Abstract | ||
---|---|---|
Intensive search schemes are commonly adopted in patched-based texture synthesis to identity the proper neighbors of each patch. However, they do not always provide perfect solutions. This work presents a genetic algorithm in evolutionary computation for patch-based texture synthesis. The representation of an input source texture is first adjusted. Then, the synthesizing result is generated and refined by the selection of individuals based on their fitness and executing crossover and mutation until the criteria are met. After the entire execution, a large output texture is generated with texture features similar to the source texture. Because this approach optimizes the genetic algorithm, the results are satisfactory. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1142/S0218213008004126 | INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS |
Keywords | Field | DocType |
Genetic algorithm, evolutionary computation, texturing, texture synthesis | Crossover,Pattern recognition,Computer science,Evolutionary computation,Artificial intelligence,Texture synthesis,Genetic algorithm,Machine learning | Journal |
Volume | Issue | ISSN |
17 | 4 | 0218-2130 |
Citations | PageRank | References |
2 | 0.38 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chin Chen Chang | 1 | 7849 | 725.95 |
Yen-Ting Kuo | 2 | 21 | 3.11 |
Wen-Kai Tai | 3 | 119 | 16.71 |