Computational Models of V1 cells. Gabor and CORF
|
|
- Jeffery Briggs
- 5 years ago
- Views:
Transcription
1 1 Computational Models of V1 cells Gabor and CORF George Azzopardi Nicolai Petkov
2 2 Primary visual cortex (striate cortex or V1)
3 3 Types of V1 Cells Hubel and Wiesel, Nobel Prize winners Three main types Simple cells Complex Cells Hyper-complex cells (end-stopping) Etc
4 4 References to origins - neurophysiology Hubel and Wiesel named one type of cell "simple" because they shared the following properties: Their receptive fields have distinct excitatory and inhibitory regions. It is possible to predict responses to stimuli given the map of excitatory and inhibitory regions.
5 5
6 6 Neurophysiology D.H. Hubel and T.N. Wiesel: Receptive fields, binocular interaction and functional architecture in the cat's visual cortex, Journal of Physiology (London), vol. 160, pp , D.H. Hubel and T.N. Wiesel: Sequence regularity and geometry of orientation columns in the monkey striate cortex, Journal of Computational Neurology, vol. 158, pp , D.H. Hubel: Exploration of the primary visual cortex, , Nature, vol. 299, pp , 1982.
7 7 Receptive Fields of Simple Cells [Jones and Palmer, 1987]
8 8 Computational Models 2D Gabor functions Combination of Receptive Fields (CORF) Derivative of Gaussians
9 9 Gabor = Gaussian x Cosine Gaussian (sigma) Cosine: lambda and phase Space domain Frequency domain
10 Parameterization according to N. Petkov: Biologically motivated computationally intensive approaches to image pattern recognition, Future Generation Computer Systems, 11 (4-5), 1995, N. Petkov and P. Kruizinga: Computational models of visual neurons specialised in the detection of periodic and aperiodic oriented visual stimuli: bar and grating cells, Biological Cybernetics, 76 (2), 1997, P. Kruizinga and N. Petkov: Non-linear operator for oriented texture, IEEE Trans. on Image Processing, 8 (10), 1999, S.E. Grigorescu, N. Petkov and P. Kruizinga: Comparison of texture features based on Gabor filters, IEEE Trans. on Image Processing, 11 (10), 2002, N. Petkov and M. A. Westenberg: Suppression of contour perception by band-limited noise and its relation to non-classical receptive field inhibition, Biological Cybernetics, 88, 2003, C. Grigorescu, N. Petkov and M. A. Westenberg: Contour detection based on nonclassical receptive field inhibition, IEEE Trans. on Image Processing, 12 (7), 2003,
11 11 Wavelength
12 12 Wavelength Space domain Frequency domain Smallest Wavelength = 2 pixels
13 13 Wavelength Space domain Frequency domain Wavelength = 4 pixels
14 14 Wavelength Space domain Frequency domain Wavelength = 8 pixels
15 15 Wavelength Space domain Frequency domain Wavelength = 16 pixels
16 16 Wavelength Space domain Frequency domain Wavelength = 32 pixels
17 17 Wavelength Space domain Frequency domain Wavelength = 64 pixels
18 18 Orientation
19 19 Orientation Space domain Frequency domain Orientation = 0
20 20 Orientation Space domain Frequency domain Orientation = 45
21 21 Orientation Space domain Frequency domain Orientation = 90
22 22 Symmetry (phase offset)
23 23 Symmetry (phase offset) Space domain Space domain Phase offset = 0 (symmetric function) Phase offset = -90 (anti-symmetric function)
24 24 Spatial aspect ratio
25 25 Spatial aspect ratio Space domain Frequency domain Aspect ratio = 0.5
26 26 Spatial aspect ratio Space domain Frequency domain Aspect ratio = 1
27 27 Spatial aspect ratio Space domain Frequency domain Aspect ratio = 2 (does not occur)
28 28 Sigma/lambda ratio Determines the spatial frequency bandwidth i.e. number of stripe zones
29 29 Preferred spatial frequency and size Space domain Frequency domain Bandwidth = 1 (σ = 0.56 λ) Wavelength = 8/512
30 30 Bandwidth Space domain Frequency domain Bandwidth = 0.5 Wavelength = 8/512
31 31 Bandwidth Space domain Frequency domain Bandwidth = 2 Wavelength = 8/512
32 32 Bandwidth Space domain Frequency domain Bandwidth = 1 (σ = 0.56 λ) Wavelength = 32/512
33 33 Bandwidth Space domain Frequency domain Bandwidth = 0.5 Wavelength = 32/512
34 34 Bandwidth Space domain Frequency domain Bandwidth = 2 Wavelength = 32/512
35 Semi-linear Gabor filter: What is it useful for? 35 Receptive field G(-x,-y) Input Output of Convolution followed by half-wave rectification bandwidth = 2 Ori = 0 Phi = 90 edges Ori = 180 Phi = 90 edges Ori = 0 Phi = 0 lines Ori = 0 Phi = 180 lines
36 Bank of semi-linear Gabor filters: Which orientations to use? 36 frequency domain Receptive field G(-x,-y) Ori = For filters with s.a.r=0.5 and bw=2, good coverage of angles with 6 orientations
37 Ori = For filters with sar=0.5 and bw=2, good coverage of angles with 12 orientations Input Output BICV Summer School, Shenyang, China, Bank of semi-linear Gabor filters: Which orientations to use Filter in frequency domain
38 Bank of semi-linear Gabor filters: Which orientations to use 38 Result of superposition of the outputs of 12 semi-linear anti-symmetric (phi=90) Gabor filters with wavelength = 4, bandwidth = 2, spatial aspect ratio = 0.5 (after thinning and thresholding lt = 0.1, ht = 0.15).
39 39 V1 gets input from Lateral Geniculate Nucleus (LGN)
40 40 V1 gets input from LGN Center-surround receptive fields Detect changes in light intensity Computational model Laplacian of Gaussian(Marr and Hildreth, 1980) or Difference of Gaussians (DoG)
41 41 [Hubel and Wiesel, 1962]
42 42 Combination Of Receptive Fields (CORF) model of a simple cell
43 43 Configuration of a CORF Model
44 44 Configuration of a CORF model
45 45 Response of a CORF Model
46 46 Modulated response to drifting gratings
47 47 Receptive field profile determined by simulated reverse correlation
48 48 Contrast Invariant Orientation Tuning Real simple cell CORF Model GF Model
49 49 CORF model with linear response
50 50 Cross Orientation Suppression CORF model responds as real simple cells do
51 51 CORF Model with linear response
52 52 Tolerance to Rotation
53 53 Tolerance to Rotation
54 54 Tolerance to Rotation
55 55 Contour Detection
56 56 Contour Detection Consider 12 orientations (intervals of 30) Take maximum superposition Thinning Hysteresis thresholding Compare model contour map with ground truth: Count TP, FP, and FN Precision P = TP/(TP + FP) Recall R = TP/(TP + FN) F-measure F = 2PR/(P + R)
57 57 Results
58 58 Results
59 59 Results: RuG Data Set
60 60 Results: CORF vs. Gabor Right-tailed paired t-test RuG: 40 images t = 4.39, p < 0.01 Berkeley: 500 images t = 4.95, p < 0.01
61 61 Robustness to noise
62 62 Take home message 1. Gabor and CORF: computational models of simple cells 2. CORF is nonlinear, Gabor is linear 3. CORF achieves more properties than Gabor 4. CORF is more effective in contour detection 5. Gabor is mathematically more elegant
63 63 Matlab Code
Nicolai Petkov Intelligent Systems group Institute for Mathematics and Computing Science
2D Gabor functions and filters for image processing and computer vision Nicolai Petkov Intelligent Systems group Institute for Mathematics and Computing Science 2 Most of the images in this presentation
More informationNicolai Petkov Intelligent Systems group Institute for Mathematics and Computing Science
V1-inspired orientation selective filters for image processing and computer vision Nicolai Petkov Intelligent Systems group Institute for Mathematics and Computing Science 2 Most of the images in this
More informationNicolai Petkov Intelligent Systems group Institute for Mathematics and Computing Science
2D Gabor functions and filters for image processing and computer vision Nicolai Petkov Intelligent Systems group Institute for Mathematics and Computing Science 2 Most of the images in this presentation
More informationIntroduction to visual computation and the primate visual system
Introduction to visual computation and the primate visual system Problems in vision Basic facts about the visual system Mathematical models for early vision Marr s computational philosophy and proposal
More informationLocating Fabric Defects Using Gabor Filters
Locating Fabric Defects Using Gabor Filters Padmavathi S, Prem P, Praveenn D Department of Information Technology, Amrita School of Engineering, Tamil Nadu, India Abstract- Quality inspection is the key
More informationVessels delineation in retinal images using COSFIRE filters
university of salerno 1 Vessels delineation in retinal images using COSFIRE filters George Azzopardi 1,3, Nicola Strisciuglio 1,2, Mario Vento 2, Nicolai Petkov 1 1 University of Groningen (The Netherlands)
More informationRetinal Vessel Segmentation Using Gabor Filter and Textons
ZHANG, FISHER, WANG: RETINAL VESSEL SEGMENTATION 1 Retinal Vessel Segmentation Using Gabor Filter and Textons Lei Zhang 1 Lei.zhang@uea.ac.uk Mark Fisher 1 http://www2.cmp.uea.ac.uk/~mhf/ Wenjia Wang 1
More informationSchedule for Rest of Semester
Schedule for Rest of Semester Date Lecture Topic 11/20 24 Texture 11/27 25 Review of Statistics & Linear Algebra, Eigenvectors 11/29 26 Eigenvector expansions, Pattern Recognition 12/4 27 Cameras & calibration
More informationRobust contour extraction and junction detection by a neural model utilizing recurrent long-range interactions
Robust contour extraction and junction detection by a neural model utilizing recurrent long-range interactions Thorsten Hansen 1, 2 & Heiko Neumann 2 1 Abteilung Allgemeine Psychologie, Justus-Liebig-Universität
More informationFont Identification Using the Grating Cell Texture Operator
Font Identification Using the Grating Cell Texture Operator Huanfeng Ma and David Doermann Language and Media Processing Laboratory Institute for Advanced Computer Studies University of Maryland, College
More informationCAP 5415 Computer Vision Fall 2012
CAP 5415 Computer Vision Fall 01 Dr. Mubarak Shah Univ. of Central Florida Office 47-F HEC Lecture-5 SIFT: David Lowe, UBC SIFT - Key Point Extraction Stands for scale invariant feature transform Patented
More informationBiologically-Inspired Translation, Scale, and rotation invariant object recognition models
Rochester Institute of Technology RIT Scholar Works Theses Thesis/Dissertation Collections 2007 Biologically-Inspired Translation, Scale, and rotation invariant object recognition models Myung Woo Follow
More informationExercise: Simulating spatial processing in the visual pathway with convolution
Exercise: Simulating spatial processing in the visual pathway with convolution This problem uses convolution to simulate the spatial filtering performed by neurons in the early stages of the visual pathway,
More informationTEXTURE ANALYSIS USING GABOR FILTERS
TEXTURE ANALYSIS USING GABOR FILTERS Texture Types Definition of Texture Texture types Synthetic Natural Stochastic < Prev Next > Texture Definition Texture: the regular repetition of an element or pattern
More informationEdge Detection (with a sidelight introduction to linear, associative operators). Images
Images (we will, eventually, come back to imaging geometry. But, now that we know how images come from the world, we will examine operations on images). Edge Detection (with a sidelight introduction to
More informationOBJECT RECOGNITION ALGORITHM FOR MOBILE DEVICES
Image Processing & Communication, vol. 18,no. 1, pp.31-36 DOI: 10.2478/v10248-012-0088-x 31 OBJECT RECOGNITION ALGORITHM FOR MOBILE DEVICES RAFAŁ KOZIK ADAM MARCHEWKA Institute of Telecommunications, University
More informationNatural image statistics and efficient coding
Network: Computation in Neural Systems 7 (1996) 333 339. Printed in the UK WORKSHOP PAPER Natural image statistics and efficient coding B A Olshausen and D J Field Department of Psychology, Uris Hall,
More informationDetecting Salient Contours Using Orientation Energy Distribution. Part I: Thresholding Based on. Response Distribution
Detecting Salient Contours Using Orientation Energy Distribution The Problem: How Does the Visual System Detect Salient Contours? CPSC 636 Slide12, Spring 212 Yoonsuck Choe Co-work with S. Sarma and H.-C.
More informationEdge Detection Techniques in Processing Digital Images: Investigation of Canny Algorithm and Gabor Method
World Applied Programming, Vol (3), Issue (3), March 013. 116-11 ISSN: -510 013 WAP journal. www.waprogramming.com Edge Detection Techniques in Processing Digital Images: Investigation of Canny Algorithm
More informationFiltering, scale, orientation, localization, and texture. Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth)
Filtering, scale, orientation, localization, and texture Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth) Beyond edges we have talked a lot about edges while they are important, it
More informationTEXTURE ANALYSIS USING GABOR FILTERS FIL
TEXTURE ANALYSIS USING GABOR FILTERS Texture Types Definition of Texture Texture types Synthetic ti Natural Stochastic < Prev Next > Texture Definition Texture: the regular repetition of an element or
More informationmonocular linear neuron binocular linear neuron monocular energy neuron binocular energy neuron
1 Modelling Binocular Neurons in the Primary Visual Cortex David J. Fleet David J. Heeger Hermann Wagner 1.1 Introduction Neurons sensitive to binocular disparityhave been found in the visual cortex of
More informationFiltering Images. Contents
Image Processing and Data Visualization with MATLAB Filtering Images Hansrudi Noser June 8-9, 010 UZH, Multimedia and Robotics Summer School Noise Smoothing Filters Sigmoid Filters Gradient Filters Contents
More informationLocal Image preprocessing (cont d)
Local Image preprocessing (cont d) 1 Outline - Edge detectors - Corner detectors - Reading: textbook 5.3.1-5.3.5 and 5.3.10 2 What are edges? Edges correspond to relevant features in the image. An edge
More informationENEE731 Project Texture Segmentation using Gabor Filters
ENEE731 Project Texture Segmentation using Gabor Filters Naotoshi Seo, sonots@umd.edu November 8, 2006 1 Introduction Malik and Perona (1989) [1] presented a model of texture perception with the early
More informationA SYNOPTIC ACCOUNT FOR TEXTURE SEGMENTATION: FROM EDGE- TO REGION-BASED MECHANISMS
A SYNOPTIC ACCOUNT FOR TEXTURE SEGMENTATION: FROM EDGE- TO REGION-BASED MECHANISMS Enrico Giora and Clara Casco Department of General Psychology, University of Padua, Italy Abstract Edge-based energy models
More informationEECS150 - Digital Design Lecture 14 FIFO 2 and SIFT. Recap and Outline
EECS150 - Digital Design Lecture 14 FIFO 2 and SIFT Oct. 15, 2013 Prof. Ronald Fearing Electrical Engineering and Computer Sciences University of California, Berkeley (slides courtesy of Prof. John Wawrzynek)
More informationDigital Image Processing COSC 6380/4393
Digital Image Processing COSC 6380/4393 Lecture 21 Nov 16 th, 2017 Pranav Mantini Ack: Shah. M Image Processing Geometric Transformation Point Operations Filtering (spatial, Frequency) Input Restoration/
More informationCS334: Digital Imaging and Multimedia Edges and Contours. Ahmed Elgammal Dept. of Computer Science Rutgers University
CS334: Digital Imaging and Multimedia Edges and Contours Ahmed Elgammal Dept. of Computer Science Rutgers University Outlines What makes an edge? Gradient-based edge detection Edge Operators From Edges
More informationFACE RECOGNITION USING INDEPENDENT COMPONENT
Chapter 5 FACE RECOGNITION USING INDEPENDENT COMPONENT ANALYSIS OF GABORJET (GABORJET-ICA) 5.1 INTRODUCTION PCA is probably the most widely used subspace projection technique for face recognition. A major
More informationVision: From Eye to Brain (Chap 3)
Vision: From Eye to Brain (Chap 3) Lecture 7 Jonathan Pillow Sensation & Perception (PSY 345 / NEU 325) Princeton University, Fall 2017 early visual pathway eye eye optic nerve optic chiasm optic tract
More informationCS534: Introduction to Computer Vision Edges and Contours. Ahmed Elgammal Dept. of Computer Science Rutgers University
CS534: Introduction to Computer Vision Edges and Contours Ahmed Elgammal Dept. of Computer Science Rutgers University Outlines What makes an edge? Gradient-based edge detection Edge Operators Laplacian
More informationBio-inspired Binocular Disparity with Position-Shift Receptive Field
Bio-inspired Binocular Disparity with Position-Shift Receptive Field Fernanda da C. e C. Faria, Jorge Batista and Helder Araújo Institute of Systems and Robotics, Department of Electrical Engineering and
More informationCS 4495 Computer Vision. Linear Filtering 2: Templates, Edges. Aaron Bobick. School of Interactive Computing. Templates/Edges
CS 4495 Computer Vision Linear Filtering 2: Templates, Edges Aaron Bobick School of Interactive Computing Last time: Convolution Convolution: Flip the filter in both dimensions (right to left, bottom to
More informationThe SIFT (Scale Invariant Feature
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor developed by David Lowe University of British Columbia Initial paper ICCV 1999 Newer journal paper IJCV 2004 Review: Matt Brown s Canonical
More informationWhat is an edge? Paint. Depth discontinuity. Material change. Texture boundary
EDGES AND TEXTURES The slides are from several sources through James Hays (Brown); Srinivasa Narasimhan (CMU); Silvio Savarese (U. of Michigan); Bill Freeman and Antonio Torralba (MIT), including their
More informationAnalysis and Synthesis of Texture
Analysis and Synthesis of Texture CMPE 264: Image Analysis and Computer Vision Spring 02, Hai Tao 31/5/02 Extracting image structure by filter banks Q Represent image textures using the responses of a
More informationMulti-scale Cortical Keypoint Representation for Attention and Object Detection
Multi-scale Cortical Keypoint Representation for Attention and Object Detection 255 João Rodrigues 1 and Hans du Buf 2 1 University of Algarve, Escola Superior Tecnologia, Faro, Portugal 2 University of
More informationWavelets, vision and the statistics of natural scenes
Wavelets, vision and the statistics of natural scenes By D. J. Field Uris Hall, Cornell University, Ithaca, NY 14853, USA The processing of spatial information by the visual system shows a number of similarities
More informationAnno accademico 2006/2007. Davide Migliore
Robotica Anno accademico 6/7 Davide Migliore migliore@elet.polimi.it Today What is a feature? Some useful information The world of features: Detectors Edges detection Corners/Points detection Descriptors?!?!?
More informationDepartment of Psychology, Uris Hall, Cornell University, Ithaca, New York
Natural image statistics and ecient coding B A Olshausen and D J Field Department of Psychology, Uris Hall, Cornell University, Ithaca, New York 14853. Email: bao1@cornell.edu, djf3@cornell.edu To appear
More informationArtifacts and Textured Region Detection
Artifacts and Textured Region Detection 1 Vishal Bangard ECE 738 - Spring 2003 I. INTRODUCTION A lot of transformations, when applied to images, lead to the development of various artifacts in them. In
More informationEfficient Visual Coding: From Retina To V2
Efficient Visual Coding: From Retina To V Honghao Shan Garrison Cottrell Computer Science and Engineering UCSD La Jolla, CA 9093-0404 shanhonghao@gmail.com, gary@ucsd.edu Abstract The human visual system
More informationFace Detection Using Convolutional Neural Networks and Gabor Filters
Face Detection Using Convolutional Neural Networks and Gabor Filters Bogdan Kwolek Rzeszów University of Technology W. Pola 2, 35-959 Rzeszów, Poland bkwolek@prz.rzeszow.pl Abstract. This paper proposes
More informationNeural Network Model for the Cortical Representation of Surface Curvature from Images of Shaded Surfaces
In: Lund, J. S. (Ed.) Sensory Processing in the Mammalian Brain: Neural Substrates and Experimental Strategies,, Oxford: Oxford University Press (1988) Neural Network Model for the Cortical Representation
More informationSpatiotemporal Gabor filters: a new method for dynamic texture recognition
Spatiotemporal Gabor filters: a new method for dynamic texture recognition Wesley Nunes Gonçalves, Bruno Brandoli Machado, Odemir Martinez Bruno Physics Institute of São Carlos (IFSC) Institute of Mathematical
More informationDigital Image Processing. Image Enhancement - Filtering
Digital Image Processing Image Enhancement - Filtering Derivative Derivative is defined as a rate of change. Discrete Derivative Finite Distance Example Derivatives in 2-dimension Derivatives of Images
More informationVisual representation in the determination of saliency
2011 Canadian Conference on Computer and Robot Vision Visual representation in the determination of saliency Neil D. B. Bruce, Xun Shi, Evgueni Simine and John K. Tsotsos Department of Computer Science
More informationFeature Extraction and Image Processing, 2 nd Edition. Contents. Preface
, 2 nd Edition Preface ix 1 Introduction 1 1.1 Overview 1 1.2 Human and Computer Vision 1 1.3 The Human Vision System 3 1.3.1 The Eye 4 1.3.2 The Neural System 7 1.3.3 Processing 7 1.4 Computer Vision
More informationEdge and Texture. CS 554 Computer Vision Pinar Duygulu Bilkent University
Edge and Texture CS 554 Computer Vision Pinar Duygulu Bilkent University Filters for features Previously, thinking of filtering as a way to remove or reduce noise Now, consider how filters will allow us
More informationEdge detection. Goal: Identify sudden. an image. Ideal: artist s line drawing. object-level knowledge)
Edge detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the image can be encoded in the edges More compact than pixels Ideal: artist
More informationOutline 7/2/201011/6/
Outline Pattern recognition in computer vision Background on the development of SIFT SIFT algorithm and some of its variations Computational considerations (SURF) Potential improvement Summary 01 2 Pattern
More informationLeaf vein segmentation using Odd Gabor filters and morphological operations
Leaf vein segmentation using Odd Gabor filters and morphological operations Vini Katyal 1, Aviral 2 1 Computer Science, Amity University, Noida, Uttar Pradesh, India vini_katyal@yahoo.co.in 2 Computer
More informationOptimal disparity estimation in natural stereo- images (Supplement) Johannes Burge & Wilson S. Geisler
Optimal disparity estimation in natural stereo- images (Supplement) Johannes Burge & Wilson S. Geisler Computing the log likelihood with populations of simple and complex cells Simple cells in visual cortex
More informationImage Analysis. Edge Detection
Image Analysis Edge Detection Christophoros Nikou cnikou@cs.uoi.gr Images taken from: Computer Vision course by Kristen Grauman, University of Texas at Austin (http://www.cs.utexas.edu/~grauman/courses/spring2011/index.html).
More informationOn the road to invariant object recognition: How cortical area V2 transforms absolute to relative disparity during 3D vision
On the road to invariant object recognition: How cortical area V2 transforms absolute to relative disparity during 3D vision Stephen Grossberg, Karthik Srinivasan, and Arash Yazdanbakhsh Center for Adaptive
More informationLocal Features: Detection, Description & Matching
Local Features: Detection, Description & Matching Lecture 08 Computer Vision Material Citations Dr George Stockman Professor Emeritus, Michigan State University Dr David Lowe Professor, University of British
More informationIntroduction. Introduction. Related Research. SIFT method. SIFT method. Distinctive Image Features from Scale-Invariant. Scale.
Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe presented by, Sudheendra Invariance Intensity Scale Rotation Affine View point Introduction Introduction SIFT (Scale Invariant Feature
More informationCOMPARATIVE STUDY OF IMAGE EDGE DETECTION ALGORITHMS
COMPARATIVE STUDY OF IMAGE EDGE DETECTION ALGORITHMS Shubham Saini 1, Bhavesh Kasliwal 2, Shraey Bhatia 3 1 Student, School of Computing Science and Engineering, Vellore Institute of Technology, India,
More informationProject proposal: Statistical models of visual neurons
Project proposal: Statistical models of visual neurons Anna Sotnikova asotniko@math.umd.edu Project Advisor: Prof. Daniel A. Butts dab@umd.edu Department of Biology Abstract Studying visual neurons may
More informationMultimedia Computing: Algorithms, Systems, and Applications: Edge Detection
Multimedia Computing: Algorithms, Systems, and Applications: Edge Detection By Dr. Yu Cao Department of Computer Science The University of Massachusetts Lowell Lowell, MA 01854, USA Part of the slides
More informationA Modified Approach to Biologically Motivated Saliency Mapping
A Modified Approach to Biologically Motivated Saliency Mapping Shane Grant Department of Computer Science University of California, San Diego La Jolla, CA 9093 wgrant@ucsd.edu Kevin A Heins Department
More informationNeural competitive structures for segmentation based on motion features
Neural competitive structures for segmentation based on motion features Javier Díaz 1, Sonia Mota 1, Eduardo Ros 1 and Guillermo Botella 1 1 Departamento de Arquitectura y Tecnología de Computadores, E.T.S.I.
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 10 130221 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Canny Edge Detector Hough Transform Feature-Based
More informationObject-Based Saliency Maps Harry Marr Computing BSc 2009/2010
Object-Based Saliency Maps Harry Marr Computing BSc 2009/2010 The candidate confirms that the work submitted is their own and the appropriate credit has been given where reference has been made to the
More informationCHAPTER 1 Introduction 1. CHAPTER 2 Images, Sampling and Frequency Domain Processing 37
Extended Contents List Preface... xi About the authors... xvii CHAPTER 1 Introduction 1 1.1 Overview... 1 1.2 Human and Computer Vision... 2 1.3 The Human Vision System... 4 1.3.1 The Eye... 5 1.3.2 The
More informationConcepts in. Edge Detection
Concepts in Edge Detection Dr. Sukhendu Das Deptt. of Computer Science and Engg., Indian Institute of Technology, Madras Chennai 600036, India. http://www.cs.iitm.ernet.in/~sdas Email: sdas@iitm.ac.in
More informationEdge Detection CSC 767
Edge Detection CSC 767 Edge detection Goal: Identify sudden changes (discontinuities) in an image Most semantic and shape information from the image can be encoded in the edges More compact than pixels
More informationCS 523: Multimedia Systems
CS 523: Multimedia Systems Angus Forbes creativecoding.evl.uic.edu/courses/cs523 Today - Convolutional Neural Networks - Work on Project 1 http://playground.tensorflow.org/ Convolutional Neural Networks
More informationC. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun
Efficient Learning of Sparse Overcomplete Representations with an Energy-Based Model Marc'Aurelio Ranzato C. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun CIAR Summer School Toronto 2006 Why Extracting
More informationUsing perceptual relation of regularity and anisotropy in the texture with independent component model for defect detection
Using perceptual relation of regularity and anisotropy in the texture with independent component model for defect detection O.G. Sezer a, 1, A. Ercil b,, and A. Ertuzun c a Electrical Sciences and Computer
More informationComparison between Various Edge Detection Methods on Satellite Image
Comparison between Various Edge Detection Methods on Satellite Image H.S. Bhadauria 1, Annapurna Singh 2, Anuj Kumar 3 Govind Ballabh Pant Engineering College ( Pauri garhwal),computer Science and Engineering
More informationTexture. Outline. Image representations: spatial and frequency Fourier transform Frequency filtering Oriented pyramids Texture representation
Texture Outline Image representations: spatial and frequency Fourier transform Frequency filtering Oriented pyramids Texture representation 1 Image Representation The standard basis for images is the set
More informationRELATIONSHIP BETWEEN SUSPICIOUS COINCIDENCE IN NATURAL IMAGES AND CONTOUR-SALIENCE IN ORIENTED FILTER RESPONSES. A Thesis SUBRAMONIA P.
RELATIONSHIP BETWEEN SUSPICIOUS COINCIDENCE IN NATURAL IMAGES AND CONTOUR-SALIENCE IN ORIENTED FILTER RESPONSES A Thesis by SUBRAMONIA P. SARMA Submitted to the Office of Graduate Studies of Texas A&M
More informationEdges, interpolation, templates. Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth)
Edges, interpolation, templates Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth) Gradients and edges edges are points of large gradient magnitude edge detection strategy 1. determine
More informationComputer Vision for HCI. Topics of This Lecture
Computer Vision for HCI Interest Points Topics of This Lecture Local Invariant Features Motivation Requirements, Invariances Keypoint Localization Features from Accelerated Segment Test (FAST) Harris Shi-Tomasi
More informationSemi-automatic Segmentation of Fibrous Liver Tissue
Semi-automatic Segmentation of Fibrous Liver Tissue P. Andruszkiewicz 1,2, C. Bołdak 1, J. Jaroszewicz 3 pandruszkiewicz@gmail.com, boldak@ii.pb.bialystok.pl, jerzy.jr@gmail.com 1 Faculty of Computer Science,
More informationEdge detection. Winter in Kraków photographed by Marcin Ryczek
Edge detection Winter in Kraków photographed by Marcin Ryczek Edge detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the image
More informationRepresenting the World
Table of Contents Representing the World...1 Sensory Transducers...1 The Lateral Geniculate Nucleus (LGN)... 2 Areas V1 to V5 the Visual Cortex... 2 Computer Vision... 3 Intensity Images... 3 Image Focusing...
More informationIntegrated Querying of Images by Color, Shape, and Texture Content of Salient Objects
Integrated Querying of Images by Color, Shape, and Texture Content of Salient Objects Ediz Şaykol, Uğur Güdükbay, and Özgür Ulusoy Department of Computer Engineering, Bilkent University 06800 Bilkent,
More informationEE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm
EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm Group 1: Mina A. Makar Stanford University mamakar@stanford.edu Abstract In this report, we investigate the application of the Scale-Invariant
More informationSCALE INVARIANT FEATURE TRANSFORM (SIFT)
1 SCALE INVARIANT FEATURE TRANSFORM (SIFT) OUTLINE SIFT Background SIFT Extraction Application in Content Based Image Search Conclusion 2 SIFT BACKGROUND Scale-invariant feature transform SIFT: to detect
More informationSUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS
SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS Cognitive Robotics Original: David G. Lowe, 004 Summary: Coen van Leeuwen, s1460919 Abstract: This article presents a method to extract
More informationEdge Detection. CSE 576 Ali Farhadi. Many slides from Steve Seitz and Larry Zitnick
Edge Detection CSE 576 Ali Farhadi Many slides from Steve Seitz and Larry Zitnick Edge Attneave's Cat (1954) Origin of edges surface normal discontinuity depth discontinuity surface color discontinuity
More informationReview of Filtering. Filtering in frequency domain
Review of Filtering Filtering in frequency domain Can be faster than filtering in spatial domain (for large filters) Can help understand effect of filter Algorithm: 1. Convert image and filter to fft (fft2
More informationDEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING DS7201 ADVANCED DIGITAL IMAGE PROCESSING II M.E (C.S) QUESTION BANK UNIT I 1. Write the differences between photopic and scotopic vision? 2. What
More informationEdge detection. Winter in Kraków photographed by Marcin Ryczek
Edge detection Winter in Kraków photographed by Marcin Ryczek Edge detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, edges carry most of the semantic and shape information
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 09 130219 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Feature Descriptors Feature Matching Feature
More informationDeep Learning. Deep Learning. Practical Application Automatically Adding Sounds To Silent Movies
http://blog.csdn.net/zouxy09/article/details/8775360 Automatic Colorization of Black and White Images Automatically Adding Sounds To Silent Movies Traditionally this was done by hand with human effort
More informationThe Vehicle Logo Location System based on saliency model
ISSN 746-7659, England, UK Journal of Information and Computing Science Vol. 0, No. 3, 205, pp. 73-77 The Vehicle Logo Location System based on saliency model Shangbing Gao,2, Liangliang Wang, Hongyang
More informationAutomatic Detection of Texture Defects using Texture-Periodicity and Gabor Wavelets
Abstract Automatic Detection of Texture Defects using Texture-Periodicity and Gabor Wavelets V Asha 1, N U Bhajantri, and P Nagabhushan 3 1 New Horizon College of Engineering, Bangalore, Karnataka, India
More informationMORPH-II: Feature Vector Documentation
MORPH-II: Feature Vector Documentation Troy P. Kling NSF-REU Site at UNC Wilmington, Summer 2017 1 MORPH-II Subsets Four different subsets of the MORPH-II database were selected for a wide range of purposes,
More informationANALYSIS DIRECTIONAL FEATURES IN IMAGES USING GABOR FILTERS
ANALYSIS DIRECTIONAL FEATURES IN IMAGES USING GABOR FILTERS Z.-Q. Liu*, R. M. Rangayyan*, and C. B. Frank** Departments of Electrical Engineering* and Surgery**, The University of Calgary Calgary, Alberta,
More informationLearning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009
Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer
More informationImage Analysis. Edge Detection
Image Analysis Edge Detection Christophoros Nikou cnikou@cs.uoi.gr Images taken from: Computer Vision course by Kristen Grauman, University of Texas at Austin (http://www.cs.utexas.edu/~grauman/courses/spring2011/index.html).
More informationSolution: filter the image, then subsample F 1 F 2. subsample blur subsample. blur
Pyramids Gaussian pre-filtering Solution: filter the image, then subsample blur F 0 subsample blur subsample * F 0 H F 1 F 1 * H F 2 { Gaussian pyramid blur F 0 subsample blur subsample * F 0 H F 1 F 1
More informationEdge detection. Convert a 2D image into a set of curves. Extracts salient features of the scene More compact than pixels
Edge Detection Edge detection Convert a 2D image into a set of curves Extracts salient features of the scene More compact than pixels Origin of Edges surface normal discontinuity depth discontinuity surface
More informationLocal Features Tutorial: Nov. 8, 04
Local Features Tutorial: Nov. 8, 04 Local Features Tutorial References: Matlab SIFT tutorial (from course webpage) Lowe, David G. Distinctive Image Features from Scale Invariant Features, International
More informationCS 4495 Computer Vision A. Bobick. CS 4495 Computer Vision. Features 2 SIFT descriptor. Aaron Bobick School of Interactive Computing
CS 4495 Computer Vision Features 2 SIFT descriptor Aaron Bobick School of Interactive Computing Administrivia PS 3: Out due Oct 6 th. Features recap: Goal is to find corresponding locations in two images.
More informationEdges Are Not Just Steps
ACCV2002: The 5th Asian Conference on Computer Vision, 23 25 January 2002, Melbourne, Australia. 1 Edges Are Not Just Steps Peter Kovesi Department of Computer Science & Software Engineering The University
More information