DocumentCode :
2269781
Title :
Eye illusion enhancement using interactive Differential Evolution
Author :
Mohamad, Zaid Salami ; Darvish, Arman ; Rahnamayan, Shahryar
Author_Institution :
Fac. of Eng. & Appl. Sci., Univ. of Ontario Inst. of Technol. (UOIT), Oshawa, ON, Canada
fYear :
2011
fDate :
11-15 April 2011
Firstpage :
1
Lastpage :
7
Abstract :
Eye illusion is one of the most interesting topics which attracts majority of the people. In this paper, an interactive evolutionary technique has been proposed to improve the illusion factor in eye illusion images. Eye illusion or vision illusion is subjective and can differ from person to person. This technique utilizes an evolutionary algorithm, namely Differential Evolution (DE), to improve the vision deceiving factor for an Eye Illusion image. Modeling of human vision perception is impossible or at least very complicated even for a specific person. So, proposing a general fitness function as an optimization objective would not be an easy task. That is why an interactive optimization approach seems a reasonable approach in this regard. To the best of our knowledge, the current work is the first attempt which utilizes an interactive optimization technique to enhance vision illusion images. Performance of the proposed approach is verified on two eye illusion test cases, but that is applicable to other eye illusion image enhancements and also image processing tasks, such as image filtering.
Keywords :
eye; image enhancement; medical image processing; optimisation; visual perception; eye image illusion enhancement; human vision perception; illusion test; image enhancement; image filtering; image processing; interactive differential evolution; optimization; vision illusion; Evolutionary computation; Filtering algorithms; Image processing; Next generation networking; Optimization; Particle separators; Pixel; Differential Evolution (DE); Eye Illusion; Image Enhancement; Interactive Evolutionary Algorithm (IEA);
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Differential Evolution (SDE), 2011 IEEE Symposium on
Conference_Location :
Paris
Print_ISBN :
978-1-61284-071-0
Type :
conf
DOI :
10.1109/SDE.2011.5952064
Filename :
5952064
Link To Document :
بازگشت