Title :
Knowledge-based semantic image segmentation and global precedence effect
Author :
Tab, Fardin Akhlaghian ; Naghdy, Glolshah
Author_Institution :
Sch. of Electr., Comput. & Telecommun. Eng., Univ. of Wollongong, Wollongong, NSW, Australia
fDate :
Nov. 30 2005-Dec. 1 2005
Abstract :
This paper introduces a knowledge-based semantic image segmentation which extracts the "object(s)-of-interest" from the image. Image templates are the high-level knowledge in the system. The major contribution of this work is the use of the "Global Precedence Effect" (forest before trees) of the human visual system (HVS) in image analysis and understanding. The "object-of-interest" is searched for hierarchically through an irregular pyramid by an affine invariant comparison between the different region combinations and the template starting from lowest to the highest resolutions. The global/large size objects are found at lower resolutions with significantly lower computational complexity.
Keywords :
data visualisation; feature extraction; image segmentation; knowledge based systems; Image template; computational complexity; global precedence effect; human visual system; image analysis; image segmentation; knowledge based semantic;
Conference_Titel :
Integration of Knowledge, Semantics and Digital Media Technology, 2005. EWIMT 2005. The 2nd European Workshop on the (Ref. No. 2005/11099)
Conference_Location :
London
Print_ISBN :
0-86341-595-4