Title :
Perceptually based techniques for image segmentation and semantic classification
Author :
Pappas, Thrasyvoulos N. ; Chen, Junqing ; Depalov, Dejan
Author_Institution :
Northwestern Univ., Evanston, IL
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. Applications include content-based image retrieval and region of interest extraction for efficient compression/transmission over heterogeneous networks
Keywords :
image classification; image segmentation; content-based image retrieval; heterogeneous networks; human perception; image segmentation; natural scene segmentation; perceptually based techniques; region statistics; region-of-interest extraction; semantic classification; semantic image analysis; semantic information; Face detection; Humans; Image analysis; Image coding; Image color analysis; Image segmentation; Image texture analysis; Information analysis; Layout; Shape;
Journal_Title :
Communications Magazine, IEEE
DOI :
10.1109/MCOM.2007.284537
