- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
AN EVOLUTIONARY BASED IMAGE GENERATOR | ||
| Journal of Al-Nahrain University - Science | ||
| Article 1, Volume 13, Issue 2, 2010, Pages 235-246 | ||
| Author | ||
| Amenah Dahim Abooud | ||
| Abstract | ||
| This paper presents a fast algorithm that utilizes evolutionary algorithm for patch based image generation. The algorithm attempts to find the most appropriate collection of source square image patches that can generate altogether a given colored/gray target image. Each patch holds complete information for both luminance and chromatic components from the source image to be used to generate a specified target patch. The difficulties are occurred when chromatic and luminance information is to be transferred to a blank canvas to generate a specified target image. The proposed Evolutionary Algorithm (EA) is used to overcome these difficulties and attempts to find an acceptable and perceived solution to this problem by the search for best patch luminance matching until a specified number of generations is met. Also, this algorithm modifies the traditional uniform crossover to a multi-sexual recombination operator which inherits vital genes among all individual to one super generated offspring. All other offspring are generated by mutating that super offspring. The experimental results have demonstrated that good results can be obtained with reasonable convergence speed. Also, results show that when the patch size is increasing, the mean square error is decreasing. | ||
| Keywords | ||
| Image Generation; luminance and chromatic; evolutionary algorithm | ||
|
Statistics Article View: 90 PDF Download: 56 |
||