Clustering Detection Algorithm of Plant Leaf Relative Lesion Area Based on Improved GA. Issue 2 (2nd April 2016)

• Record Type: Journal Article
• Authors: Ren, Shun; Yu, Haiye; Wang, Linlin; Zhang, Lei
• Is Part Of: Intelligent automation & soft computing. Volume 22:Issue 2(2016)
• Page Start: 249
• Page End: 254
• Publication Date: 2016-04-02
• Subjects: Computer graphics -- clustering algorithm -- genetic algorithm -- relative lesion area (RLA); Artificial intelligence -- Periodicals; Intelligent control systems -- Periodicals; 003.5
• DOI: 10.1080/10798587.2015.1095479
• Languages: English
• ISSNs: 1079-8587

Abstract

Abstract: In order to overcome the defects of traditional methods on measuring plant leaf diseases and achieve accurate detection of blade relative lesion area, clustering algorithm and the improved clustering algorithm are used to calculate the leaf relative lesion area with the knowledge of computer graphics technology. First, preprocess the image selectively by the image correction, color space conversion technology and so on, use the clustering algorithm to divide the target area. Finally calculate relative lesion area according to the partition determined by objective function. This paper proposed an improved genetic algorithm to improve the limitation problem of selecting the clustering algorithm initial value and enhance the searching capability and the robustness of the original algorithm by improving genetic operator of genetic algorithm. Considering the accuracy of image processing as the quota, the results show that the algorithm in this paper makes the lesion area calculated by the clustering center more accurate and lays more effective theoretical foundation for diagnosis of crop diseases and insects level.