EE 6882 Visual Search Engine
|
|
- Cecilia Sparks
- 5 years ago
- Views:
Transcription
1 /0/0 EE 688 Visual Search Engine Prof. Shih Fu Chang, Jan. 0, 0 Lecture # Visual Features: Global features and matching Evaluation metrics (Many slides from. Efors, W. Freeman, C. Kambhamettu, L. Xie, and likely others) (Slides preparation assisted by Rong Rong Ji) Course Format Lectures + two hands on homeworks (due /, /7) Mid term proect Review and implement topics of interest, students each team Proposal due /5, narrated slides due /6 Selected proects presented and discussed in class (/6 4/9) Final proect Extension of mid term proects encouraged, students each team Proposal due 4/, narrated slides due 4/0 Selected proects presented and discussed in class (4/0 5/7) Grading: Class participation (0%), homework (0%), mid term (0%), final (40%) Late policy: a total budget of 4 days for late submissions. No other delays accepted.
2 /0/ Image Features Why features are needed? Finding similar images in database Classifying images to categories Tracking obects in video Creating panorama Stereo matching > D Desired properties Compact (~ dimensions) Easy to compute (0 fps for video) Robust (invariant to photometric, geometric, content variations) photoguides.net merl.com Desired Properties of Visual Features Invariance: Rotation, scaling, cropping, shift, etc. illumination, pose, clutter, occlusion, viewpoint
3 /0/0 Invariant Local Features Image content is transformed into local feature coordinates that are invariant to translation, rotation, scale, and other imaging parameters Features Descriptors (Slide of. Efros) (review) Imaging Formation irradiance Lens CCD Sensor dditive Noise R G R G R G G G R G R G R G G G R G R G R Demosaicking Filter Camera Response Function DSP (White alance, Contrast Enhancement etc) Image intensity 6
4 /0/0 Color Spaces and Color Order Systems Color Spaces RG cube in Euclidean space R G r g b R G RG RG Standard representation used in color displays Drawbacks RG basis not related to human color udgments Intensity should be one of the dimensions of color Important perceptual components of color are hue, saturation, and brightness Perceptual color spaces: HIS, HSV Understanding HSI from RG Turn the RG cube so that lack White axis is vertical Each plane containing the W axis and a color point contains all the colors of the same hue Hue represented as angle between the plane and a reference plane (e.g. Red) Saturation: distance to axis, less saturated by mixing more grey colors Intensity measured by intersection with the W axis. Cross section shape: triangle hexagon triangle 8 Images from Gonzalez and Woods 4
5 /0/0 Colors on the HSI color cone Cross section approximated by triangle or circle HSI values computed by various geometrical models, e.g., I / V / 6 V / 6 / / 6 / 6 / R / 6 G 0 V H tan ( ) V Chroma ( V V / ) More suitable for measuring perceptual distance Can be quantized unevenly, e.g., Columbia VisualSEEK System: 6M colors (in RG) quantized to 66 HSV colors (8 Hue, Sat, Val, 4 Gray) 9 Manipulations in the HSI space HSI values of primary/secondary colors HSI allows independent manipulations of colors Hue of Green & lue set to 0. Saturation of Cyan reduced by half. Intensity of White reduced by half. 0 5
6 /0/0 Color Histogram Feature extraction from color images h RG Choose GOOD color space Quantize color space to reduce number of colors [, r g, b] Invariance? m n if IR[ m, n] r, IG[ m, n] g, I[ m, n] b 0 otherwise Scale, shift, rotation, crop, view angle, illumination, clutter, occlusion dvantages Easy to compute and compare Cons Lack spatial information, dimension may be high Color Moments Is there a more compact representation than color histogram? Compute moment statistics in each color channel.? 6
7 /0/0 Localizing Color Layout Search Columbia VisualSEEk (Smith & Chang, 96) IM QIC (Flickner et al 95) Query results 7
8 /0/0 Color correlogram 8
9 /0/0 Color Coherence Vector (CCV) (Pass et al, 997) Region segmentation C C C D E E E E E Not ust count of colors, also check adacency regions color size 5 C D E 5 Coherent! Size threshold: CCV color 5 0 5,,...,,,,...,, G G I n n I n n n = = G i i i i H i i i i i i G H by triangular inequality n 9
10 /0/0 Distance Metrics between Feature Vectors Lp distance Quadratic distance D q ( x D p ( x ( x i ) i x ( i ) x T C ( x p / p ( i) x( i) ) x ( i ) C ( i, ) x ) ( ) x ( ) ) C(i,): color distance Histogram Intersection Mohalanobis distance Normalize distance in the maor/minor axes where C x is the covariance matrix Mohalanobis Metric T mah x D x x C x x covariance matrix C N k x c(,) c(, )... c(, d) d: dimension of features cd (,) cd (,)... cdd (, ) c(, i ) x k() i m() i x k( ) m( ) / N, N : number of samples x x x x x o o o o o oo o o o o o o o o o o oo o o o x i x i x i x i x c s i is c s i s c 0 c s i s c s is s i, s : std. deviation 0
11 /0/0 Mohalanobis Metric where C x is the covariance matrix T Cx e e... ed diag(,,..., d) e e... ed Cx e e... ed ( diag(,,..., d)) e e... ed T e e Normalize distance in the eigen vector axes Proect data to the eigen vectors, divide with the sd of each eigen dimension, and compute Euclidian distance Mohalanobis Metric (cont.) dvantages of Mahalanobis metric ccount for scaling of coordinate axes Invariant under linear transformation T If y x Cy Cx, Dy Dx Correct for correlation Produce curved as well as linear decision boundaries cm km x i m c m c c c Maha. Dist. Maha. Dist. Minimum Selector Selected class Potential issue Need enough training data to estimate Cov. Matrix
12 /0/0 Earth Mover s Distance (EMD) Rubner, Tomasi, Guibas 98 Mallow s distance in statistics in 950 s Transportation Problem [Dantzig 5] I: set of suppliers J: set of consumers c i : cost of shipping a unit of supply from i to I c i J Problem: find the optimal flows f i minimize c f s.t. ii ii i i fi 0, i I, J (No reverse shipping) f y, J (satisfy each consumer need /cacacity) ii J J i f x, i I (bounded by each supplier's limit) i i y x ( feasibility) ii i EMD of Color Histogram h h, h,..., h M, g= g, g,..., h N, assume g( ) h( i) EMD h, g M N Ci fi i M N fi i M N N i i / i Earth Hole = C f g Fill up each hole C i : distance between color i in color space h and color in color space g f : move f units of mass from color i in h to color in g i i Normalization by the denominator term void bias toward low mass distributions (i.e., small images) what s the difference if both h and g are normalized first? i
13 /0/0 Evaluation Ground truth " Relevant" V n Detection False larms Misses 0 " Irrelevant " Returned Correct Dismissals Relevant Results D C C D n 0 N - ( ( K V n0 n K n0 ( V ) N n0 n N n0 n V ) ( V )) n search D N Images K Returned Results Recall R /( C ) Precision P /( ) Fallout F /( D) P R Combined F ( P R) / Evaluation Measures Precision at depth K k Pk ( n0vn ) / K Precision Recall Curve P ( P vs R ) Receiver Operating Characteristic (ROC Curve) (hit) vs (false) R
14 /0/0 Evaluation Metric: verage Precision P approximates areas under PR curve K P [ P I ( D min( K, R ) Example: R : total # of Ground truth Precision relevant Ranked list of data in response to a query D D D D D 5 / Precision / data, 6 / /4 is correct I : indicator 0 /5 0 /6 0 s /7 Pi P )] function Evaluation Metric: verage Precision Observations (P) P depends on the rankings of relevant data and the size of the relevant data set. E.g., R=0 Case I: Pre: P= Case II: - + Pre: / Case II: Pre: / / / / / / / / / / / 0/0 P=/ P~0. 4
15 /0/0 Homework # Given a small image database and a few queries Implement codes to extract color histogram Implement codes to measure L image similarity Use image obect labels to measure precision/recall curves onus: dd new color features or similarity metrics to improve performance Design GUI for result browsing Reading List Rui, Y., T.S. Huang, and S. F. Chang, Image retrieval: current techniques, promising directions and open issues. Journal of Visual Communication and Image Representation, (4): p Smith, J.R. and S. F. Chang. VisualSEEk: a Fully utomated Content ased Image Query System. in CM International Conference on Multimedia oston, M. David G. Lowe, Distinctive Image Features from Scale Invariant Keypoints, International Journal of Computer Vision, 60(), 004, pp9 0. Randen, T. and J. Husoy, Filtering for texture classification: comparative study. Pattern nalysis and Machine Intelligence, IEEE Transactions on, 00. (4): p Mikolaczyk, K. and C. Schmid, performance evaluation of local descriptors. IEEE Transactions on Pattern nalysis and Machine Intelligence, 005: p rown, M., R. Szeliski, and S. Winder. Multi image matching using multi scale oriented patches. in IEEE CVPR
Corners, Blobs & Descriptors. With slides from S. Lazebnik & S. Seitz, D. Lowe, A. Efros
Corners, Blobs & Descriptors With slides from S. Lazebnik & S. Seitz, D. Lowe, A. Efros Motivation: Build a Panorama M. Brown and D. G. Lowe. Recognising Panoramas. ICCV 2003 How do we build panorama?
More informationFeature extraction: Corners and blobs
Feature extraction: Corners and blobs Review: Linear filtering and edge detection Name two different kinds of image noise Name a non-linear smoothing filter What advantages does median filtering have over
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 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 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 informationCITS 4402 Computer Vision
CITS 4402 Computer Vision A/Prof Ajmal Mian Adj/A/Prof Mehdi Ravanbakhsh Lecture 06 Object Recognition Objectives To understand the concept of image based object recognition To learn how to match images
More informationShape of Gaussians as Feature Descriptors
Shape of Gaussians as Feature Descriptors Liyu Gong, Tianjiang Wang and Fang Liu Intelligent and Distributed Computing Lab, School of Computer Science and Technology Huazhong University of Science and
More informationAdvances in Computer Vision. Prof. Bill Freeman. Image and shape descriptors. Readings: Mikolajczyk and Schmid; Belongie et al.
6.869 Advances in Computer Vision Prof. Bill Freeman March 3, 2005 Image and shape descriptors Affine invariant features Comparison of feature descriptors Shape context Readings: Mikolajczyk and Schmid;
More informationBlobs & Scale Invariance
Blobs & Scale Invariance Prof. Didier Stricker Doz. Gabriele Bleser Computer Vision: Object and People Tracking With slides from Bebis, S. Lazebnik & S. Seitz, D. Lowe, A. Efros 1 Apertizer: some videos
More informationEE 6882 Visual Search Engine
EE 6882 Visual Search Engine Prof. Shih Fu Chang, Feb. 13 th 2012 Lecture #4 Local Feature Matching Bag of Word image representation: coding and pooling (Many slides from A. Efors, W. Freeman, C. Kambhamettu,
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 informationDetectors part II Descriptors
EECS 442 Computer vision Detectors part II Descriptors Blob detectors Invariance Descriptors Some slides of this lectures are courtesy of prof F. Li, prof S. Lazebnik, and various other lecturers Goal:
More informationRecap: edge detection. Source: D. Lowe, L. Fei-Fei
Recap: edge detection Source: D. Lowe, L. Fei-Fei Canny edge detector 1. Filter image with x, y derivatives of Gaussian 2. Find magnitude and orientation of gradient 3. Non-maximum suppression: Thin multi-pixel
More information6.869 Advances in Computer Vision. Prof. Bill Freeman March 1, 2005
6.869 Advances in Computer Vision Prof. Bill Freeman March 1 2005 1 2 Local Features Matching points across images important for: object identification instance recognition object class recognition pose
More informationCS5670: Computer Vision
CS5670: Computer Vision Noah Snavely Lecture 5: Feature descriptors and matching Szeliski: 4.1 Reading Announcements Project 1 Artifacts due tomorrow, Friday 2/17, at 11:59pm Project 2 will be released
More informationFeature detectors and descriptors. Fei-Fei Li
Feature detectors and descriptors Fei-Fei Li Feature Detection e.g. DoG detected points (~300) coordinates, neighbourhoods Feature Description e.g. SIFT local descriptors (invariant) vectors database of
More informationInstance-level l recognition. Cordelia Schmid INRIA
nstance-level l recognition Cordelia Schmid NRA nstance-level recognition Particular objects and scenes large databases Application Search photos on the web for particular places Find these landmars...in
More informationSIFT: Scale Invariant Feature Transform
1 SIFT: Scale Invariant Feature Transform With slides from Sebastian Thrun Stanford CS223B Computer Vision, Winter 2006 3 Pattern Recognition Want to find in here SIFT Invariances: Scaling Rotation Illumination
More informationVisual Object Recognition
Visual Object Recognition Lecture 2: Image Formation Per-Erik Forssén, docent Computer Vision Laboratory Department of Electrical Engineering Linköping University Lecture 2: Image Formation Pin-hole, and
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 informationUncertainty Models in Quasiconvex Optimization for Geometric Reconstruction
Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction Qifa Ke and Takeo Kanade Department of Computer Science, Carnegie Mellon University Email: ke@cmu.edu, tk@cs.cmu.edu Abstract
More informationCS 3710: Visual Recognition Describing Images with Features. Adriana Kovashka Department of Computer Science January 8, 2015
CS 3710: Visual Recognition Describing Images with Features Adriana Kovashka Department of Computer Science January 8, 2015 Plan for Today Presentation assignments + schedule changes Image filtering Feature
More informationScale & Affine Invariant Interest Point Detectors
Scale & Affine Invariant Interest Point Detectors Krystian Mikolajczyk and Cordelia Schmid Presented by Hunter Brown & Gaurav Pandey, February 19, 2009 Roadmap: Motivation Scale Invariant Detector Affine
More informationFeature detectors and descriptors. Fei-Fei Li
Feature detectors and descriptors Fei-Fei Li Feature Detection e.g. DoG detected points (~300) coordinates, neighbourhoods Feature Description e.g. SIFT local descriptors (invariant) vectors database of
More informationBlob Detection CSC 767
Blob Detection CSC 767 Blob detection Slides: S. Lazebnik Feature detection with scale selection We want to extract features with characteristic scale that is covariant with the image transformation Blob
More informationINTEREST POINTS AT DIFFERENT SCALES
INTEREST POINTS AT DIFFERENT SCALES Thank you for the slides. They come mostly from the following sources. Dan Huttenlocher Cornell U David Lowe U. of British Columbia Martial Hebert CMU Intuitively, junctions
More informationIntroduction to Computer Vision
Introduction to Computer Vision Michael J. Black Oct. 2009 Lecture 10: Images as vectors. Appearance-based models. News Assignment 1 parts 3&4 extension. Due tomorrow, Tuesday, 10/6 at 11am. Goals Images
More informationRapid Object Recognition from Discriminative Regions of Interest
Rapid Object Recognition from Discriminative Regions of Interest Gerald Fritz, Christin Seifert, Lucas Paletta JOANNEUM RESEARCH Institute of Digital Image Processing Wastiangasse 6, A-81 Graz, Austria
More informationLecture 12. Local Feature Detection. Matching with Invariant Features. Why extract features? Why extract features? Why extract features?
Lecture 1 Why extract eatures? Motivation: panorama stitching We have two images how do we combine them? Local Feature Detection Guest lecturer: Alex Berg Reading: Harris and Stephens David Lowe IJCV We
More informationFeature Vector Similarity Based on Local Structure
Feature Vector Similarity Based on Local Structure Evgeniya Balmachnova, Luc Florack, and Bart ter Haar Romeny Eindhoven University of Technology, P.O. Box 53, 5600 MB Eindhoven, The Netherlands {E.Balmachnova,L.M.J.Florack,B.M.terHaarRomeny}@tue.nl
More informationMultiscale Autoconvolution Histograms for Affine Invariant Pattern Recognition
Multiscale Autoconvolution Histograms for Affine Invariant Pattern Recognition Esa Rahtu Mikko Salo Janne Heikkilä Department of Electrical and Information Engineering P.O. Box 4500, 90014 University of
More informationInternational Journal of Computer Engineering and Applications, Volume XII, Special Issue, August 18, ISSN
International Journal of Computer Engineering and Applications, Volume XII, Special Issue, August 18, www.ijcea.com ISSN 2321-3469 CONTENT-BASED IMAGE RETRIEVAL USING ZERNIKE MOMENTS AND SURF Priyanka
More informationRESTORATION OF VIDEO BY REMOVING RAIN
RESTORATION OF VIDEO BY REMOVING RAIN Sajitha Krishnan 1 and D.Venkataraman 1 1 Computer Vision and Image Processing, Department of Computer Science, Amrita Vishwa Vidyapeetham University, Coimbatore,
More informationInstance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble
nstance-level recognition: ocal invariant features Cordelia Schmid NRA Grenoble Overview ntroduction to local features Harris interest points + SSD ZNCC SFT Scale & affine invariant interest point detectors
More informationSIFT keypoint detection. D. Lowe, Distinctive image features from scale-invariant keypoints, IJCV 60 (2), pp , 2004.
SIFT keypoint detection D. Lowe, Distinctive image features from scale-invariant keypoints, IJCV 60 (), pp. 91-110, 004. Keypoint detection with scale selection We want to extract keypoints with characteristic
More informationStephen Scott.
1 / 35 (Adapted from Ethem Alpaydin and Tom Mitchell) sscott@cse.unl.edu In Homework 1, you are (supposedly) 1 Choosing a data set 2 Extracting a test set of size > 30 3 Building a tree on the training
More informationA METHOD OF FINDING IMAGE SIMILAR PATCHES BASED ON GRADIENT-COVARIANCE SIMILARITY
IJAMML 3:1 (015) 69-78 September 015 ISSN: 394-58 Available at http://scientificadvances.co.in DOI: http://dx.doi.org/10.1864/ijamml_710011547 A METHOD OF FINDING IMAGE SIMILAR PATCHES BASED ON GRADIENT-COVARIANCE
More informationOriginal Article Design Approach for Content-Based Image Retrieval Using Gabor-Zernike Features
International Archive of Applied Sciences and Technology Volume 3 [2] June 2012: 42-46 ISSN: 0976-4828 Society of Education, India Website: www.soeagra.com/iaast/iaast.htm Original Article Design Approach
More informationFace detection and recognition. Detection Recognition Sally
Face detection and recognition Detection Recognition Sally Face detection & recognition Viola & Jones detector Available in open CV Face recognition Eigenfaces for face recognition Metric learning identification
More informationPerformance Metrics for Machine Learning. Sargur N. Srihari
Performance Metrics for Machine Learning Sargur N. srihari@cedar.buffalo.edu 1 Topics 1. Performance Metrics 2. Default Baseline Models 3. Determining whether to gather more data 4. Selecting hyperparamaters
More information1 FUNDAMENTALS OF. Proof. Dr. Fuhui Long, Dr. Hongjiang Zhang and Prof. David Dagan Feng
1 FUNDAMENTALS OF Proof CONTENT-BASED IMAGE RETRIEVAL Dr. Fuhui Long, Dr. Hongjiang Zhang and Prof. David Dagan Feng We introduce in this chapter some fundamental theories for content-based image retrieval.
More informationRiemannian Metric Learning for Symmetric Positive Definite Matrices
CMSC 88J: Linear Subspaces and Manifolds for Computer Vision and Machine Learning Riemannian Metric Learning for Symmetric Positive Definite Matrices Raviteja Vemulapalli Guide: Professor David W. Jacobs
More informationLinear Classifiers as Pattern Detectors
Intelligent Systems: Reasoning and Recognition James L. Crowley ENSIMAG 2 / MoSIG M1 Second Semester 2013/2014 Lesson 18 23 April 2014 Contents Linear Classifiers as Pattern Detectors Notation...2 Linear
More informationHuman Action Recognition under Log-Euclidean Riemannian Metric
Human Action Recognition under Log-Euclidean Riemannian Metric Chunfeng Yuan, Weiming Hu, Xi Li, Stephen Maybank 2, Guan Luo, National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing,
More informationMetric Embedding of Task-Specific Similarity. joint work with Trevor Darrell (MIT)
Metric Embedding of Task-Specific Similarity Greg Shakhnarovich Brown University joint work with Trevor Darrell (MIT) August 9, 2006 Task-specific similarity A toy example: Task-specific similarity A toy
More informationImage Characteristics
1 Image Characteristics Image Mean I I av = i i j I( i, j 1 j) I I NEW (x,y)=i(x,y)-b x x Changing the image mean Image Contrast The contrast definition of the entire image is ambiguous In general it is
More informationAdvanced Features. Advanced Features: Topics. Jana Kosecka. Slides from: S. Thurn, D. Lowe, Forsyth and Ponce. Advanced features and feature matching
Advanced Features Jana Kosecka Slides from: S. Thurn, D. Lowe, Forsyth and Ponce Advanced Features: Topics Advanced features and feature matching Template matching SIFT features Haar features 2 1 Features
More informationMachine Learning (CS 567) Lecture 5
Machine Learning (CS 567) Lecture 5 Time: T-Th 5:00pm - 6:20pm Location: GFS 118 Instructor: Sofus A. Macskassy (macskass@usc.edu) Office: SAL 216 Office hours: by appointment Teaching assistant: Cheol
More informationThe state of the art and beyond
Feature Detectors and Descriptors The state of the art and beyond Local covariant detectors and descriptors have been successful in many applications Registration Stereo vision Motion estimation Matching
More informationLeast Squares Classification
Least Squares Classification Stephen Boyd EE103 Stanford University November 4, 2017 Outline Classification Least squares classification Multi-class classifiers Classification 2 Classification data fitting
More informationLec 12 Review of Part I: (Hand-crafted) Features and Classifiers in Image Classification
Image Analysis & Retrieval Spring 2017: Image Analysis Lec 12 Review of Part I: (Hand-crafted) Features and Classifiers in Image Classification Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu,
More informationObject Recognition Using Local Characterisation and Zernike Moments
Object Recognition Using Local Characterisation and Zernike Moments A. Choksuriwong, H. Laurent, C. Rosenberger, and C. Maaoui Laboratoire Vision et Robotique - UPRES EA 2078, ENSI de Bourges - Université
More informationComputer Assisted Image Analysis
Computer Assisted Image Analysis Lecture 0 - Object Descriptors II Amin Allalou amin@cb.uu.se Centre for Image Analysis Uppsala University 2009-04-27 A. Allalou (Uppsala University) Object Descriptors
More informationKeypoint extraction: Corners Harris Corners Pkwy, Charlotte, NC
Kepoint etraction: Corners 9300 Harris Corners Pkw Charlotte NC Wh etract kepoints? Motivation: panorama stitching We have two images how do we combine them? Wh etract kepoints? Motivation: panorama stitching
More informationThe Detection Techniques for Several Different Types of Fiducial Markers
Vol. 1, No. 2, pp. 86-93(2013) The Detection Techniques for Several Different Types of Fiducial Markers Chuen-Horng Lin 1,*,Yu-Ching Lin 1,and Hau-Wei Lee 2 1 Department of Computer Science and Information
More informationECE 661: Homework 10 Fall 2014
ECE 661: Homework 10 Fall 2014 This homework consists of the following two parts: (1) Face recognition with PCA and LDA for dimensionality reduction and the nearest-neighborhood rule for classification;
More informationBasic Concepts of. Feature Selection
Basic Concepts of Pattern Recognition and Feature Selection Xiaojun Qi -- REU Site Program in CVMA (2011 Summer) 1 Outline Pattern Recognition Pattern vs. Features Pattern Classes Classification Feature
More informationAruna Bhat Research Scholar, Department of Electrical Engineering, IIT Delhi, India
International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2017 IJSRCSEIT Volume 2 Issue 6 ISSN : 2456-3307 Robust Face Recognition System using Non Additive
More informationMultiple Similarities Based Kernel Subspace Learning for Image Classification
Multiple Similarities Based Kernel Subspace Learning for Image Classification Wang Yan, Qingshan Liu, Hanqing Lu, and Songde Ma National Laboratory of Pattern Recognition, Institute of Automation, Chinese
More informationFace recognition Computer Vision Spring 2018, Lecture 21
Face recognition http://www.cs.cmu.edu/~16385/ 16-385 Computer Vision Spring 2018, Lecture 21 Course announcements Homework 6 has been posted and is due on April 27 th. - Any questions about the homework?
More informationRegion Moments: Fast invariant descriptors for detecting small image structures
Region Moments: Fast invariant descriptors for detecting small image structures Gianfranco Doretto Yi Yao Visualization and Computer Vision Lab, GE Global Research, Niskayuna, NY 39 doretto@research.ge.com
More informationHarris Corner Detector
Multimedia Computing: Algorithms, Systems, and Applications: Feature Extraction By Dr. Yu Cao Department of Computer Science The University of Massachusetts Lowell Lowell, MA 01854, USA Part of the slides
More informationProperties of detectors Edge detectors Harris DoG Properties of descriptors SIFT HOG Shape context
Lecture 10 Detectors and descriptors Properties of detectors Edge detectors Harris DoG Properties of descriptors SIFT HOG Shape context Silvio Savarese Lecture 10-16-Feb-15 From the 3D to 2D & vice versa
More informationLECTURE NOTE #3 PROF. ALAN YUILLE
LECTURE NOTE #3 PROF. ALAN YUILLE 1. Three Topics (1) Precision and Recall Curves. Receiver Operating Characteristic Curves (ROC). What to do if we do not fix the loss function? (2) The Curse of Dimensionality.
More informationINF Introduction to classifiction Anne Solberg
INF 4300 8.09.17 Introduction to classifiction Anne Solberg anne@ifi.uio.no Introduction to classification Based on handout from Pattern Recognition b Theodoridis, available after the lecture INF 4300
More informationClassifying Galaxy Morphology using Machine Learning
Julian Kates-Harbeck, Introduction: Classifying Galaxy Morphology using Machine Learning The goal of this project is to classify galaxy morphologies. Generally, galaxy morphologies fall into one of two
More informationLecture 13 Visual recognition
Lecture 13 Visual recognition Announcements Silvio Savarese Lecture 13-20-Feb-14 Lecture 13 Visual recognition Object classification bag of words models Discriminative methods Generative methods Object
More informationBiometrics: Introduction and Examples. Raymond Veldhuis
Biometrics: Introduction and Examples Raymond Veldhuis 1 Overview Biometric recognition Face recognition Challenges Transparent face recognition Large-scale identification Watch list Anonymous biometrics
More informationLecture 3: Pattern Classification. Pattern classification
EE E68: Speech & Audio Processing & Recognition Lecture 3: Pattern Classification 3 4 5 The problem of classification Linear and nonlinear classifiers Probabilistic classification Gaussians, mitures and
More informationMaximally Stable Local Description for Scale Selection
Maximally Stable Local Description for Scale Selection Gyuri Dorkó and Cordelia Schmid INRIA Rhône-Alpes, 655 Avenue de l Europe, 38334 Montbonnot, France {gyuri.dorko,cordelia.schmid}@inrialpes.fr Abstract.
More informationDeformation and Viewpoint Invariant Color Histograms
1 Deformation and Viewpoint Invariant Histograms Justin Domke and Yiannis Aloimonos Computer Vision Laboratory, Department of Computer Science University of Maryland College Park, MD 274, USA domke@cs.umd.edu,
More informationUniversity of Cambridge Engineering Part IIB Module 3F3: Signal and Pattern Processing Handout 2:. The Multivariate Gaussian & Decision Boundaries
University of Cambridge Engineering Part IIB Module 3F3: Signal and Pattern Processing Handout :. The Multivariate Gaussian & Decision Boundaries..15.1.5 1 8 6 6 8 1 Mark Gales mjfg@eng.cam.ac.uk Lent
More informationWavelet-based Salient Points with Scale Information for Classification
Wavelet-based Salient Points with Scale Information for Classification Alexandra Teynor and Hans Burkhardt Department of Computer Science, Albert-Ludwigs-Universität Freiburg, Germany {teynor, Hans.Burkhardt}@informatik.uni-freiburg.de
More informationPedestrian Density Estimation by a Weighted Bag of Visual Words Model
Pedestrian Density Estimation by a Weighted Bag of Visual Words Model Shilin Zhang and Xunyuan Zhang image representation termed bag of visual words integrating weighting scheme and spatial pyramid co-occurrence,
More informationInstance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble
nstance-level recognition: ocal invariant features Cordelia Schmid NRA Grenoble Overview ntroduction to local features Harris interest points + SSD ZNCC SFT Scale & affine invariant interest point detectors
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 informationLecture 7: Finding Features (part 2/2)
Lecture 7: Finding Features (part 2/2) Dr. Juan Carlos Niebles Stanford AI Lab Professor Fei- Fei Li Stanford Vision Lab 1 What we will learn today? Local invariant features MoPvaPon Requirements, invariances
More informationMachine Learning. for Image Retrieval. Edward Chang Associate Professor, Electrical Engineering, UC Santa Barbara CTO, VIMA Technologies
Machine Learning for Image Retrieval Edward Chang Associate Professor, Electrical Engineering, UC Santa Barbara CTO, VIMA Technologies 4/5/2004 JHU-APL 1 Are They Similar? 4/5/2004 JHU-APL 2 Are They Similar?
More information9.5. Polynomial and Rational Inequalities. Objectives. Solve quadratic inequalities. Solve polynomial inequalities of degree 3 or greater.
Chapter 9 Section 5 9.5 Polynomial and Rational Inequalities Objectives 1 3 Solve quadratic inequalities. Solve polynomial inequalities of degree 3 or greater. Solve rational inequalities. Objective 1
More informationOptical Flow, Motion Segmentation, Feature Tracking
BIL 719 - Computer Vision May 21, 2014 Optical Flow, Motion Segmentation, Feature Tracking Aykut Erdem Dept. of Computer Engineering Hacettepe University Motion Optical Flow Motion Segmentation Feature
More informationRepresenting regions in 2 ways:
Representing regions in 2 ways: Based on their external characteristics (its boundary): Shape characteristics Based on their internal characteristics (its region): Both Regional properties: color, texture,
More informationA Recognition System for 3D Embossed Digits on Non-Smooth Metallic Surface
2011 International Conference on elecommunication echnology and Applications Proc.of CSI vol.5 (2011) (2011) IACSI Press, Singapore A Recognition System for 3D Embossed Digits on Non-Smooth Metallic Surface
More informationHilbert-Huang Transform-based Local Regions Descriptors
Hilbert-Huang Transform-based Local Regions Descriptors Dongfeng Han, Wenhui Li, Wu Guo Computer Science and Technology, Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of
More informationA New Efficient Method for Producing Global Affine Invariants
A New Efficient Method for Producing Global Affine Invariants Esa Rahtu, Mikko Salo 2, and Janne Heikkilä Machine Vision Group, Department of Electrical and Information Engineering, P.O. Box 45, 94 University
More informationLecture Topics GVMS Prof. Dr.-Ing. habil. Hermann Lödding Prof. Dr.-Ing. Wolfgang Hintze. PD Dr.-Ing. habil.
Lecture Topics 1. Introduction 2. Sensor Guides Robots / Machines 3. Motivation Model Calibration 4. 3D Video Metric (Geometrical Camera Model) 5. Grey Level Picture Processing for Position Measurement
More informationLecture 3: Pattern Classification
EE E6820: Speech & Audio Processing & Recognition Lecture 3: Pattern Classification 1 2 3 4 5 The problem of classification Linear and nonlinear classifiers Probabilistic classification Gaussians, mixtures
More informationRotational Invariants for Wide-baseline Stereo
Rotational Invariants for Wide-baseline Stereo Jiří Matas, Petr Bílek, Ondřej Chum Centre for Machine Perception Czech Technical University, Department of Cybernetics Karlovo namesti 13, Prague, Czech
More informationGiven a feature in I 1, how to find the best match in I 2?
Feature Matching 1 Feature matching Given a feature in I 1, how to find the best match in I 2? 1. Define distance function that compares two descriptors 2. Test all the features in I 2, find the one with
More informationOverview. Introduction to local features. Harris interest points + SSD, ZNCC, SIFT. Evaluation and comparison of different detectors
Overview Introduction to local features Harris interest points + SSD, ZNCC, SIFT Scale & affine invariant interest point detectors Evaluation and comparison of different detectors Region descriptors and
More informationMultimedia Databases. Previous Lecture. 4.1 Multiresolution Analysis. 4 Shape-based Features. 4.1 Multiresolution Analysis
Previous Lecture Multimedia Databases Texture-Based Image Retrieval Low Level Features Tamura Measure, Random Field Model High-Level Features Fourier-Transform, Wavelets Wolf-Tilo Balke Silviu Homoceanu
More informationL11: Pattern recognition principles
L11: Pattern recognition principles Bayesian decision theory Statistical classifiers Dimensionality reduction Clustering This lecture is partly based on [Huang, Acero and Hon, 2001, ch. 4] Introduction
More informationOverview. Harris interest points. Comparing interest points (SSD, ZNCC, SIFT) Scale & affine invariant interest points
Overview Harris interest points Comparing interest points (SSD, ZNCC, SIFT) Scale & affine invariant interest points Evaluation and comparison of different detectors Region descriptors and their performance
More informationMultimedia Databases. Wolf-Tilo Balke Philipp Wille Institut für Informationssysteme Technische Universität Braunschweig
Multimedia Databases Wolf-Tilo Balke Philipp Wille Institut für Informationssysteme Technische Universität Braunschweig http://www.ifis.cs.tu-bs.de 4 Previous Lecture Texture-Based Image Retrieval Low
More informationLecture 7: Finding Features (part 2/2)
Lecture 7: Finding Features (part 2/2) Professor Fei- Fei Li Stanford Vision Lab Lecture 7 -! 1 What we will learn today? Local invariant features MoHvaHon Requirements, invariances Keypoint localizahon
More informationImage Processing 1 (IP1) Bildverarbeitung 1
MIN-Fakultät Fachbereich Informatik Arbeitsbereich SAV/BV KOGS Image Processing 1 IP1 Bildverarbeitung 1 Lecture : Object Recognition Winter Semester 015/16 Slides: Prof. Bernd Neumann Slightly revised
More informationOrientation Map Based Palmprint Recognition
Orientation Map Based Palmprint Recognition (BM) 45 Orientation Map Based Palmprint Recognition B. H. Shekar, N. Harivinod bhshekar@gmail.com, harivinodn@gmail.com India, Mangalore University, Department
More informationEEL 851: Biometrics. An Overview of Statistical Pattern Recognition EEL 851 1
EEL 851: Biometrics An Overview of Statistical Pattern Recognition EEL 851 1 Outline Introduction Pattern Feature Noise Example Problem Analysis Segmentation Feature Extraction Classification Design Cycle
More informationMultimedia Databases. 4 Shape-based Features. 4.1 Multiresolution Analysis. 4.1 Multiresolution Analysis. 4.1 Multiresolution Analysis
4 Shape-based Features Multimedia Databases Wolf-Tilo Balke Silviu Homoceanu Institut für Informationssysteme Technische Universität Braunschweig http://www.ifis.cs.tu-bs.de 4 Multiresolution Analysis
More informationInternet Video Search
Internet Video Search Arnold W.M. Smeulders & Cees Snoek CWI & UvA Overview Image and Video Search Lecture 1 Lecture 2 Lecture 3 visual search, the problem color-spatial-textural-temporal features measures
More information