Title :
A recognition method of apples based on texture features and EM algorithm
Author :
Gao Rui ; Liu Gang ; Si Yongsheng
Author_Institution :
Key Lab. of MOE on Modern Precision Agric. Syst. Integration Res., China Agric. Univ., Beijing, China
Abstract :
This paper presents an apple recognition method based on texture features and Maximum Expectation (EM) algorithm for Gaussian Mixture Model (GMM). The images were converted to HSV space from RGB space and the H channel images were selected as interested images to be processed. The images of H channel were divided into blocks of 8*8 pixels and the texture features of the blocks were calculated. Angular second moment was selected for clustering using EM algorithm. Their prior probability, mean and variance were computed. And then the images were segmented according to these parameters obtained. Results showed that the proposed segmentation method could recognize the apples effectively, and 85.33% of apples were successfully recognized.
Keywords :
Gaussian processes; agricultural products; image recognition; image resolution; image segmentation; image texture; pattern clustering; probability; production engineering computing; statistical analysis; EM algorithm; Gaussian mixture model; H channel images; HSV space; RGB space; angular second moment; apple recognition; clustering; image pixels; image segmentation; maximum expectation algorithm; probability; texture features; Clustering algorithms; Feature extraction; Image color analysis; Image recognition; Image segmentation; Object segmentation; Pixel;
Conference_Titel :
World Automation Congress (WAC), 2010
Conference_Location :
Kobe
Print_ISBN :
978-1-4244-9673-0
Electronic_ISBN :
2154-4824
