Abstract :
Notice of Violation of IEEE Publication Principles
"Biologically-Inspired Model for Multi-Order Coloring Texture Boundary Detection"
by Tiending Chen,
in the Proceedings of the 2006 IEEE International Conference on Information Acquisition, August 20 - 23, 2006
After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE\´s Publication Principles.
This paper is a duplication of the original text from the paper cited below. The original text was copied without attribution and without permission.
Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following thesis:
"Biologically-Inspired Model for Hybrid-Order Chromatic Texture Boundary Detection"
by Tsung-Heng Tsai,
published at National Chiao-Tung University, July 2005It presents a hybrid-level texture image boundary detection algorithm inspired from human visual system (HVS). The proposed algorithm integrates three important visual primitives: luminance, texture, and color into a functional system. The paper focuses on relevant fundamental researches on HVS and systematic integration to investigate the task of texture boundary detection thoroughly. It employs the encoding form in HVS with systematic integration to build up a complete algorithm for texture boundary detection. Color images are firstly decomposed into three opponent axes and the 1st- and 2nd- order features are extracted by a Gaussian filter and Gabor filters. With the proposed adaptive weights selecting mechanism, the hybrid-order boundary can be obtained. Among extensive tests, boundaries between uniform textures can be detected successfully and accurately. For textures that are non-uniform or non-regular, the results also reflect some meaningful properties which are - consistent to human visual sensation. In addition to satisfying testing results, processing employed in this algorithm is very simple and intuitive with only few assumptions and no training procedure involved. Compared with the present researches, the proposed algorithm has a good application potential.
Keywords :
Gaussian processes; feature extraction; image colour analysis; image texture; Gabor filters; Gaussian filter; biologically-inspired model; color images; feature extraction; human visual system; hybrid-level texture image boundary detection algorithm; multi-order coloring texture boundary detection; adaptive weights selecting; biologically-inspired model; boundary detection; color texture;
