Fruit Quality Evaluation Using K-Means Clustering Approach
Manual identification of defected fruit is very time consuming. In previous years, several types of image
analysis techniques are applied to analyse the fruit quality. This work presents a novel defect segmentation of fruits based on
texture feature with K-means clustering algorithm. This approach thus provides a feasible robust solution for defect
segmentation of fruits.
The proposed method can process, analyze, classify and identify the fruits images, which are selected and sent in to the
system based on color and texture feature of the fruit. The recognition system that has been developed is able to recognize all
the test fruit images which are being selected by a user from the fruit selection menu which is based on GUI block in
MATLAB on the system.
Apple is taken as a case study and evaluated the proposed approach using defected apples. The experimental results clarify
the effectiveness of proposed approach to improve the defect segmentation quality in aspects of precision and computational
Keywords— Segmentation, K-means Clustering, GLCM.