Perceptual Image/Video Segmentation and Semantic...

Google Tech Talks February 2, 2007 ABSTRACT We present a new approach for semantic image analysis that combines knowledge of human perception with an understanding of signal characteristics to segment natural scenes into perceptually uniform regions, and then uses the region statistics to extract semantic information that can be used for intelligent and efficient image organization and retrieval. Our focus is on images of natural scenes. One of the challenges of this problem is that the statistical characteristics of perceptually uniform regions are spatially-varying due to effects of lighting, perspective, scale changes, etc. We present a new adaptive perceptual color-texture segmentation...