TexturesImage Segmentation
SummaryTextures
Textures and their usage inImage Segmentation
Martin Petrıcek
April 14, 2011
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryTextures
TexturesFeaturesIllumination invariance
Image Segmentation
Summary
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryTextures
Textures
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
FeaturesIllumination invariance
Texture features - colorspaces
I Several colospacesI RGB - acquisition colorspaceI HSV - perceptual colorspaceI L*A*B* - based on human vision
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
FeaturesIllumination invariance
Texture features - CM
I Co-occurence matrixI Which colors occur in texture together?I QuantizationI RSCCM - Reduced Size Chromatic Co-occurence MatrixI Haralick Features
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
FeaturesIllumination invariance
Texture features - Haralick Features
I Co-occurence matrix featuresI Angular second momentI ContrastI CorrelationI Sum of squares: varianceI Inverse difference momewntI Sum averageI Sum varianceI Sum entropyI EntropyI Difference varianceI Difference entropyI Information measures of correlationI Maximal correlation coefficient
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
FeaturesIllumination invariance
Training
I Classify images into categoriesI Tedious
I Classify several image pairsI Must-link or cannot-link constraints (Same or different class)
I Selection of most relevant texture featuresI based on Laplacian score
I projections of same classes should be together
I based on constraint scoreI relevance with must-links and cannot-link constraints
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
FeaturesIllumination invariance
Results
I Constraint score is better
100 %92 % 89 %
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
FeaturesIllumination invariance
Illumination invariance
I Different light sources,different spectralcharacteristics
I Black body radiation,different temperatures
I Light sources with narrowspectrum
I Human eye can adapt
I Metameres
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
FeaturesIllumination invariance
Illumination models
I Illumination modelsI DiagonalI Diagonal-OffsetI Affine
R ′ = R × αr + βrG ′ = G × αg + βgB ′ = B × αb + βb
R ′ = R × αrr + G × αrg + B × αrb + βrG ′ = R ×αgr +G ×αgg +B ×αgb +βgB ′ = R ×αbr +G ×αbg +B ×αbb + βb
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
FeaturesIllumination invariance
Illumination invariance - solution
I Normalize colors beforecomputing features
I Assume diagonal model
I Normalize using FFT
I Use Gabor filtering or Locallinear transform on result
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryImage Segmentation
Image Segmentation
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryImage Segmentation
Training data
I We need to obtain training data
I Manually tracing examples istedious
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryImage Segmentation
Alternate approach
I Manually pick a bounding boxaround object
I Inside: object and some parts ofbackground
I Outside: only background
I Less precise
I Much faster, more images intraining set
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryImage Segmentation
Algorithm
I Split images into superpixels - patches of same texture
I Use patches to learn the system
I Learn using texture features from patches
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryImage Segmentation
Algorithm
I Fully segmented dataI Markov Random FieldsI Conditional Random FieldsI BoostingI SVM
I Partially segmented dataI Multiple Instance Learning
I 1. Identify positive in training dataI 2. Learn to distinguish positive and negative
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryImage Segmentation
Active learning
I Find out images with patches close to decision boundary
I Get user help with classifying these patches
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
SummaryImage Segmentation
Improvement - Background
I Use background information to improveaccuracy
I Cow is more likely to be on grass
I Car is more likely to be on road
Martin Petrıcek Textures and their usage in Image Segmentation
TexturesImage Segmentation
Summary
LiteratureQuestions
Literature
I Rahat Khan, Damien Muselet and Alain Tremeau, Classicaltexture features and illumination color variations
I M. Kalakech, A. Porebski, P. Biela, D. Hamad and L.Macaire, Constraint score for semi-supervised selection ofcolor texture features
I Jaume Amores, David Geronimo, Antonio Lopez, MultipleInstance and Active Learning for weakly-supervisedobject-class segmentation
I R. Haralick, K. Shanmugan and I. Dinstein, Textural featuresfor image classification
Martin Petrıcek Textures and their usage in Image Segmentation
Top Related