Texture We would like to thank Amnon Drory for this deck הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע /לא מופיע במצגת. Syllabus • Textons • TextonsBoost Textons • • • • Run filter bank on images Build Texton dictionary using K-means Map texture image to histogram Histogram Similarity using Chi-square TextonBoost • • • • • Build Texton dictionary Texture Layout (pixel, rectangle, Texton) Count number of textons in rectangle Use Integral Image Generate multiple Texture layouts (Features) • For each class do 1-vs-all classifier: – For each pixel in class • Train GentleBoost Classifier • Map strong classifier to probability • Take Maximum value CRF/MRF • How to ensure Spatial Consistency? ML Xˆ ML ArgMax Pr obY | X PrY | X X PrX | Y Likelihood Posterior PrX Y Bayes PrY X PrX Xˆ MAP ArgMax PrY X PrX X ArgMin HY X AX 2 X MAP PrY PrX Const exp AX Prior Semantic Texton Forest • Decision Trees • Forest and Averaging • Split decision to minimize Entropy • Two level STF to add spatial regularization • Works well when there is ample data, does not generalize well (1) Textons B. Julesz, Leung, Malik M. Varma, A. Zisserman (II) TextonBoost J. Shotton, J. Winn, C. Rother, A. Criminisi (III) Semantic Texton Forests J. Shotton, M. Johnson, R. Cipolla (IV) Pose Recognition from Depth Images J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, A. Blake Textures Filter Bank K-means Texton Histogram Classification Results TextonBoost : Joint Appearance, Shape and Context Modeling for Multi-Class Object Recognition and Segmentation J. Shotton*, J. Winn†, C. Rother†, and A. Criminisi† * University of Cambridge † Microsoft Research Ltd, Cambridge, UK TextonBoost Simultaneous recognition and segmentation Explain every pixel TextonBoost 1. Input: Training: Images with pixel level ground truth classification MSRC 21 Database TextonBoost 1. 2. Input: Training: Images with pixel level ground truth classification. Testing: Images Output: A classification of each pixel in the test images to an object class. Conditional Random Field Unary Term Unary Term Binary Term Binary Term Textons • Shape filters use texton maps ([Varma & Zisserman IJCV 05], [Leung & Malik IJCV 01]) • Convolve with 17D filter bank (Gaussians, Derivatives of Gaussians, DoGs, LoGs) – Can use Gabor instead • Use k-means to create 400 clusters Clustering Texton map Input image Colors Texton Indices Filter Bank • Compact and efficient characterisation of local texture CRF: Unary Term ℎ 𝒙 = 𝑎𝛿 𝑣 𝑖, 𝑟, 𝑡 > 𝜃 + 𝑏 𝑐𝑜𝑛𝑠𝑡. 𝑀 𝐻 𝒙 = 𝑚=1 0.001 ℎ𝑚 𝒙 0.47 0.23 0.02 Probability of class c_i given feature vector x 𝑃𝑖 𝑐𝑖 𝒙 = 𝑦 𝑖𝑛 𝑐𝑙𝑎𝑠𝑠 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒 𝑒𝑥𝑝 𝐻 𝑐𝑖 𝑐′𝑖 𝑒𝑥𝑝 𝐻 𝑐′𝑖 0.1 Texture-Layout Filters up to 200 pixels • Pair: , ( rectangle r ) v(i1, r, t) = a texton t • Feature responses v(i, r, t) • Large bounding boxes enable long range interactions ( , ) ( , ) v(i3, r, t) = a/2 Texture Layout (Toy Example) CRF: Binary Term CRF: Binary Term Potts model encourages neighbouring pixels to have same label Contrast sensitivity encourages segmentation to follow image edges Accurate Segmentation? • Boosted classifier alone – effectively recognises objects – but not sufficient for pixelperfect segmentation • Conditional Random Field (CRF) – jointly classifies all pixels whilst respecting image edges unary term only CRF The TextonBoost CRF Unary Term Texture-Layout Color edge Binary Term location Location Term Texture-Layout Color edge Capture prior on absolute image location tree sky road location Color Term Texture-Layout Color edge location Texture-Layout Term Texton Boost - Summary Performs per-pixel classification using: 1. Statistics learned from Training Set: - Absolute location statistics - Configuration of textured areas around pixel of interest. 2. Cues from the Test Image: - Edges - Object Colors 3. Priors. Results on 21-Class Database building Effect of Model Components shape-texture Shape-texture potentials only: + edge potentials: + Color potentials: + location potentials: + edge 69.6% 70.3% 72.0% 72.2% + Color & location pixel-wise segmentation accuracies