基于亮度颜色文理边缘检测2试卷.pptx

Texture Features Texture Gradient TG(x,y,r,) Pixel-texture values are computed using 13 filters Pixels are thus represented with a 13-feature vector Each disk-half is modeled by a point cloud of vectors in 13-dimensional space Problem: How does one compare two 13D spaces? 0 Texture Features Solution: Textons estimate joint distribution using adaptive bins Filter response vectors are clustered using k-means Cluster centers represent texture primitives (textons) Example Texton set K = 64 Trained using 200 images 1 Texture Features 2 Texture Gradient TG(x,y,r,) Pixels in each disk-half are assigned to nearest texton 2 difference of texton histograms Textons are vector-quantized filter outputs TextonMap Feature Localization 3 Evaluation Boundary detector quality Used for optimizing parameters Comparing to other techniques Human-marked boundaries as ground truth 1000 images, 5-10 segmentations Highly consistent 4 Alternate Approaches Canny Detector Canny 1986 MATLAB implementation With and without hysteresis Second Moment Matrix Nitzberg/Mumford/Shiota 1993 cf. Förstner and Harris corner detectors Used by Konishi et al. 1999 in learning framework Logistic model trained on eigenspectrum 5 Summary Comments A simple linear model is sufficient for cue combination All cues weighted approximately equally in logistic Edge detection does not optimally for complex natural images Texture suppression is not sufficient Proposed method offers significant improvements Simple but powerful feature detectors Simple model for cue combination Surprisingly effective for a low level approach Likely isn’t robust to larger textures Offset by using multiple scales Prohibitively slow for on-line use Minutes per image after optimizations Normalized Cuts: Boundaries  Regions 6