|
IMPROVED COLOR CONSTANCY ALGORITHMS USING FUZZY TECHNIQUE |
|---|---|
| รหัสดีโอไอ | |
| Creator | Parastoo Fathi, Mohsen Ebrahimi Moghadam |
| Title | IMPROVED COLOR CONSTANCY ALGORITHMS USING FUZZY TECHNIQUE |
| Contributor | - |
| Publisher | TuEngr Group |
| Publication Year | 2562 |
| Journal Title | International Transaction Journal of Engineering, Management, & Applied Sciences & Technologies |
| Journal Vol. | 10 |
| Journal No. | 5 |
| Page no. | 709-719 |
| Keyword | Fuzzy clustering-based algorithm, Color space, Color constancy algorithm selection, Diagonal mapping, Fuzzification. |
| URL Website | http://tuengr.com/Vol10_5.html |
| Website title | ITJEMAST V10(5) 2019 @ TuEngr.com |
| ISSN | 2228-9860 |
| Abstract | Color constancy is the ability to recognize the color of objects independent of the light source luminance. Color processing and especially color constancy performs an important role in computer vision and image processing applications such as image retrieval, image classification, color object recognition, and object tracking. Color constancy is usually understood as the task of finding descriptors which are invariant to illumination changes in surfaces of a scene while correcting colors in an image is considered as a different phase. This paper proposes a new combinational method based on fuzzy method and clustering to estimate the chromaticity of the light source as the major step of color constancy. In this algorithm, after fuzzification different features of the image by using a clustering algorithm estimates the light source illuminant. To verify the proposed method, four well-known algorithms were selected based on the best algorithm by the proposed approach. In selecting these methods, it was tried to choose the ones which had better performance in comparison to other methods. It is shown in this article that the proposed approach performs better than other proposed methods for color constancy most of the time. |
