Perceptually based techniques for image segmentation and semantic classification
Thrasyvoulos N. Pappas, Junqing Chen, Dejan Depalov · IEEE Communications Magazine · 2007
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. Applications include content-based image retrieval and region of interest extraction for efficient compression/transmission over heterogeneous networks