Band effect in human visual system l Analoous to unsharp maskin technique in photoraphy 69 Mach Bands l In 1865, Mach discovered that we perceive an ede (chane of intensity) at lines that separate surface reions with identical intensity on both sides but different intensity derivatives l It is caused by the lateral inhibition of the receptors in the eyes 70 35
36 Mach Bands Actual brihtness Perceived by you 71 Laplacian Ede Detectors l Laplacians are also combined with smoothin for ede detectors u Take the Laplacian of a Gaussian-smoothed imae - called the Laplacian-of-Gaussian (LoG), Mexican Hat operator, Difference-of-Gaussians (DoG), Marr- Hildreth, 2 G operator u Locate the zero-crossin of the operator l these are pixels whose LoG is positive and which have neihbor s whose LoG is neative or zero u Usually, measure the radient or directional first derivatives at these points to eliminate low contrast edes 72 36
37 Laplacian of Gaussian (LoG) 2 G σ (x, y) = -[1/2πσ 4 ] (2 - (x 2 + y 2 )/σ 2 ) e -(x2 + y 2 )/2σ
38 LoG Properties l Linear, shift invariant convolution l Circularly symmetric isotropic l Size of LoG operator approximately 6σ x 6σ l LoG is separable l LoG G σ1 - G σ2, where σ 1 = 1.6σ 2 l Analoous to spatial oranization of receptive fields of retinal anlion cells, with a central excitatory reion and an inhibitory surround
39 Receptive Field + - u Reion on retina that influences activity of a anlion cell u Firin rate of neuron u Excitatory center, inhibitory surround 77 u Ganlion cells detect differences in luminance at a border, line, or spot u Retina is NOT a spot-meter 78 39
40 Lateral Inhibition Explanation dark band liht band B < A B inhibited by surround D > E D less inhibited by surround 79 Hermann Grid l Illustrates lateral inhibition 80 40
41 Visual illusions 81 Lateral Inhibition Explanation Inhibited less by white stripes Inhibited more by white stripes 82 41
42 The Scale Space Problem l Usually, any sinle choice of σ does not produce a ood ede map u a lare σ will produce edes from only the larest objects, and they will not accurately delineate the object because the smoothin reduces shape detail u a small σ will produce many edes and very jaed boundaries of many objects l Scale-space approaches u detect edes at a rane of scales [σ 1, σ 2 ] u combine the resultin ede maps l trace edes detected usin lare σ down throuh scale space to obtain more accurate spatial localization 83 42
43 43
44 44
45 Pyramids l Very useful for representin imaes l Pyramid is built by usin multiple copies of imae l Each level in the pyramid is 1/4 the area of previous level, i.e., each dimension is 1/2 resolution of previous level 89 Pyramids 45
46 91 Gaussian Pyramid 92 46
47 Gaussian Pyramid l Multiresolution, low-pass filter l Hierarchical convolution u G0 = input imae u G k (u, v) = w(m, n) G k-1 (u-m, v-n) u G k (u, v) = G k (2u, 2v), 0 < u, v < 2 N-k ; smooth ; sub-sample l w is a small (e.., 5 x 5) separable eneratin kernel, e.., 1/16 [ ] l Cascadin w equivalent to applyin lare kernel u Effective size of kernel at level k = 2M(2 k - 1) + 1, where w has width 2M+1 u Example: Let M=1. If k=1 then equivalent size = 5; k=2 then equivalent size = 13; k=3 then equivalent size = Gaussian Pyramids 2 2 = m= 2n = 2 l ( u, v) w( m, n) l 1(2u + m,2v + n) l = REDUCE [ l 1 ] 94 47
48 Reduce (1D) 2 l = wˆ( m) l + m=2 ( u) (2) = wˆ( 2) l wˆ (0) wˆ (0) l1 l1 (4) + wˆ(1) (2) = wˆ ( 2) l l1 l1 (4) + wˆ (1) 1(2u m) (4 2) + wˆ ( 1) l1 (2) + wˆ ( 1) l1 l1 (4 + 1) + wˆ (2) l1 (5) + wˆ (2) (3) + l1 (6) (4 1) + l1 (4 + 2) 95 Reduce 96 48
49 49 97 Gaussian Pyramids [ 1 ],, = n l n l EXPAND ) 2, 2 ( ), ( ), ( ,, q v p u q p w v u p q n l n l = = = 98 Expand (1D) ) 2 ( ) ˆ ( ) ( 2 2 1,, p u p w u p n l n l = = ) ( ˆ (2) ) ( ˆ (1) ) 2 4 ( ˆ (0) ) ( 1) ˆ( ) ( 2) ˆ ( (4) 1, 1, 1, 1, 1,, = n l n l n l n l n l n l w w w w w (3) ˆ(2) (2) ˆ (0) (1) 2) ˆ( 4) ( 1, 1, 1,, + + = n l n l n l n l w w w
50 Expand 99 Convolution Mask [ w( 2), w( 1), w(0), w(1), w(2)]
51 Convolution Mask l Separable w ( m, n) = wˆ ( m) wˆ( n) l Symmetric wˆ ( u) = wˆ ( u) [ c, b, a, b, c] 101 Convolution Mask l The sum of mask should be 1: a + 2 b + 2c = 1 l All nodes at a iven level must contribute the same total weiht to the nodes at the next hiher level: a + 2 c = 2b
52 Convolution Mask w$ ( 0) = a 1 w$ ( 1) = w$ ( 1) = 4 1 a w$ ( 2) = w$ ( 2) = Alorithm l Apply 1D mask to alternate pixels alon each row of imae l Apply 1D mask to each pixel alon alternate columns of resultant imae from previous step
53 Laplacian Pyramids l Similar to results of ede detection l Most pixels are 0 l Can be used for imae compression: L L 2 = 2 L 1 = 1 EXPAND[ 2 ] EXPAND[ 3 ] 3 = 3 EXPAND[ 4 ]
54 Laplacian Pyramid l Computes a set of bandpass filtered versions of imae l L k = G k - w * G k = G k - Expand(G k+1 ) l L N = G N (apex of Laplacian pyr = apex of Gaussian pyr) l Separates features by their scale (size) l Enhances features l Compact representation l L k = (G 0 - G 1 ) + (G 1 - G 2 ) (G N-1 - G N ) + G N = G
55 Gaussian and Laplacian Pyramids 109 Codin usin the Laplacian Pyramid Compute Gaussian pyramid 1 2, 3,, 4 Compute Laplacian pyramid L L L L = 1 = = = EXPAND [ EXPAND [ EXPAND [ Code Laplacian pyramid ] ] ]
56 Decodin usin Laplacian pyramid l Decode Laplacian pyramid l Compute Gaussian pyramid from Laplacian pyramid: 4 = L 4 [ + L 3 = EXPAND 4] 2 = EXPAND[ 3 ] + L = EXPAND[ 2 ] + L 1 l 1 is reconstructed imae 111 Imae Compression Laplacian Pyramid After Quantization Level
57 Imae Compression Oriinals Encoded 113 Imae Compositin by Pyramid Blendin l Given: Two 2 n x 2 n imaes l Goal: Create an imae that contains left half of imae A and riht half of imae B l Alorithm u Compute Laplacian pyramids, LA and LB, from imaes A and B u Compute Laplacian pyramid LS by copyin left half of LA and riht half of LB. Pyramid nodes down the center line = averae of correspondin LA and LB nodes blend alon center line u Expand and sum levels of LS to obtain output imae S
58 Combinin Apple & Orane 115 Combinin Apple & Orane (usin Pyramids)
59 Imae Compositin from Arbitrary Reions l Given: Two 2 n x 2 n imaes and one 2 n x 2 n binary mask l Goal: Output imae containin imae A where mask=1, and imae B where mask=0 l Alorithm: u Construct Laplacian pyramids LA and LB from imaes A and B u Construct Gaussian pyramid GR from mask R u Construct Laplacian pyramid LS: LS k (u, v) = GR k (u, v) LA k (u, v) + (1 - GR k (u, v)) LB k (u, v) u Expand and sum levels of LS to obtain output imae S
60 60
61 61
62 Oriented ( Steerable ) Pyramids l Laplacian pyramid is orientation-independent l Apply an oriented filter to determine orientations at each layer u by clever filter desin, we can simplify synthesis u this represents imae information at a particular scale and orientation
63 125 From Shiftable MultiScale Transforms, by Simoncelli et al., IEEE Transactions on Information Theory,
64 Analysis 127 Synthesis
65 Ede Detection by Function Fittin: Facet Model l General approach u Fit a function to each pixel s neihborhood of the imae u Use the radient of the function as the diital radient of the imae neihborhood l Example: Fit a plane to a 2 x 2 neihborhood u z = ax + by + c; z is ray level u Gradient is then (a 2 + b 2 ) 1/2 u Neihborhood points are I(x,y), I(x+1,y), I(x,y+1) and I(x+1,y+1) l Need to minimize E(a,b,c) = ΣΣ [a(x+i) + b(y+j) + c - I(x+i,y+j)] 2 l Solve this and similar problems by: u Differentiatin with respect to a,b,c, set results to 0, and u Solve for a,b,c in resultin system of equations 129 Ede Detection by Function Fittin l E/ a = ΣΣ2[a(x+i) + b(y+j) + c - I(x+i,y+j)](x+i) l E/ b = ΣΣ2[a(x+i) + b(y+j) + c - I(x+i,y+j)](y+j) l E/ c = ΣΣ2[a(x+i) + b(y+j) + c - I(x+i,y+j)] l It is easy to verify that a = [I(x+1,y) + I(x+1,y+1) - I(x,y) - I(x,y+1)]/2 b = [I(x,y+1) + I(x+1,y+1) - I(x,y) - I(x+1,y)]/2 l a and b are the partial derivatives with respect to x and y a = -1 1 b =
66 Ede Detection by Function Fittin l Could also fit a hiher order surface than a plane u With a second order surface we could find the (linear) combination of pixel values that corresponds to the hiher order derivatives, which can also be used for ede detection l Would ordinarily use a neihborhood larer than 2 x 2 u Better fit u For hih deree functions need more points for the fit to be reliable 131 Ede Linkin and Followin l Group ede pixels into chains and chains into lare pieces of object boundary. u can use the shapes of lon ede chains in reconition l slopes l curvature l corners l Basic steps u thin connected components of edes to one pixel thick u find simply connected paths u link them at corners into a raph model of imae contours u compute local and lobal properties of contours and corners
67 Findin Simply Connected Chains l Goal: create a raph-structured representation (chain raph) of the imae contours u vertex for each junction in the imae u ede connectin vertices correspondin to junctions that are connected by an chain; ede labeled with chain u b α β a s c φ d f δ e ε η r h j β b α c a δ e ε d φ f η 133 Creatin the Chain Graph l Alorithm: iven binary imae, E, of thinned edes u create a binary imae, J, of junctions and end points l points in E that are 1 and have more than two neihbors that are 1 or exactly one neihbor that is a 1 u create the imae E-J = C(chains) l this imae contains the chains of E, but they are broken at junctions u perform a connected component analysis of C. For each component store in a table T: l its end points (0 or 2) l the list of coordinates joinin its end points u For each point in J: l create a node in the chain raph, G, with a unique label
68 Creatin the Chain Graph l For each chain in C u if that chain is a closed loop (has no end points) l choose one point from the chain randomly and create a new node in G correspondin to that point l mark that point as a loop junction to distinuish it from other junctions l create an ede in G connectin this new node to itself, and mark that ede with the name of the chain loop u if that chain is not a closed loop, then it has two end points l create an ede in G linkin the two points from J adjacent to its end points 135 Creatin the Chain Graph l Data structure for creatin the chain raph l Biest problem is determinin for each open chain in C the points in J that are adjacent to its end points u sophisticated solution miht use a hierarchical data structure, like a k-d tree, to represent the points in J u more direct solution is to create imae J in which all 1 s are marked with their unique labels u For each chain in C l Examine the 3 x 3 neihborhood of each end point of C in J l Find the name of the junction or end point adjacent to that end point from this 3 x 3 neihborhood
69 Findin Internal Corners of Chains l Chains are only broken at junctions u But important features of the chain miht occur at internal points u Example: closed loop correspondin to a square - would like to find the natural corners of the square and add them as junctions to the chain raph (splittin the chains at those natural corners) l Curve sementation u similar to imae sementation, but in a 1D form l Local methods, like ede detectors l Global methods, like reion analyzers 137 Local Methods of Curve Sementation l Natural locations to sement contours are points where the slope of the curve is chanin quickly u These correspond, perceptually, to corners of the curve l To measure the chane in slope we are measurin the curvature of the curve u Straiht line has 0 curvature u Circular arc has constant curvature correspondin to 1/r l Can estimate curvature by fittin a simple function (circular arc, quadratic function, cubic function) to each neihborhood of a chain, and usin the parameters of the fit to estimate the curvature at the center of the neihborhood
70 Formulas for Curvature l Consider movin a point, P, alon a curve u Let T be the unit tanent vector as P moves l T has constant lenth (1) l The direction of T, φ, chanes from point to point unless the curve is a straiht line l Measure this direction as the anle between T and the x-axis T = dr / ds, s distance alon curve P φ R 139 Formulas for Curvature l The curvature, κ, is the instantaneous rate of chane of φ with respect to s, distance alon the curve u κ = dφ / ds u ds = [dx 2 + dy 2 ] 1/2 u φ = tan -1 dy/dx T = dr / ds, s distance alon curve P φ R
71 Formulas for Curvature l Now dφ / dx = d 2 y dx ( dy dx )2 and so ds / dx = κ = dφ / ds = 1+ ( dy dx )2 d 2 y dφ / dx ds / dx = dx 2 [1+ ( dy dx )2 ] 3/ Example - Circle l For the circle u s = aθ u φ = θ + π/2 u so κ = dφ/ds = dθ/adθ = 1/a a θ s φ
72 Local Methods of Curve Sementation l There are also a wide variety of heuristic methods to estimate curvature like local properties u For each point, p, alon the curve u Find the points k pixels before and after p on the curve (p +k, p -k ) and then measure l the anle between pp +k and pp -k θ l the ratio s/t l Similar problems to ede detection u what is the appropriate size for k? t k s k u how do we combine the curvature estimates at different scales? u boundary problems near the ends of open curves - not enouh pixels to look out k in both directions
Edge Detection. CS 650: Computer Vision
CS 650: Computer Vision Edges and Gradients Edge: local indication of an object transition Edge detection: local operators that find edges (usually involves convolution) Local intensity transitions are
More informationEdge Detection. What Causes Image Intensity Changes? What type of real-world edge is this contrast border? Need global information too
Ede Detection What Causes Imae Intensity Chanes? Why Detect Edes? u Information reduction Repace imae by a cartoon in which objects and surface markins are outined create ine drawin description These are
More informationLecture 7: Edge Detection
#1 Lecture 7: Edge Detection Saad J Bedros sbedros@umn.edu Review From Last Lecture Definition of an Edge First Order Derivative Approximation as Edge Detector #2 This Lecture Examples of Edge Detection
More informationComputer Vision Lecture 3
Demo Haribo Classification Computer Vision Lecture 3 Linear Filters 23..24 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Code available on the class website...
More informationFiltering and Edge Detection
Filtering and Edge Detection Local Neighborhoods Hard to tell anything from a single pixel Example: you see a reddish pixel. Is this the object s color? Illumination? Noise? The next step in order of complexity
More informationEdge Detection in Computer Vision Systems
1 CS332 Visual Processing in Computer and Biological Vision Systems Edge Detection in Computer Vision Systems This handout summarizes much of the material on the detection and description of intensity
More information2.2 Differentiation and Integration of Vector-Valued Functions
.. DIFFERENTIATION AND INTEGRATION OF VECTOR-VALUED FUNCTIONS133. Differentiation and Interation of Vector-Valued Functions Simply put, we differentiate and interate vector functions by differentiatin
More informationLecture 6: Edge Detection. CAP 5415: Computer Vision Fall 2008
Lecture 6: Edge Detection CAP 5415: Computer Vision Fall 2008 Announcements PS 2 is available Please read it by Thursday During Thursday lecture, I will be going over it in some detail Monday - Computer
More informationEdge Detection. Introduction to Computer Vision. Useful Mathematics Funcs. The bad news
Edge Detection Introduction to Computer Vision CS / ECE 8B Thursday, April, 004 Edge detection (HO #5) Edge detection is a local area operator that seeks to find significant, meaningful changes in image
More informationMachine vision, spring 2018 Summary 4
Machine vision Summary # 4 The mask for Laplacian is given L = 4 (6) Another Laplacian mask that gives more importance to the center element is given by L = 8 (7) Note that the sum of the elements in the
More informationRoadmap. Introduction to image analysis (computer vision) Theory of edge detection. Applications
Edge Detection Roadmap Introduction to image analysis (computer vision) Its connection with psychology and neuroscience Why is image analysis difficult? Theory of edge detection Gradient operator Advanced
More informationMachine vision. Summary # 4. The mask for Laplacian is given
1 Machine vision Summary # 4 The mask for Laplacian is given L = 0 1 0 1 4 1 (6) 0 1 0 Another Laplacian mask that gives more importance to the center element is L = 1 1 1 1 8 1 (7) 1 1 1 Note that the
More informationLaplacian Filters. Sobel Filters. Laplacian Filters. Laplacian Filters. Laplacian Filters. Laplacian Filters
Sobel Filters Note that smoothing the image before applying a Sobel filter typically gives better results. Even thresholding the Sobel filtered image cannot usually create precise, i.e., -pixel wide, edges.
More informationExperiment 3 The Simple Pendulum
PHY191 Fall003 Experiment 3: The Simple Pendulum 10/7/004 Pae 1 Suested Readin for this lab Experiment 3 The Simple Pendulum Read Taylor chapter 5. (You can skip section 5.6.IV if you aren't comfortable
More informationPHY 133 Lab 1 - The Pendulum
3/20/2017 PHY 133 Lab 1 The Pendulum [Stony Brook Physics Laboratory Manuals] Stony Brook Physics Laboratory Manuals PHY 133 Lab 1 - The Pendulum The purpose of this lab is to measure the period of a simple
More informationConvergence of DFT eigenvalues with cell volume and vacuum level
Converence of DFT eienvalues with cell volume and vacuum level Sohrab Ismail-Beii October 4, 2013 Computin work functions or absolute DFT eienvalues (e.. ionization potentials) requires some care. Obviously,
More information1 CHAPTER 7 PROJECTILES. 7.1 No Air Resistance
CHAPTER 7 PROJECTILES 7 No Air Resistance We suppose that a particle is projected from a point O at the oriin of a coordinate system, the y-axis bein vertical and the x-axis directed alon the round The
More informationImage Gradients and Gradient Filtering Computer Vision
Image Gradients and Gradient Filtering 16-385 Computer Vision What is an image edge? Recall that an image is a 2D function f(x) edge edge How would you detect an edge? What kinds of filter would you use?
More informationEdge Detection. Image Processing - Computer Vision
Image Processing - Lesson 10 Edge Detection Image Processing - Computer Vision Low Level Edge detection masks Gradient Detectors Compass Detectors Second Derivative - Laplace detectors Edge Linking Image
More informationNANO 703-Notes. Chapter 12-Reciprocal space
1 Chapter 1-Reciprocal space Conical dark-field imain We primarily use DF imain to control imae contrast, thouh STEM-DF can also ive very hih resolution, in some cases. If we have sinle crystal, a -DF
More informationParametric Equations
Parametric Equations Suppose a cricket jumps off of the round with an initial velocity v 0 at an anle θ. If we take his initial position as the oriin, his horizontal and vertical positions follow the equations:
More information6.869 Advances in Computer Vision. Bill Freeman, Antonio Torralba and Phillip Isola MIT Oct. 3, 2018
6.869 Advances in Computer Vision Bill Freeman, Antonio Torralba and Phillip Isola MIT Oct. 3, 2018 1 Sampling Sampling Pixels Continuous world 3 Sampling 4 Sampling 5 Continuous image f (x, y) Sampling
More informationParameterization and Vector Fields
Parameterization and Vector Fields 17.1 Parameterized Curves Curves in 2 and 3-space can be represented by parametric equations. Parametric equations have the form x x(t), y y(t) in the plane and x x(t),
More informationVlad Estivill-Castro (2016) Robots for People --- A project for intelligent integrated systems
1 Vlad Estivill-Castro (2016) Robots for People --- A project for intelligent integrated systems V. Estivill-Castro 2 Perception Concepts Vision Chapter 4 (textbook) Sections 4.3 to 4.5 What is the course
More informationn j u = (3) b u Then we select m j u as a cross product between n j u and û j to create an orthonormal basis: m j u = n j u û j (4)
4 A Position error covariance for sface feate points For each sface feate point j, we first compute the normal û j by usin 9 of the neihborin points to fit a plane In order to create a 3D error ellipsoid
More informationEdges and Scale. Image Features. Detecting edges. Origin of Edges. Solution: smooth first. Effects of noise
Edges and Scale Image Features From Sandlot Science Slides revised from S. Seitz, R. Szeliski, S. Lazebnik, etc. Origin of Edges surface normal discontinuity depth discontinuity surface color discontinuity
More informationECE Digital Image Processing and Introduction to Computer Vision. Outline
2/9/7 ECE592-064 Digital Image Processing and Introduction to Computer Vision Depart. of ECE, NC State University Instructor: Tianfu (Matt) Wu Spring 207. Recap Outline 2. Sharpening Filtering Illustration
More informationPROJECTILE MOTION. ( ) g y 0. Equations ( ) General time of flight (TOF) General range. Angle for maximum range ("optimum angle")
PROJECTILE MOTION Equations General time of fliht (TOF) T sin θ y 0 sin( θ) General rane R cos( θ) T R cos θ sin( θ) sin( θ) y 0 Anle for maximum rane ("optimum anle") θ opt atan y 0 atan v f atan v f
More informationIT6502 DIGITAL SIGNAL PROCESSING Unit I - SIGNALS AND SYSTEMS Basic elements of DSP concepts of frequency in Analo and Diital Sinals samplin theorem Discrete time sinals, systems Analysis of discrete time
More informationLecture 8: Interest Point Detection. Saad J Bedros
#1 Lecture 8: Interest Point Detection Saad J Bedros sbedros@umn.edu Review of Edge Detectors #2 Today s Lecture Interest Points Detection What do we mean with Interest Point Detection in an Image Goal:
More informationExperiment 1: Simple Pendulum
COMSATS Institute of Information Technoloy, Islamabad Campus PHY-108 : Physics Lab 1 (Mechanics of Particles) Experiment 1: Simple Pendulum A simple pendulum consists of a small object (known as the bob)
More informationREVIEW: Going from ONE to TWO Dimensions with Kinematics. Review of one dimension, constant acceleration kinematics. v x (t) = v x0 + a x t
Lecture 5: Projectile motion, uniform circular motion 1 REVIEW: Goin from ONE to TWO Dimensions with Kinematics In Lecture 2, we studied the motion of a particle in just one dimension. The concepts of
More informationXI PHYSICS M. AFFAN KHAN LECTURER PHYSICS, AKHSS, K. https://promotephysics.wordpress.com
XI PHYSICS M. AFFAN KHAN LECTURER PHYSICS, AKHSS, K affan_414@live.com https://promotephysics.wordpress.com [MOTION IN TWO DIMENSIONS] CHAPTER NO. 4 In this chapter we are oin to discuss motion in projectile
More information(a) 1m s -2 (b) 2 m s -2 (c) zero (d) -1 m s -2
11 th Physics - Unit 2 Kinematics Solutions for the Textbook Problems One Marks 1. Which one of the followin Cartesian coordinate system is not followed in physics? 5. If a particle has neative velocity
More informationv( t) g 2 v 0 sin θ ( ) ( ) g t ( ) = 0
PROJECTILE MOTION Velocity We seek to explore the velocity of the projectile, includin its final value as it hits the round, or a taret above the round. The anle made by the velocity vector with the local
More informationRESISTANCE STRAIN GAGES FILLAMENTS EFFECT
RESISTANCE STRAIN GAGES FILLAMENTS EFFECT Nashwan T. Younis, Younis@enr.ipfw.edu Department of Mechanical Enineerin, Indiana University-Purdue University Fort Wayne, USA Bonsu Kan, kan@enr.ipfw.edu Department
More informationCh 14: Feedback Control systems
Ch 4: Feedback Control systems Part IV A is concerned with sinle loop control The followin topics are covered in chapter 4: The concept of feedback control Block diaram development Classical feedback controllers
More informationEdge Detection. Computer Vision P. Schrater Spring 2003
Edge Detection Computer Vision P. Schrater Spring 2003 Simplest Model: (Canny) Edge(x) = a U(x) + n(x) U(x)? x=0 Convolve image with U and find points with high magnitude. Choose value by comparing with
More informationMechanics Cycle 3 Chapter 12++ Chapter 12++ Revisit Circular Motion
Chapter 12++ Revisit Circular Motion Revisit: Anular variables Second laws for radial and tanential acceleration Circular motion CM 2 nd aw with F net To-Do: Vertical circular motion in ravity Complete
More informationTRACKING and DETECTION in COMPUTER VISION Filtering and edge detection
Technischen Universität München Winter Semester 0/0 TRACKING and DETECTION in COMPUTER VISION Filtering and edge detection Slobodan Ilić Overview Image formation Convolution Non-liner filtering: Median
More informationImage Analysis. Feature extraction: corners and blobs
Image Analysis Feature extraction: corners and blobs Christophoros Nikou cnikou@cs.uoi.gr Images taken from: Computer Vision course by Svetlana Lazebnik, University of North Carolina at Chapel Hill (http://www.cs.unc.edu/~lazebnik/spring10/).
More informationProblem Set 2 Solutions
UNIVERSITY OF ALABAMA Department of Physics and Astronomy PH 125 / LeClair Sprin 2009 Problem Set 2 Solutions The followin three problems are due 20 January 2009 at the beinnin of class. 1. (H,R,&W 4.39)
More informationHomework # 2. SOLUTION - We start writing Newton s second law for x and y components: F x = 0, (1) F y = mg (2) x (t) = 0 v x (t) = v 0x (3)
Physics 411 Homework # Due:..18 Mechanics I 1. A projectile is fired from the oriin of a coordinate system, in the x-y plane (x is the horizontal displacement; y, the vertical with initial velocity v =
More informationEdge Detection PSY 5018H: Math Models Hum Behavior, Prof. Paul Schrater, Spring 2005
Edge Detection PSY 5018H: Math Models Hum Behavior, Prof. Paul Schrater, Spring 2005 Gradients and edges Points of sharp change in an image are interesting: change in reflectance change in object change
More informationGround Rules. PC1221 Fundamentals of Physics I. Position and Displacement. Average Velocity. Lectures 7 and 8 Motion in Two Dimensions
PC11 Fundamentals of Physics I Lectures 7 and 8 Motion in Two Dimensions Dr Tay Sen Chuan 1 Ground Rules Switch off your handphone and paer Switch off your laptop computer and keep it No talkin while lecture
More informationDisclaimer: This lab write-up is not
Disclaimer: This lab write-up is not to be copied, in whole or in part, unless a proper reference is made as to the source. (It is stronly recommended that you use this document only to enerate ideas,
More informationEE 435 Lecture 13. Cascaded Amplifiers. -- Two-Stage Op Amp Design
EE 435 Lecture 13 ascaded Amplifiers -- Two-Stae Op Amp Desin Review from Last Time Routh-Hurwitz Stability riteria: A third-order polynomial s 3 +a 2 s 2 +a 1 s+a 0 has all poles in the LHP iff all coefficients
More informationIntroduction to Computer Vision
Introduction to Computer Vision Michael J. Black Sept 2009 Lecture 8: Pyramids and image derivatives Goals Images as functions Derivatives of images Edges and gradients Laplacian pyramids Code for lecture
More informationLecture 8: Interest Point Detection. Saad J Bedros
#1 Lecture 8: Interest Point Detection Saad J Bedros sbedros@umn.edu Last Lecture : Edge Detection Preprocessing of image is desired to eliminate or at least minimize noise effects There is always tradeoff
More informationImage Filtering. Slides, adapted from. Steve Seitz and Rick Szeliski, U.Washington
Image Filtering Slides, adapted from Steve Seitz and Rick Szeliski, U.Washington The power of blur All is Vanity by Charles Allen Gillbert (1873-1929) Harmon LD & JuleszB (1973) The recognition of faces.
More informationEmpirical Mean and Variance!
Global Image Properties! Global image properties refer to an image as a whole rather than components. Computation of global image properties is often required for image enhancement, preceding image analysis.!
More informationLecture 5 Processing microarray data
Lecture 5 Processin microarray data (1)Transform the data into a scale suitable for analysis ()Remove the effects of systematic and obfuscatin sources of variation (3)Identify discrepant observations Preprocessin
More informationA Mathematical Model for the Fire-extinguishing Rocket Flight in a Turbulent Atmosphere
A Mathematical Model for the Fire-extinuishin Rocket Fliht in a Turbulent Atmosphere CRISTINA MIHAILESCU Electromecanica Ploiesti SA Soseaua Ploiesti-Tiroviste, Km 8 ROMANIA crismihailescu@yahoo.com http://www.elmec.ro
More informationECE Digital Image Processing and Introduction to Computer Vision
ECE592-064 Digital Image Processing and Introduction to Computer Vision Depart. of ECE, NC State University Instructor: Tianfu (Matt) Wu Spring 2017 Outline Recap, image degradation / restoration Template
More informationAssignment 6. Name MULTIPLE CHOICE. Choose the one alternative that best completes the statement or answers the question.
Assinment 6 Name MULTIPLE CHOICE. Choose the one alternative that best completes the statement or answers the question. Round your answer, if appropriate. 1) A man 6 ft tall walks at a rate of 3 ft/sec
More informationAnother possibility is a rotation or reflection, represented by a matrix M.
1 Chapter 25: Planar defects Planar defects: orientation and types Crystalline films often contain internal, 2-D interfaces separatin two reions transformed with respect to one another, but with, otherwise,
More informationPhase Diagrams: construction and comparative statics
1 / 11 Phase Diarams: construction and comparative statics November 13, 215 Alecos Papadopoulos PhD Candidate Department of Economics, Athens University of Economics and Business papadopalex@aueb.r, https://alecospapadopoulos.wordpress.com
More informationFourier Optics and Image Analysis
Laboratory instruction to Fourier Optics and Imae Analysis Sven-Göran Pettersson and Anders Persson updated by Maïté Louisy and Henrik Ekerfelt This laboratory exercise demonstrates some important applications
More informationMultiscale Image Transforms
Multiscale Image Transforms Goal: Develop filter-based representations to decompose images into component parts, to extract features/structures of interest, and to attenuate noise. Motivation: extract
More informationAdjustment of Sampling Locations in Rail-Geometry Datasets: Using Dynamic Programming and Nonlinear Filtering
Systems and Computers in Japan, Vol. 37, No. 1, 2006 Translated from Denshi Joho Tsushin Gakkai Ronbunshi, Vol. J87-D-II, No. 6, June 2004, pp. 1199 1207 Adjustment of Samplin Locations in Rail-Geometry
More informationC. Non-linear Difference and Differential Equations: Linearization and Phase Diagram Technique
C. Non-linear Difference and Differential Equations: Linearization and Phase Diaram Technique So far we have discussed methods of solvin linear difference and differential equations. Let us now discuss
More informationMassachusetts Institute of Technology Department of Electrical Engineering and Computer Science
Massachusetts nstitute of Technoloy Department of Electrical Enineerin and Computer Science 6.685 Electric Machines Class Notes 2 Manetic Circuit Basics September 5, 2005 c 2003 James L. Kirtley Jr. 1
More informationLinearized optimal power flow
Linearized optimal power flow. Some introductory comments The advantae of the economic dispatch formulation to obtain minimum cost allocation of demand to the eneration units is that it is computationally
More informationGraph Entropy, Network Coding and Guessing games
Graph Entropy, Network Codin and Guessin ames Søren Riis November 25, 2007 Abstract We introduce the (private) entropy of a directed raph (in a new network codin sense) as well as a number of related concepts.
More informationJournal of Inequalities in Pure and Applied Mathematics
Journal of Inequalities in Pure and Applied Mathematics L HOSPITAL TYPE RULES FOR OSCILLATION, WITH APPLICATIONS IOSIF PINELIS Department of Mathematical Sciences, Michian Technoloical University, Houhton,
More informationLoG Blob Finding and Scale. Scale Selection. Blobs (and scale selection) Achieving scale covariance. Blob detection in 2D. Blob detection in 2D
Achieving scale covariance Blobs (and scale selection) Goal: independently detect corresponding regions in scaled versions of the same image Need scale selection mechanism for finding characteristic region
More informationVectors [and more on masks] Vector space theory applies directly to several image processing/ representation problems
Vectors [and more on masks] Vector space theory applies directly to several image processing/ representation problems 1 Image as a sum of basic images What if every person s portrait photo could be expressed
More informationAdvanced Edge Detection 1
Advanced Edge Detection 1 Lecture 4 See Sections 2.4 and 1.2.5 in Reinhard Klette: Concise Computer Vision Springer-Verlag, London, 2014 1 See last slide for copyright information. 1 / 27 Agenda 1 LoG
More informationA Multigrid-like Technique for Power Grid Analysis
A Multirid-like Technique for Power Grid Analysis Joseph N. Kozhaya, Sani R. Nassif, and Farid N. Najm 1 Abstract Modern sub-micron VLSI desins include hue power rids that are required to distribute lare
More informationf 1. (8.1.1) This means that SI unit for frequency is going to be s 1 also known as Hertz d1hz
ecture 8-1 Oscillations 1. Oscillations Simple Harmonic Motion So far we have considered two basic types of motion: translational motion and rotational motion. But these are not the only types of motion
More informationPyramid. Gaussian Pyramids
Comments Aorithm- orks ony or sma motion. I object moves aster the brihtness chanes rapidy x or 3x3 masks ai to estimate spatiotempora derivatives. Pyramids can be used to compute are optica o vectors.
More informationCSE 473/573 Computer Vision and Image Processing (CVIP)
CSE 473/573 Computer Vision and Image Processing (CVIP) Ifeoma Nwogu inwogu@buffalo.edu Lecture 11 Local Features 1 Schedule Last class We started local features Today More on local features Readings for
More informationLecture 04 Image Filtering
Institute of Informatics Institute of Neuroinformatics Lecture 04 Image Filtering Davide Scaramuzza 1 Lab Exercise 2 - Today afternoon Room ETH HG E 1.1 from 13:15 to 15:00 Work description: your first
More informationGeodesics as gravity
Geodesics as ravity February 8, 05 It is not obvious that curvature can account for ravity. The orbitin path of a planet, for example, does not immediately seem to be the shortest path between points.
More informationExam 2A Solution. 1. A baseball is thrown vertically upward and feels no air resistance. As it is rising
Exam 2A Solution 1. A baseball is thrown vertically upward and feels no air resistance. As it is risin Solution: Possible answers: A) both its momentum and its mechanical enery are conserved - incorrect.
More informationPIRATE SHIP EXAMPLE REPORT WRITE UP
PIRATE SHIP EXAMPE REPORT WRITE UP Title Aim period Pirate Ship investiation To find the relationship between the lenth of a pendulum and its Independent variable the lenth of the pendulum. I will use
More informationAnnouncements. Filtering. Image Filtering. Linear Filters. Example: Smoothing by Averaging. Homework 2 is due Apr 26, 11:59 PM Reading:
Announcements Filtering Homework 2 is due Apr 26, :59 PM eading: Chapter 4: Linear Filters CSE 52 Lecture 6 mage Filtering nput Output Filter (From Bill Freeman) Example: Smoothing by Averaging Linear
More information1999 AAPT PHYSICS OLYMPIAD
1999 AAPT PHYSICS OLYMPIAD Entia non multiplicanda sunt praeter necessitatem 1999 MULTIPLE CHOICE SCREENING TEST 30 QUESTIONS - 40 MINUTES INSTRUCTIONS DO NOT OPEN THIS TEST UNTIL YOU ARE TOLD TO BEGIN
More informationAAPT UNITED STATES PHYSICS TEAM AIP 2009
2009 F = ma Exam 1 AAPT UNITED STATES PHYSICS TEAM AIP 2009 2009 F = ma Contest 25 QUESTIONS - 75 MINUTES INSTRUCTIONS DO NOT OPEN THIS TEST UNTI YOU ARE TOD TO BEGIN Use = 10 N/k throuhout this contest.
More informationInvestigation of ternary systems
Investiation of ternary systems Introduction The three component or ternary systems raise not only interestin theoretical issues, but also have reat practical sinificance, such as metallury, plastic industry
More informationInteractions with Matter
Manetic Lenses Manetic fields can displace electrons Manetic field can be produced by passin an electrical current throuh coils of wire Manetic field strenth can be increased by usin a soft ferromanetic
More informationV DD. M 1 M 2 V i2. V o2 R 1 R 2 C C
UNVERSTY OF CALFORNA Collee of Enineerin Department of Electrical Enineerin and Computer Sciences E. Alon Homework #3 Solutions EECS 40 P. Nuzzo Use the EECS40 90nm CMOS process in all home works and projects
More informationFirst- and Second Order Phase Transitions in the Holstein- Hubbard Model
Europhysics Letters PREPRINT First- and Second Order Phase Transitions in the Holstein- Hubbard Model W. Koller 1, D. Meyer 1,Y.Ōno 2 and A. C. Hewson 1 1 Department of Mathematics, Imperial Collee, London
More informationAchieving scale covariance
Achieving scale covariance Goal: independently detect corresponding regions in scaled versions of the same image Need scale selection mechanism for finding characteristic region size that is covariant
More informationWhat types of isometric transformations are we talking about here? One common case is a translation by a displacement vector R.
1. Planar Defects Planar defects: orientation and types Crystalline films often contain internal, -D interfaces separatin two reions transformed with respect to one another, but with, otherwise, essentially,
More informationMASSACHUSETTS INSTITUTE OF TECHNOLOGY Department of Physics. Physics 8.01x Fall Term 2001 EXAM 1 SOLUTIONS
MASSACHUSETTS INSTITUTE OF TECHNOLOGY Department of Physics Physics 8.01x Fall Term 2001 EXAM 1 SOLUTIONS Problem 1: We define a vertical coordinate system with positive upwards. The only forces actin
More informationTranslations on graphs with neighborhood preservation
1 Translations on raphs with neihborhood preservation Bastien Pasdeloup, Vincent Gripon, Nicolas Grelier, Jean-harles Vialatte, Dominique Pastor arxiv:1793859v1 [csdm] 12 Sep 217 Abstract In the field
More informationViscoData & ViscoShift
Introductory Theory Manual ViscoData & ViscoShift (Preliminary Version) Contents ) Preface 2) Introduction 3) Dynamic mechanical properties 4) sin ViscoShift and ViscoData 5) Concludin remarks 6) Refereces
More informationImpulse Response and Generating Functions of sinc N FIR Filters
ICDT 20 : The Sixth International Conference on Diital Telecommunications Impulse Response and eneratin Functions of sinc FIR Filters J. Le Bihan Laboratoire RESO Ecole ationale d'inénieurs de Brest (EIB)
More informationToward a Realization of Marr s Theory of Primal Sketches via Autocorrelation Wavelets: Image Representation using Multiscale Edge Information
Toward a Realization of Marr s Theory of Primal Sketches via Autocorrelation Wavelets: Image Representation using Multiscale Edge Information Naoki Saito 1 Department of Mathematics University of California,
More informationTwo-step Anomalous Diffusion Tensor Imaging
Two-step Anomalous Diffusion Tensor Imain Thomas R. Barrick 1, Matthew G. Hall 2 1 Centre for Stroke and Dementia, Division of Cardiac and Vascular Sciences, St. Geore s University of London, 2 Department
More informationModeling for control of a three degrees-of-freedom Magnetic. Levitation System
Modelin for control of a three derees-of-freedom Manetic evitation System Rafael Becerril-Arreola Dept. of Electrical and Computer En. University of Toronto Manfredi Maiore Dept. of Electrical and Computer
More informationDISCRETE FOURIER TRANSFORM
DD2423 Image Processing and Computer Vision DISCRETE FOURIER TRANSFORM Mårten Björkman Computer Vision and Active Perception School of Computer Science and Communication November 1, 2012 1 Terminology:
More informationRenormalization Group Theory
Chapter 16 Renormalization Group Theory In the previous chapter a procedure was developed where hiher order 2 n cycles were related to lower order cycles throuh a functional composition and rescalin procedure.
More informationPhysicsAndMathsTutor.com
. A particle of mass m is projected vertically upwards, at time t =, with speed. The particle is mv subject to air resistance of manitude, where v is the speed of the particle at time t and is a positive
More informationConvolutional networks. Sebastian Seung
Convolutional networks Sebastian Seung Convolutional network Neural network with spatial organization every neuron has a location usually on a grid Translation invariance synaptic strength depends on locations
More informationOptimal decoding of cellular identities in a genetic network
Optimal decodin of cellular identities in a enetic network Mariela D. Petkova, a,b,e, Gašper Tkačik, f, William Bialek, a,b Eric F. Wieschaus, b,c,d and Thomas Greor a,b,, a Joseph Henry Laboratories of
More informationFLUID flow in a slightly inclined rectangular open
Numerical Solution of de St. Venant Equations with Controlled Global Boundaries Between Unsteady Subcritical States Aldrin P. Mendoza, Adrian Roy L. Valdez, and Carlene P. Arceo Abstract This paper aims
More informationDirection of Hurricane Beta Drift in Horizontally Sheared Flows
146 JOURNAL OF THE ATMOSPHERIC SCIENCES VOLUME 54 Direction of Hurricane Beta Drift in Horizontally Sheared Flows BIN WANG, XIAOFAN LI,* AND LIGUANG WU Department of Meteoroloy, School of Ocean and Earth
More informationI Chen Lin, Assistant Professor Dept. of CS, National Chiao Tung University. Computer Vision: 4. Filtering
I Chen Lin, Assistant Professor Dept. of CS, National Chiao Tung University Computer Vision: 4. Filtering Outline Impulse response and convolution. Linear filter and image pyramid. Textbook: David A. Forsyth
More information