Arnold W.M Smeulders Theo Gevers. University of Amsterdam smeulders}

Size: px
Start display at page:

Download "Arnold W.M Smeulders Theo Gevers. University of Amsterdam smeulders}"

Transcription

1 Arnold W.M Smeulders Theo evers University of Amsterdam smeulders}

2 0 Prolem statement Query matching Query

3 0 Prolem statement Query classes 1. Query y ey-words 2. Query y feature attriutes including setch 3. Query y 1 or N examples 4. Feedac iterative definition of query

4 1 Demands World model WWW Trademar assessment Trademar in pulic Stolen goods retrieval Video dataases Product dataase Product retrieval Stamp collections general pictures unnown conditions 2D of 2D pictures nown camera 2D of 3D pictures unnown conditions general pictures well-ehaved camera general pictures unnown camera limited domain nown camera limited domain well-ehaved camera 2D of 2D pictures narrow domains

5 1 Demands Computational model geometric models detect cue group line detect line controller data detect edge

6 1 Demands Computational model symolic models oject_one_end x = house U1 = 0.8 oject_other_end x = gasline U2 = 0.7 x = house to gasline Ui = 0.7 ojectz = house to gasline Ui = 0.7 z = douly arrowed line Uii = 0.63.

7 1 Demands World and computational models conclusions 1. Visual worlds have very specific characteristics ojects scenes sensors 2. The world more models than detailed computational can e made. 3.a Narrow world domains requires detailed computational models. 3. road domain require general models ased on physical laws light sensing and materials physiological facts perception cultural oservations semiotics.

8 1 Demands Image segmentation reconsidering the definition Input : picture data Output : find what pixels form an oject in real world Segmentation requires experience with meaning!

9 1 Demands Image segmentation advanced Segmentation y elastic snae model Contour which minimises elastic energy v s 2 fvs Advanced segmentation suited for narrow domain.

10 1 Demands Image segmentation conclusions 1. Whatever rilliant techniques for segmentation: not good enough to segment general pictures. 2. Segmentation has no answer to occlusion and clutter. 3. For retrieval of general images: wea segmentation: esult is definitely in one oject no guarantee all of oject is found. Simplest form: point segmentation.

11 1 Demands Features one million views So many images of one oject due to minor differences in: camera location rotation scale light source illumination light interaction surface cover acground clutter occlusion camera type viewpoint A million different data arrays to one oject!

12 1 Demands Features invariance Image retrieval in general domains requires invariance! A feature F invariant to condition A will produce for oject x the value Fx regardless the effect of condition A. Features for general image retrieval condition A effect of A required feature everywhere any positions location invariance upside down any orientation rotation invariance closer any scale scale invariance shadow lamp any intensity illumination invariance occlusion any suset present invariance to partial no frontal view any view angle viewpoint invariance

13 1 Demands Features invariance Image retrieval requires invariance! A feature F invariant to condition A will produce for oject x the value Fx regardless the effect of condition A. Image retrieval requires selected invariance! Art = frontal view daylight no occlusion. Crowd = occluded aritrary viewpoint.

14 1 Demands Features the invariance of 42 the numer Image retrieval requires invariance! A feature F invariant to condition A will produce for oject x the value Fx regardless the effect of condition A. The most invariant feature is the value 42 or any other numer: never changes regardless whatever conditions A. Trade-off etween invariance and power to discriminate. Conclusion: Use the smallest set of relevant invariant features.

15 1 Demands Features to recognize an oject One or two details may e enough to recognise an oject if and only if recognition is invariant colour changes shape changes

16 1 Demands Features conclusions 1. Invariant to sensing conditions illumination and oject shape require photometric features 2D image of 3D world require affine invariant features 2. Invariant to emedding scene occlusion and clutter require local features 3. Use the smallest set of relevant invariant features. 4. Candidate features are shape colour & texture iff invariant for domain recording circumstances and query at hand

17 2 Colour shape What maes an image? Spectrum of source Surface reflectance eometry of oject Emedding in scene Spectrum of sensor and nothing else

18 2 Colour shape What maes an image? -space ow will ojects reflect in -space?

19 2 Colour shape What maes an image? Schafer s model ody surface

20 2 Colour shape What maes an image? Schafer s model C = m n s f λ e λ c λ dλ m n s v f λ e λ c λ d C s C s λ λ λ λ c eλ n s v f C λ surface aledo illumination oject surface normal illumination direction viewer s direction sensor sensitivity scene & viewpoint invariant scene dependent viewpoint variant scene dependent viewpoint variant scene dependent

21 cos for example the geometricterm is Lamertian i.e. Consider the ody reflection term: s n s n m d c e f s n m C C = = λ λ λ λ λ What maes an image? ody reflectance in ody reflectance in -space space 2 Colour shape

22 2 Colour shape What maes an image? ody reflectance in -space ow does -histogram loo loo lie?

23 2 Colour shape What maes an image? ody reflectance in -space

24 2 Colour shape What maes an image? surface reflectance in -space Consider the surface reflection term : m n s v s λ f C λ e λ c λ dλ where the geometric term is for example α only depends on n s and v. s the phong model cos n α where

25 2 Colour shape What maes an image? reflectance under white light reconsidered S Dichromatic reflection under white light CW = em n s c ems n s v c s f

26 2 Colour shape Colour invariance S I - space S ue: = arctan 3

27 C s n em C = For giving the red green and lue sensor response under white light. Further with } { C = λ λ λ d c f C C = Consider the ody reflection term: s n em s n em g = = s n em s n em = = s n em s n em r = = Colour invariance photometric invariance photometric invariance 2 Colour shape

28 Colour invariance photometric invariance 2 Colour shape where Then etc...} e.g. {...} e.g. { u t s r q p C s n em s n em s n em s n em s n em s n em u t s r q p = = = = = = = =

29 2 Colour shape Colour invariance c = 1 photometric invariance - c1 c2 c3 space arctan max{ } c = 2 c 3 = arctan arctan max{ } max{ } em n s c 1 arctan arctan = = max{ em n s em n s } max{ }

30 . 3 3 where Then etc...} e.g. {...} e.g. { u t s r q p C u t s r q p = = Colour invariance shiny ojects shiny ojects - l1 l2 l3 space l1 l2 l3 space 2 Colour shape

31 2 Colour shape Colour invariance m1 m2 m3 - space coloured light m 1 = 2 3 / 3 2 m 2 = 3 1 / 1 3 m 3 = 1 2 / 2 1

32 2 Colour shape Colour invariance conclusion shadows shading highlights ill. intensity ill. color I rg - - c1c2c3 - - hue - l1l2l3 - m1m2m3 - - no invariance invariance

33 2 Colour shape Shape invariant colour edge detection c1c2c3 l1l2l3

34 2 Colour shape Shape colour edge classification color edge maxima shadows and geometry highlights color edges

35 2 Colour shape Shape colour edge classification material highlight shadow or geometry

36 3 Searching and finding Searching individual images

37 3 Searching and finding Searching individual images inary VSM - results xor and Percent mrs hausdorf 20 Accumulated raning percentile

38 3 Searching and finding Searching individual images inary VSM - roust against occlusion? accumulated 100% average ran 50% Yes! Even 80% occluded occlusion percentage

39 3 Searching and finding Searching individual images inary VSM - roust against viewpoints? accumulated 100% average ran 50% Yes! Even 75 o out of sight. rotation in viewpoint

40 3 Searching and finding Searching individual images conclusions on VSM 1. VSM wors fine for multi-coloured ojects shape colour wors est single est feature is colour. 2. VSM is roust against features: viewpoint affine invariant similarity: occlusion & clutter invariant

41 3 Searching and finding Searching groups of images VSM with -NN learning K-nearest neighor represents each images y a vector in n-space. The nearness is defined y the Euclidean distance. feature2 Training samples class A Training samples class Query image feature1

42 3 Searching and finding Searching groups of images VSM in -NN photographs versus synthetic synthetic images photographic images

43 3 Searching and finding Searching groups of images VSM in -NN photographs versus synthetic Color variation Synthetic images tend to have fewer colors than photographs. Color saturation Colors in synthetic images are commonly less saturated. Color edge strength Synthetic images tend to have more arupt color transitions than photographs.

44 3 Searching and finding Searching groups of images -NN in VSM classification results Query Query esults esults Edge strength and saturation photo synthetic Classifier y -NN Data 200 training and 100 images for each class. photo 95% 5% synthetic 9% 91%

45 3 Searching and finding Searching groups of images -NN in VSM for sin detection sin pixels not-sin pixels - space versus c1 c2 c3 - space Conclusion: a range in normalized c1 c2 c3-space specific for sin.

46 3 Searching and finding Searching groups of images sin detection: results

47 3 Searching and finding Searching groups of images K-NN in VSM for portrait detection Query esults portrait non-portrait Features are color ratio s. Classification y -NN. portrait 96% 4% Data 200 training and 100 test images in each class. non-portrait 25% 75%

48 4 Oject localisation Split and merge Split regions until patch is homogeneous...

49 4 Oject localisation Split and merge... and merge patches which are alie. Wors ecause of spatial coherence.

50 4 Oject localisation omogeneity 1. Normalizedcross correlation : D C IQ = D IQ I = = 1 t t t = 1 = 1 w Q w t = 1 w Q 2. istogram intersection : min{ w w I 2 Q Q w I } D I and # D C I Q dependent on occlusion and oject cluttering I Q independen oject I cluttering Q hue t on occlusion

51 4 Oject localisation Data set example

52 4 Oject localisation esults

53 4 Oject localisation esults

54 5 Image search engine PicToSee Content-ased image retrieval Fast indexing Query pictorial example attriutes Invariance University of Amsterdam {gevers smeulders}

HOW USEFUL ARE COLOUR INVARIANTS FOR IMAGE RETRIEVAL?

HOW USEFUL ARE COLOUR INVARIANTS FOR IMAGE RETRIEVAL? HOW USEFUL ARE COLOUR INVARIANTS FOR IMAGE RETRIEVAL? Gerald Schaefer School of Computing and Technology Nottingham Trent University Nottingham, U.K. Gerald.Schaefer@ntu.ac.uk Abstract Keywords: The images

More information

Deep Learning in Image and Face Intrinsics

Deep Learning in Image and Face Intrinsics Deep Learning in Image and Face Intrinsics Theo Gevers Professor in Computer Vision: University of Amsterdam Co-founder: Sightcorp 3DUniversum Scanm WIC, Eindhoven, February 24th, 2018 Amsterdam A.I. -

More information

Depth. Common Classification Tasks. Example: AlexNet. Another Example: Inception. Another Example: Inception. Depth

Depth. Common Classification Tasks. Example: AlexNet. Another Example: Inception. Another Example: Inception. Depth Common Classification Tasks Recognition of individual objects/faces Analyze object-specific features (e.g., key points) Train with images from different viewing angles Recognition of object classes Analyze

More information

HISTOGRAMS OF ORIENTATIO N GRADIENTS

HISTOGRAMS OF ORIENTATIO N GRADIENTS HISTOGRAMS OF ORIENTATIO N GRADIENTS Histograms of Orientation Gradients Objective: object recognition Basic idea Local shape information often well described by the distribution of intensity gradients

More information

Color Invariant Snakes

Color Invariant Snakes Color Invariant Snakes Theo Gevers, Sennay Ghebreab and Arnold W.M. Smeulders ISIS, University of Amsterdam, Kruislaan 403 1098 SJ Amsterdam, The Netherlands [gevers ghebreab smeulders]@wins.uva.nl Abstract

More information

Chamfer matching. More on template matching. Distance transform example. Computing the distance transform. Shape based matching.

Chamfer matching. More on template matching. Distance transform example. Computing the distance transform. Shape based matching. Chamfer matching Given: binary image, B, of edge and local feature locations binary edge template, T, of shape we want to match More on template matching Shape based matching Let D be an array in registration

More information

What is Computer Vision? Introduction. We all make mistakes. Why is this hard? What was happening. What do you see? Intro Computer Vision

What is Computer Vision? Introduction. We all make mistakes. Why is this hard? What was happening. What do you see? Intro Computer Vision What is Computer Vision? Trucco and Verri (Text): Computing properties of the 3-D world from one or more digital images Introduction Introduction to Computer Vision CSE 152 Lecture 1 Sockman and Shapiro:

More information

Image Features: Detection, Description, and Matching and their Applications

Image Features: Detection, Description, and Matching and their Applications Image Features: Detection, Description, and Matching and their Applications Image Representation: Global Versus Local Features Features/ keypoints/ interset points are interesting locations in the image.

More information

Color. making some recognition problems easy. is 400nm (blue) to 700 nm (red) more; ex. X-rays, infrared, radio waves. n Used heavily in human vision

Color. making some recognition problems easy. is 400nm (blue) to 700 nm (red) more; ex. X-rays, infrared, radio waves. n Used heavily in human vision Color n Used heavily in human vision n Color is a pixel property, making some recognition problems easy n Visible spectrum for humans is 400nm (blue) to 700 nm (red) n Machines can see much more; ex. X-rays,

More information

Physics-based Vision: an Introduction

Physics-based Vision: an Introduction Physics-based Vision: an Introduction Robby Tan ANU/NICTA (Vision Science, Technology and Applications) PhD from The University of Tokyo, 2004 1 What is Physics-based? An approach that is principally concerned

More information

Local Feature Detectors

Local Feature Detectors Local Feature Detectors Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr Slides adapted from Cordelia Schmid and David Lowe, CVPR 2003 Tutorial, Matthew Brown,

More information

Reflectance-based Classification of Color Edges

Reflectance-based Classification of Color Edges Reflectance-based Classification of Color dges Theo Gevers Informatics Institute Faculty of Science Amsterdam, The Netherlands Abstract We aim at using color information to classify the physical nature

More information

BSB663 Image Processing Pinar Duygulu. Slides are adapted from Selim Aksoy

BSB663 Image Processing Pinar Duygulu. Slides are adapted from Selim Aksoy BSB663 Image Processing Pinar Duygulu Slides are adapted from Selim Aksoy Image matching Image matching is a fundamental aspect of many problems in computer vision. Object or scene recognition Solving

More information

Image Segmentation and Similarity of Color-Texture Objects

Image Segmentation and Similarity of Color-Texture Objects IEEE TRANSACTIONS ON MULTIMEDIA, VOL. XX, NO. Y, MONTH 2002 1 Image Segmentation and Similarity of Color-Texture Objects Theo Gevers, member, IEEE Abstract We aim for content-based image retrieval of textured

More information

Announcements. Recognition I. Gradient Space (p,q) What is the reflectance map?

Announcements. Recognition I. Gradient Space (p,q) What is the reflectance map? Announcements I HW 3 due 12 noon, tomorrow. HW 4 to be posted soon recognition Lecture plan recognition for next two lectures, then video and motion. Introduction to Computer Vision CSE 152 Lecture 17

More information

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK 1 Po-Jen Lai ( 賴柏任 ), 2 Chiou-Shann Fuh ( 傅楸善 ) 1 Dept. of Electrical Engineering, National Taiwan University, Taiwan 2 Dept.

More information

Last update: May 4, Vision. CMSC 421: Chapter 24. CMSC 421: Chapter 24 1

Last update: May 4, Vision. CMSC 421: Chapter 24. CMSC 421: Chapter 24 1 Last update: May 4, 200 Vision CMSC 42: Chapter 24 CMSC 42: Chapter 24 Outline Perception generally Image formation Early vision 2D D Object recognition CMSC 42: Chapter 24 2 Perception generally Stimulus

More information

Color and Shading. Color. Shapiro and Stockman, Chapter 6. Color and Machine Vision. Color and Perception

Color and Shading. Color. Shapiro and Stockman, Chapter 6. Color and Machine Vision. Color and Perception Color and Shading Color Shapiro and Stockman, Chapter 6 Color is an important factor for for human perception for object and material identification, even time of day. Color perception depends upon both

More information

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009

Learning 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 information

TEXTURE CLASSIFICATION BY LOCAL SPATIAL PATTERN MAPPING BASED ON COMPLEX NETWORK MODEL. Srisupang Thewsuwan and Keiichi Horio

TEXTURE CLASSIFICATION BY LOCAL SPATIAL PATTERN MAPPING BASED ON COMPLEX NETWORK MODEL. Srisupang Thewsuwan and Keiichi Horio International Journal of Innovative Computing, Information and Control ICIC International c 2018 ISSN 1349-4198 Volume 14, Numer 3, June 2018 pp. 1113 1121 TEXTURE CLASSIFICATION BY LOCAL SPATIAL PATTERN

More information

Yudistira Pictures; Universitas Brawijaya

Yudistira Pictures; Universitas Brawijaya Evaluation of Feature Detector-Descriptor for Real Object Matching under Various Conditions of Ilumination and Affine Transformation Novanto Yudistira1, Achmad Ridok2, Moch Ali Fauzi3 1) Yudistira Pictures;

More information

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS

SUMMARY: 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 information

CEng 477 Introduction to Computer Graphics Fall 2007

CEng 477 Introduction to Computer Graphics Fall 2007 Visible Surface Detection CEng 477 Introduction to Computer Graphics Fall 2007 Visible Surface Detection Visible surface detection or hidden surface removal. Realistic scenes: closer objects occludes the

More information

Multiple-Choice Questionnaire Group C

Multiple-Choice Questionnaire Group C Family name: Vision and Machine-Learning Given name: 1/28/2011 Multiple-Choice naire Group C No documents authorized. There can be several right answers to a question. Marking-scheme: 2 points if all right

More information

Different types of images. Taxonomy of fixed images. Introduction to image databases. Chapter VI: Image Databases

Different types of images. Taxonomy of fixed images. Introduction to image databases. Chapter VI: Image Databases Visual nformation Systems ifferent types of images Taxonomy of fixed images ntroduction to image dataases mages Simple Picture irect Complex yrid Picture ndirect Chapter V: mage ataases rawing Visual Surrogate

More information

So far, we have considered only local models of illumination; they only account for incident light coming directly from the light sources.

So far, we have considered only local models of illumination; they only account for incident light coming directly from the light sources. 11 11.1 Basics So far, we have considered only local models of illumination; they only account for incident light coming directly from the light sources. Global models include incident light that arrives

More information

Aalborg Universitet. A new approach for detecting local features Nguyen, Phuong Giang; Andersen, Hans Jørgen

Aalborg Universitet. A new approach for detecting local features Nguyen, Phuong Giang; Andersen, Hans Jørgen Aalborg Universitet A new approach for detecting local features Nguyen, Phuong Giang; Andersen, Hans Jørgen Published in: International Conference on Computer Vision Theory and Applications Publication

More information

Computer Vision I - Appearance-based Matching and Projective Geometry

Computer Vision I - Appearance-based Matching and Projective Geometry Computer Vision I - Appearance-based Matching and Projective Geometry Carsten Rother 01/11/2016 Computer Vision I: Image Formation Process Roadmap for next four lectures Computer Vision I: Image Formation

More information

Features Points. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE)

Features Points. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE) Features Points Andrea Torsello DAIS Università Ca Foscari via Torino 155, 30172 Mestre (VE) Finding Corners Edge detectors perform poorly at corners. Corners provide repeatable points for matching, so

More information

Evaluation and comparison of interest points/regions

Evaluation and comparison of interest points/regions Introduction Evaluation and comparison of interest points/regions Quantitative evaluation of interest point/region detectors points / regions at the same relative location and area Repeatability rate :

More information

Robotics Programming Laboratory

Robotics Programming Laboratory Chair of Software Engineering Robotics Programming Laboratory Bertrand Meyer Jiwon Shin Lecture 8: Robot Perception Perception http://pascallin.ecs.soton.ac.uk/challenges/voc/databases.html#caltech car

More information

Visualisatie BMT. Rendering. Arjan Kok

Visualisatie BMT. Rendering. Arjan Kok Visualisatie BMT Rendering Arjan Kok a.j.f.kok@tue.nl 1 Lecture overview Color Rendering Illumination 2 Visualization pipeline Raw Data Data Enrichment/Enhancement Derived Data Visualization Mapping Abstract

More information

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking Feature descriptors Alain Pagani Prof. Didier Stricker Computer Vision: Object and People Tracking 1 Overview Previous lectures: Feature extraction Today: Gradiant/edge Points (Kanade-Tomasi + Harris)

More information

Automatic Image Alignment (feature-based)

Automatic Image Alignment (feature-based) Automatic Image Alignment (feature-based) Mike Nese with a lot of slides stolen from Steve Seitz and Rick Szeliski 15-463: Computational Photography Alexei Efros, CMU, Fall 2006 Today s lecture Feature

More information

Local features: detection and description. Local invariant features

Local features: detection and description. Local invariant features Local features: detection and description Local invariant features Detection of interest points Harris corner detection Scale invariant blob detection: LoG Description of local patches SIFT : Histograms

More information

Evaluating Color and Shape Invariant Image Indexing of Consumer Photography T. Gevers and A.W.M. Smeulders Faculty of Mathematics & Computer Science,

Evaluating Color and Shape Invariant Image Indexing of Consumer Photography T. Gevers and A.W.M. Smeulders Faculty of Mathematics & Computer Science, Evaluating Color and Shape Invariant Image Indexing of Consumer Photography T. Gevers and A.W.M. Smeulders Faculty of Mathematics & Computer Science, University of Amsterdam Kruislaan 3, 19 SJ Amsterdam,

More information

Moving cast shadow detection of vehicle using combined color models

Moving cast shadow detection of vehicle using combined color models Moving cast shadow detection of vehicle using comined color models Bangyu Sun 1 Shutao Li 1 1. College of Electrical Information Engineering, Hunan University, Changsha, 41008, China E-mail: jinjin135@16.com;

More information

2 Related Work Very large digital image archives have been created and used in a number of applications including archives of images of postal stamps,

2 Related Work Very large digital image archives have been created and used in a number of applications including archives of images of postal stamps, The PicToSeek WWW Image Search System Theo Gevers and Arnold W. M. Smeulders Faculty of Mathematics & Computer Science, University of Amsterdam Kruislaan 403, 1098 SJ Amsterdam, The Netherlands E-mail:

More information

Visualization Concepts

Visualization Concepts AML710 CAD LECTURE 36 Visualization Concepts Visible Lines and Surfaces Visibility - Hidden lines / Surfaces Many applications require the visibility determination for lines, points, edges, surfaces or

More information

Shadows in the graphics pipeline

Shadows in the graphics pipeline Shadows in the graphics pipeline Steve Marschner Cornell University CS 569 Spring 2008, 19 February There are a number of visual cues that help let the viewer know about the 3D relationships between objects

More information

Digital Vision Face recognition

Digital Vision Face recognition Ulrik Söderström ulrik.soderstrom@tfe.umu.se 27 May 2007 Digital Vision Face recognition 1 Faces Faces are integral to human interaction Manual facial recognition is already used in everyday authentication

More information

Color Constancy from Hyper-Spectral Data

Color Constancy from Hyper-Spectral Data Color Constancy from Hyper-Spectral Data Th. Gevers, H. M. G. Stokman, J. van de Weijer Faculty of Science, University of Amsterdam, The Netherlands fgevers, stokman, joostwg@wins.uva.nl Abstract This

More information

Outline 7/2/201011/6/

Outline 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 information

Colour Reading: Chapter 6. Black body radiators

Colour Reading: Chapter 6. Black body radiators Colour Reading: Chapter 6 Light is produced in different amounts at different wavelengths by each light source Light is differentially reflected at each wavelength, which gives objects their natural colours

More information

[2006] IEEE. Reprinted, with permission, from [Wenjing Jia, Huaifeng Zhang, Xiangjian He, and Qiang Wu, A Comparison on Histogram Based Image

[2006] IEEE. Reprinted, with permission, from [Wenjing Jia, Huaifeng Zhang, Xiangjian He, and Qiang Wu, A Comparison on Histogram Based Image [6] IEEE. Reprinted, with permission, from [Wenjing Jia, Huaifeng Zhang, Xiangjian He, and Qiang Wu, A Comparison on Histogram Based Image Matching Methods, Video and Signal Based Surveillance, 6. AVSS

More information

Object color forma9on

Object color forma9on Color Oject color forma9on The color of an oject is determined y its reflectance ρλ and the visile wavelenghts of the light it is exposed with and angle. Ojects change their color due to different factors:

More information

Digital Image Processing

Digital Image Processing Digital Image Processing Part 9: Representation and Description AASS Learning Systems Lab, Dep. Teknik Room T1209 (Fr, 11-12 o'clock) achim.lilienthal@oru.se Course Book Chapter 11 2011-05-17 Contents

More information

CS 664 Segmentation. Daniel Huttenlocher

CS 664 Segmentation. Daniel Huttenlocher CS 664 Segmentation Daniel Huttenlocher Grouping Perceptual Organization Structural relationships between tokens Parallelism, symmetry, alignment Similarity of token properties Often strong psychophysical

More information

Chapter 4. Chapter 4. Computer Graphics 2006/2007 Chapter 4. Introduction to 3D 1

Chapter 4. Chapter 4. Computer Graphics 2006/2007 Chapter 4. Introduction to 3D 1 Chapter 4 Chapter 4 Chapter 4. Introduction to 3D graphics 4.1 Scene traversal 4.2 Modeling transformation 4.3 Viewing transformation 4.4 Clipping 4.5 Hidden faces removal 4.6 Projection 4.7 Lighting 4.8

More information

Computational Photography and Video: Intrinsic Images. Prof. Marc Pollefeys Dr. Gabriel Brostow

Computational Photography and Video: Intrinsic Images. Prof. Marc Pollefeys Dr. Gabriel Brostow Computational Photography and Video: Intrinsic Images Prof. Marc Pollefeys Dr. Gabriel Brostow Last Week Schedule Computational Photography and Video Exercises 18 Feb Introduction to Computational Photography

More information

Announcements. Stereo Vision Wrapup & Intro Recognition

Announcements. Stereo Vision Wrapup & Intro Recognition Announcements Stereo Vision Wrapup & Intro Introduction to Computer Vision CSE 152 Lecture 17 HW3 due date postpone to Thursday HW4 to posted by Thursday, due next Friday. Order of material we ll first

More information

Ray-Tracing. Misha Kazhdan

Ray-Tracing. Misha Kazhdan Ray-Tracing Misha Kazhdan Ray-Tracing In graphics, we often represent the surface of a 3D shape by a set of triangles. Goal: Ray-Tracing Take a collection of triangles representing a 3D scene and render

More information

Local Illumination. CMPT 361 Introduction to Computer Graphics Torsten Möller. Machiraju/Zhang/Möller

Local Illumination. CMPT 361 Introduction to Computer Graphics Torsten Möller. Machiraju/Zhang/Möller Local Illumination CMPT 361 Introduction to Computer Graphics Torsten Möller Graphics Pipeline Hardware Modelling Transform Visibility Illumination + Shading Perception, Interaction Color Texture/ Realism

More information

Local Image preprocessing (cont d)

Local 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 information

An Algorithm to Determine the Chromaticity Under Non-uniform Illuminant

An Algorithm to Determine the Chromaticity Under Non-uniform Illuminant An Algorithm to Determine the Chromaticity Under Non-uniform Illuminant Sivalogeswaran Ratnasingam and Steve Collins Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, United Kingdom

More information

12/3/2009. What is Computer Vision? Applications. Application: Assisted driving Pedestrian and car detection. Application: Improving online search

12/3/2009. What is Computer Vision? Applications. Application: Assisted driving Pedestrian and car detection. Application: Improving online search Introduction to Artificial Intelligence V22.0472-001 Fall 2009 Lecture 26: Computer Vision Rob Fergus Dept of Computer Science, Courant Institute, NYU Slides from Andrew Zisserman What is Computer Vision?

More information

General Principles of 3D Image Analysis

General Principles of 3D Image Analysis General Principles of 3D Image Analysis high-level interpretations objects scene elements Extraction of 3D information from an image (sequence) is important for - vision in general (= scene reconstruction)

More information

Computer Vision I - Appearance-based Matching and Projective Geometry

Computer Vision I - Appearance-based Matching and Projective Geometry Computer Vision I - Appearance-based Matching and Projective Geometry Carsten Rother 05/11/2015 Computer Vision I: Image Formation Process Roadmap for next four lectures Computer Vision I: Image Formation

More information

Object Recognition with Invariant Features

Object Recognition with Invariant Features Object Recognition with Invariant Features Definition: Identify objects or scenes and determine their pose and model parameters Applications Industrial automation and inspection Mobile robots, toys, user

More information

TA Section 7 Problem Set 3. SIFT (Lowe 2004) Shape Context (Belongie et al. 2002) Voxel Coloring (Seitz and Dyer 1999)

TA Section 7 Problem Set 3. SIFT (Lowe 2004) Shape Context (Belongie et al. 2002) Voxel Coloring (Seitz and Dyer 1999) TA Section 7 Problem Set 3 SIFT (Lowe 2004) Shape Context (Belongie et al. 2002) Voxel Coloring (Seitz and Dyer 1999) Sam Corbett-Davies TA Section 7 02-13-2014 Distinctive Image Features from Scale-Invariant

More information

3D Modeling using multiple images Exam January 2008

3D Modeling using multiple images Exam January 2008 3D Modeling using multiple images Exam January 2008 All documents are allowed. Answers should be justified. The different sections below are independant. 1 3D Reconstruction A Robust Approche Consider

More information

Retrieving images based on a specific place in a living room

Retrieving images based on a specific place in a living room Retrieving images based on a specific place in a living room Anouk E.M. Visser 6277209 Bachelor thesis Credits: 18 EC Bachelor Opleiding Kunstmatige Intelligentie University of Amsterdam Faculty of Science

More information

Light source estimation using feature points from specular highlights and cast shadows

Light source estimation using feature points from specular highlights and cast shadows Vol. 11(13), pp. 168-177, 16 July, 2016 DOI: 10.5897/IJPS2015.4274 Article Number: F492B6D59616 ISSN 1992-1950 Copyright 2016 Author(s) retain the copyright of this article http://www.academicjournals.org/ijps

More information

Basic distinctions. Definitions. Epstein (1965) familiar size experiment. Distance, depth, and 3D shape cues. Distance, depth, and 3D shape cues

Basic distinctions. Definitions. Epstein (1965) familiar size experiment. Distance, depth, and 3D shape cues. Distance, depth, and 3D shape cues Distance, depth, and 3D shape cues Pictorial depth cues: familiar size, relative size, brightness, occlusion, shading and shadows, aerial/ atmospheric perspective, linear perspective, height within image,

More information

Illumination and Reflectance

Illumination and Reflectance COMP 546 Lecture 12 Illumination and Reflectance Tues. Feb. 20, 2018 1 Illumination and Reflectance Shading Brightness versus Lightness Color constancy Shading on a sunny day N(x) L N L Lambert s (cosine)

More information

Classification and Detection in Images. D.A. Forsyth

Classification and Detection in Images. D.A. Forsyth Classification and Detection in Images D.A. Forsyth Classifying Images Motivating problems detecting explicit images classifying materials classifying scenes Strategy build appropriate image features train

More information

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation Object detection using Region Proposals (RCNN) Ernest Cheung COMP790-125 Presentation 1 2 Problem to solve Object detection Input: Image Output: Bounding box of the object 3 Object detection using CNN

More information

SCALE INVARIANT FEATURE TRANSFORM (SIFT)

SCALE 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 information

CS 534: Computer Vision Segmentation and Perceptual Grouping

CS 534: Computer Vision Segmentation and Perceptual Grouping CS 534: Computer Vision Segmentation and Perceptual Grouping Spring 2005 Ahmed Elgammal Dept of Computer Science CS 534 Segmentation - 1 Where are we? Image Formation Human vision Cameras Geometric Camera

More information

Game Programming. Bing-Yu Chen National Taiwan University

Game Programming. Bing-Yu Chen National Taiwan University Game Programming Bing-Yu Chen National Taiwan University What is Computer Graphics? Definition the pictorial synthesis of real or imaginary objects from their computer-based models descriptions OUTPUT

More information

CHAPTER 3. Single-view Geometry. 1. Consequences of Projection

CHAPTER 3. Single-view Geometry. 1. Consequences of Projection CHAPTER 3 Single-view Geometry When we open an eye or take a photograph, we see only a flattened, two-dimensional projection of the physical underlying scene. The consequences are numerous and startling.

More information

An Introduction to Content Based Image Retrieval

An Introduction to Content Based Image Retrieval CHAPTER -1 An Introduction to Content Based Image Retrieval 1.1 Introduction With the advancement in internet and multimedia technologies, a huge amount of multimedia data in the form of audio, video and

More information

Illumination and Shading

Illumination and Shading Illumination and Shading Light sources emit intensity: assigns intensity to each wavelength of light Humans perceive as a colour - navy blue, light green, etc. Exeriments show that there are distinct I

More information

Implementation of 3D Object Recognition Based on Correspondence Grouping Final Report

Implementation of 3D Object Recognition Based on Correspondence Grouping Final Report Implementation of 3D Object Recognition Based on Correspondence Grouping Final Report Jamison Miles, Kevin Sheng, Jeffrey Huang May 15, 2017 Instructor: Jivko Sinapov I. Abstract Currently, the Segbots

More information

Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision

Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision What Happened Last Time? Human 3D perception (3D cinema) Computational stereo Intuitive explanation of what is meant by disparity Stereo matching

More information

Loop detection and extended target tracking using laser data

Loop detection and extended target tracking using laser data Licentiate seminar 1(39) Loop detection and extended target tracking using laser data Karl Granström Division of Automatic Control Department of Electrical Engineering Linköping University Linköping, Sweden

More information

Announcements. Recognition. Recognition. Recognition. Recognition. Homework 3 is due May 18, 11:59 PM Reading: Computer Vision I CSE 152 Lecture 14

Announcements. Recognition. Recognition. Recognition. Recognition. Homework 3 is due May 18, 11:59 PM Reading: Computer Vision I CSE 152 Lecture 14 Announcements Computer Vision I CSE 152 Lecture 14 Homework 3 is due May 18, 11:59 PM Reading: Chapter 15: Learning to Classify Chapter 16: Classifying Images Chapter 17: Detecting Objects in Images Given

More information

2D Image Processing Feature Descriptors

2D Image Processing Feature Descriptors 2D Image Processing Feature Descriptors Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Overview

More information

Pipeline Operations. CS 4620 Lecture 10

Pipeline Operations. CS 4620 Lecture 10 Pipeline Operations CS 4620 Lecture 10 2008 Steve Marschner 1 Hidden surface elimination Goal is to figure out which color to make the pixels based on what s in front of what. Hidden surface elimination

More information

Color Constancy from Illumination Changes

Color Constancy from Illumination Changes (MIRU2004) 2004 7 153-8505 4-6-1 E E-mail: {rei,robby,ki}@cvl.iis.u-tokyo.ac.jp Finlayson [10] Color Constancy from Illumination Changes Rei KAWAKAMI,RobbyT.TAN, and Katsushi IKEUCHI Institute of Industrial

More information

Segmentation by Clustering

Segmentation by Clustering KECE471 Computer Vision Segmentation by Clustering Chang-Su Kim Chapter 14, Computer Vision by Forsyth and Ponce Note: Dr. Forsyth s notes are partly used. Jae-Kyun Ahn in Korea University made the first

More information

Computer Vision for HCI. Topics of This Lecture

Computer 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 information

Visual Learning and Recognition of 3D Objects from Appearance

Visual Learning and Recognition of 3D Objects from Appearance Visual Learning and Recognition of 3D Objects from Appearance (H. Murase and S. Nayar, "Visual Learning and Recognition of 3D Objects from Appearance", International Journal of Computer Vision, vol. 14,

More information

Supervised Sementation: Pixel Classification

Supervised Sementation: Pixel Classification Supervised Sementation: Pixel Classification Example: A Classification Problem Categorize images of fish say, Atlantic salmon vs. Pacific salmon Use features such as length, width, lightness, fin shape

More information

Object and Class Recognition I:

Object and Class Recognition I: Object and Class Recognition I: Object Recognition Lectures 10 Sources ICCV 2005 short courses Li Fei-Fei (UIUC), Rob Fergus (Oxford-MIT), Antonio Torralba (MIT) http://people.csail.mit.edu/torralba/iccv2005

More information

ANDROID BASED OBJECT RECOGNITION AND MOTION DETECTION TO AID VISUALLY IMPAIRED

ANDROID BASED OBJECT RECOGNITION AND MOTION DETECTION TO AID VISUALLY IMPAIRED ISSN 2320 2602 Volume 3, No.10, October 2014 Neha Bari et International al., Journal of of Advances in Computer in Computer Science and Science Technology, and 3(10), Technology October 2014, 462 466 Available

More information

Simultaneous surface texture classification and illumination tilt angle prediction

Simultaneous surface texture classification and illumination tilt angle prediction Simultaneous surface texture classification and illumination tilt angle prediction X. Lladó, A. Oliver, M. Petrou, J. Freixenet, and J. Martí Computer Vision and Robotics Group - IIiA. University of Girona

More information

AUTOMATIC IDENTIFICATION OF PORTRAITS IN ART IMAGES DATABASES

AUTOMATIC IDENTIFICATION OF PORTRAITS IN ART IMAGES DATABASES AUTOMATIC IDENTIFICATION OF PORTRAITS IN ART IMAGES DATABASES E. Šikudová, M. Gavrielides, I. Pitas Department of Informatics Aristotle University of Thessaloniki Box 451, Thessaloniki 541 24, GREECE E-mail:

More information

Image processing and features

Image processing and features Image processing and features Gabriele Bleser gabriele.bleser@dfki.de Thanks to Harald Wuest, Folker Wientapper and Marc Pollefeys Introduction Previous lectures: geometry Pose estimation Epipolar geometry

More information

ELEC Dr Reji Mathew Electrical Engineering UNSW

ELEC Dr Reji Mathew Electrical Engineering UNSW ELEC 4622 Dr Reji Mathew Electrical Engineering UNSW Review of Motion Modelling and Estimation Introduction to Motion Modelling & Estimation Forward Motion Backward Motion Block Motion Estimation Motion

More information

Photo-realistic Renderings for Machines Seong-heum Kim

Photo-realistic Renderings for Machines Seong-heum Kim Photo-realistic Renderings for Machines 20105034 Seong-heum Kim CS580 Student Presentations 2016.04.28 Photo-realistic Renderings for Machines Scene radiances Model descriptions (Light, Shape, Material,

More information

Lecture 15: Shading-I. CITS3003 Graphics & Animation

Lecture 15: Shading-I. CITS3003 Graphics & Animation Lecture 15: Shading-I CITS3003 Graphics & Animation E. Angel and D. Shreiner: Interactive Computer Graphics 6E Addison-Wesley 2012 Objectives Learn that with appropriate shading so objects appear as threedimensional

More information

Motion Tracking and Event Understanding in Video Sequences

Motion Tracking and Event Understanding in Video Sequences Motion Tracking and Event Understanding in Video Sequences Isaac Cohen Elaine Kang, Jinman Kang Institute for Robotics and Intelligent Systems University of Southern California Los Angeles, CA Objectives!

More information

Announcements. Introduction. Why is this hard? What is Computer Vision? We all make mistakes. What do you see? Class Web Page is up:

Announcements. Introduction. Why is this hard? What is Computer Vision? We all make mistakes. What do you see? Class Web Page is up: Announcements Introduction Computer Vision I CSE 252A Lecture 1 Class Web Page is up: http://www.cs.ucsd.edu/classes/wi05/cse252a/ Assignment 0: Getting Started with Matlab is posted to web page, due 1/13/04

More information

Computer Vision. Image Segmentation. 10. Segmentation. Computer Engineering, Sejong University. Dongil Han

Computer Vision. Image Segmentation. 10. Segmentation. Computer Engineering, Sejong University. Dongil Han Computer Vision 10. Segmentation Computer Engineering, Sejong University Dongil Han Image Segmentation Image segmentation Subdivides an image into its constituent regions or objects - After an image has

More information

CS 4495 Computer Vision A. Bobick. CS 4495 Computer Vision. Features 2 SIFT descriptor. Aaron Bobick School of Interactive Computing

CS 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 information

Digital Image Fundamentals

Digital Image Fundamentals Digital Image Fundamentals Image Quality Objective/ subjective Machine/human beings Mathematical and Probabilistic/ human intuition and perception 6 Structure of the Human Eye photoreceptor cells 75~50

More information

Local Features Tutorial: Nov. 8, 04

Local 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 information

Pipeline Operations. CS 4620 Lecture Steve Marschner. Cornell CS4620 Spring 2018 Lecture 11

Pipeline Operations. CS 4620 Lecture Steve Marschner. Cornell CS4620 Spring 2018 Lecture 11 Pipeline Operations CS 4620 Lecture 11 1 Pipeline you are here APPLICATION COMMAND STREAM 3D transformations; shading VERTEX PROCESSING TRANSFORMED GEOMETRY conversion of primitives to pixels RASTERIZATION

More information

Journal of Asian Scientific Research FEATURES COMPOSITION FOR PROFICIENT AND REAL TIME RETRIEVAL IN CBIR SYSTEM. Tohid Sedghi

Journal of Asian Scientific Research FEATURES COMPOSITION FOR PROFICIENT AND REAL TIME RETRIEVAL IN CBIR SYSTEM. Tohid Sedghi Journal of Asian Scientific Research, 013, 3(1):68-74 Journal of Asian Scientific Research journal homepage: http://aessweb.com/journal-detail.php?id=5003 FEATURES COMPOSTON FOR PROFCENT AND REAL TME RETREVAL

More information