Outline Texture modeling - continued Filtering-based approaches.

Slides:



Advertisements
Similar presentations
CS Spring 2009 CS 414 – Multimedia Systems Design Lecture 4 – Digital Image Representation Klara Nahrstedt Spring 2009.
Advertisements

Face Recognition. Introduction Why we are interested in face recognition? Why we are interested in face recognition? Passport control at terminals in.
EDGE DETECTION ARCHANA IYER AADHAR AUTHENTICATION.
Texture. Edge detectors find differences in overall intensity. Average intensity is only simplest difference. many slides from David Jacobs.
Lecture 07 Segmentation Lecture 07 Segmentation Mata kuliah: T Computer Vision Tahun: 2010.
1 Building a Dictionary of Image Fragments Zicheng Liao Ali Farhadi Yang Wang Ian Endres David Forsyth Department of Computer Science, University of Illinois.
Chapter 10 Image Segmentation.
Text Detection in Video Min Cai Background  Video OCR: Text detection, extraction and recognition  Detection Target: Artificial text  Text.
Texture Turk, 91.
RETRIEVAL OF MULTIMEDIA OBJECTS USING COLOR SEGMENTATION AND DIMENSION REDUCTION OF FEATURES Mingming Lu, Qiyu Zhang, Wei-Hung Cheng, Cheng-Chang Lu Department.
Primal Sketch Integrating Structure and Texture Ying Nian Wu UCLA Department of Statistics Keck Meeting April 28, 2006 Guo, Zhu, Wu (ICCV, 2003; GMBV,
TEXTURE SYNTHESIS PEI YEAN LEE. What is texture? Images containing repeating patterns Local & stationary.
Announcements For future problems sets: matlab code by 11am, due date (same as deadline to hand in hardcopy). Today’s reading: Chapter 9, except.
1 Lecture 12 Neighbourhood Operations (2) TK3813 DR MASRI AYOB.
Chapter 10 Image Segmentation.
Color a* b* Brightness L* Texture Original Image Features Feature combination E D 22 Boundary Processing Textons A B C A B C 22 Region Processing.
Texture Reading: Chapter 9 (skip 9.4) Key issue: How do we represent texture? Topics: –Texture segmentation –Texture-based matching –Texture synthesis.
Introduction to Computer Vision CS / ECE 181B Thursday, April 22, 2004  Edge detection (HO #5)  HW#3 due, next week  No office hours today.
CS292 Computational Vision and Language Visual Features - Colour and Texture.
Kernel Methods Part 2 Bing Han June 26, Local Likelihood Logistic Regression.
Run-Length Encoding for Texture Classification
Heather Dunlop : Advanced Perception January 25, 2006
Multiclass object recognition
Neighborhood Operations
Computer vision.
Following the work of John Daugman University of Cambridge
Texture. Texture is an innate property of all surfaces (clouds, trees, bricks, hair etc…). It refers to visual patterns of homogeneity and does not result.
1. General Image Operations Three type of image operations 1.Point operations 2.Geometric operations 3.Spatial operations.
Detection of nerves in Ultrasound Images using edge detection techniques NIRANJAN TALLAPALLY.
Stylization and Abstraction of Photographs Doug Decarlo and Anthony Santella.
Page  1 LAND COVER GEOSTATISTICAL CLASSIFICATION FOR REMOTE SENSING  Kęstutis Dučinskas, Lijana Stabingiene and Giedrius Stabingis  Department of Statistics,
Chap 7 Image Segmentation. Edge-Based Segmentation The edge information is used to determine boundaries of objects Pixel-based direct classification methods.
Image Classification for Automatic Annotation
Final Review Course web page: vision.cis.udel.edu/~cv May 21, 2003  Lecture 37.
MIT AI Lab / LIDS Laboatory for Information and Decision Systems & Artificial Intelligence Laboratory Massachusetts Institute of Technology A Unified Multiresolution.
Colour and Texture. Extract 3-D information Using Vision Extract 3-D information for performing certain tasks such as manipulation, navigation, and recognition.
Type of Vehicle Recognition Using Template Matching Method Electrical Engineering Department Petra Christian University Surabaya - Indonesia Thiang, Andre.
Machine Vision Edge Detection Techniques ENT 273 Lecture 6 Hema C.R.
Image Quality Measures Omar Javed, Sohaib Khan Dr. Mubarak Shah.
Detection of nerves in Ultrasound Images using edge detection techniques NIRANJAN TALLAPALLY.
Course : T Computer Vision
2. Skin - color filtering.
- photometric aspects of image formation gray level images
Distinctive Image Features from Scale-Invariant Keypoints
Built-up Extraction from RISAT Data Using Segmentation Approach
Journal of Vision. 2009;9(3):5. doi: /9.3.5 Figure Legend:
Classification techniques
Paper Presentation: Shape and Matching
Outline Announcement Local operations (continued) Linear filters
LINEAR AND NON-LINEAR CLASSIFICATION USING SVM and KERNELS
Outline Perceptual organization, grouping, and segmentation
Outline Perceptual organization, grouping, and segmentation
Outline Linear Shift-invariant system Linear filters
Outline Announcement Texture modeling - continued Some remarks
Outline S. C. Zhu, X. Liu, and Y. Wu, “Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo”, IEEE Transactions On Pattern Analysis And Machine.
Outline Neural networks - reviewed Texture modeling
Texture.
Object Recognition Today we will move on to… April 12, 2018
Digital Image Processing Week IV
Outline Texture modeling - continued Julesz ensemble.
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
Outline Announcement Perceptual organization, grouping, and segmentation Hough transform Read Chapter 17 of the textbook File: week14-m.ppt.
Mathematical Foundations of BME
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
Support vector machine-based text detection in digital video
Intensity Transform Contrast Stretching Y ← u0+γ*(Y-u)/s
Using Association Rules as Texture features
Outline Texture modeling - continued Markov Random Field models
Presentation transcript:

Outline Texture modeling - continued Filtering-based approaches

Visual Perception Modeling Texture Modeling The structures of images The structures in images are due to the inter-pixel relationships The key issue is how to characterize the relationships 9/18/2018 Visual Perception Modeling

Representing Textures through Filtering Convolving an image with a linear filter yields a representation of the image on a different basis The advantage of the transformation is that the process makes the local structure of the image “clear” A filter can be viewed as a template There is a strong response when the local image pattern looks similar to the filter kernel and a weak response when it does not 9/18/2018 Visual Perception Modeling

Representing Textures through Filtering – cont. 9/18/2018 Visual Perception Modeling

Representing Textures through Filtering – cont. 9/18/2018 Visual Perception Modeling

Representing Textures through Filtering – cont. Gabor filters Gabor filters have been widely in texture modeling Mathematically, Gabor filters are optimal in the sense of local joint spatial/frequency representation 9/18/2018 Visual Perception Modeling

Representing Textures through Filtering – cont. 9/18/2018 Visual Perception Modeling

Representing Textures through Filtering – cont. Problems with filtering-based approaches The filter response itself does not give rise to a representation or a model for textures Even for homogenous textures, the filter responses are not homogenous 9/18/2018 Visual Perception Modeling

Representing Textures through Filtering – cont. 9/18/2018 Visual Perception Modeling

Representing Textures through Filtering – cont. Non-linear smoothing In order to derive a more homogenous and meaningful feature for textures, the filter responses are then passed through a non-linear stage The hope is that smoothed filter response will be relative homogenous within a texture region This can be used for texture classification, texture boundary detection, and texture discrimination 9/18/2018 Visual Perception Modeling

Texture Classification Based on Filtering 9/18/2018 Visual Perception Modeling

Texture Classification Based on Filtering – cont. 9/18/2018 Visual Perception Modeling

Texture Classification Based on Filtering – cont. 9/18/2018 Visual Perception Modeling

Texture Classification Based on Filtering – cont. 9/18/2018 Visual Perception Modeling

Histograms of Filter Responses as Texture Models Histograms as texture features For homogenous textures, histograms should not change very much In other words, texture images with similar histograms of filter responses should look similar Heeger and Bergen proposed a texture synthesis algorithm based on this observation 9/18/2018 Visual Perception Modeling

Histograms of Filter Responses as Texture Models – cont. 9/18/2018 Visual Perception Modeling

Histograms of Filter Responses as Texture Models – cont. 9/18/2018 Visual Perception Modeling

Histograms of Filter Responses as Texture Models – cont. 9/18/2018 Visual Perception Modeling

Histograms of Filter Responses as Texture Models – cont. 9/18/2018 Visual Perception Modeling

Histograms of Filter Responses as Texture Models – cont. 9/18/2018 Visual Perception Modeling

Histograms of Filter Responses as Texture Models – cont. 9/18/2018 Visual Perception Modeling

Histograms of Filter Responses as Texture Models – cont. 9/18/2018 Visual Perception Modeling

Non-Parametric Sampling When we need to decide a pixel value, we calculate the conditional probability given the pixel values in the surrounding neighborhood This is done by finding the similar surrounding neighborhood in the given texture 9/18/2018 Visual Perception Modeling

Non-Parametric Sampling – cont. 9/18/2018 Visual Perception Modeling

Non-Parametric Sampling – cont. 9/18/2018 Visual Perception Modeling

Non-Parametric Sampling – cont. 9/18/2018 Visual Perception Modeling