A Segmentation Method for Comprehensive Color Feature with Color-to-Grayscale Conversion Using SVD and Region-Growing Method

Autor: K. Joseph Abraham Sundar, N. Jothiaruna
Rok vydání: 2019
Předmět:
Zdroj: First International Conference on Sustainable Technologies for Computational Intelligence ISBN: 9789811500282
DOI: 10.1007/978-981-15-0029-9_24
Popis: Segmenting disease spots in leafs is achieved by Comprehensive Color feature (CCF), grayscale conversion and region growing method is discussed. Segmenting disease spots under real-field conditions with uneven illumination and clutter background has been a major challenge. Uneven illumination issues solves by applying Excess Red index, H component of HSV and grayscale conversion by using SVD, clutter background problem solves by applying region-growing method. Performance of these methods is calculated using precision, and its accurate segmentation is 89% under real-field condition.
Databáze: OpenAIRE