Determining regions of interest in synthetic images

作者: Andreas Girgensohn , Qiong Liu , Patrick Chiu

DOI:

关键词:

摘要: An algorithm for finding regions of interest (ROI) in synthetic images based on an information driven approach which sub-blocks a set image are analyzed content or compressibility textural and color features. A DCT may be used to analyze the features histogram images. Sub-blocks low grouped into ROIs using type morphological technique. Unlike other algorithms that geared highly specific types ROI (e.g. OCR text detection), method present invention is generally applicable arbitrary The can with several applications, including Stained-Glass collages presentations.

参考文章(67)
Nancy Ide, Jean Véronis, Word Sense Disambiguation: The State of the Art ,(2005)
Jinhong Katherine Guo, Yuan Cheng, Method of texture-based color document segmentation ,(2002)
Jiebo Luo, David J. Crandall, Method for detecting color objects in digital images ,(2003)
Beatriz Marcotegui, Ramon Morros, Ferran Marques, Sylvie Jeannin, Fernand Meyer, Montse Pardas, Philippe Salembier, Lionel Bouchard, Isabelle Corset, Segmented picture coding method and system, and corresponding decoding method and system ,(1996)
Hideo Takiguchi, Masakazu Matsugu, Koji Hatanaka, Image extraction apparatus and method ,(2000)
Andreas Girgensohn, Lynn Wilcox, Forrest H Bennett, Wolf Polak, Patrick Chiu, Eleanor Rieffel, A genetic segmentation algorithm for image data streams and video genetic and evolutionary computation conference. pp. 666- 673 ,(2000)