Image-Based Classification and Segmentation of Healthy and Defective Mangoes

摘要

The use of image processing and classification for agricultural applications has been widely studied and has led towork such as the automatic grading of fruit and vegetables, yield approximation and defect detection. Imagesegmentation is one of the first steps to identify the region of interest within an image. This paper presents an approachto automatic segmentation and classification of healthy and defective Carabao mangoes. K-means, range filtering andcolor-channel segmentation were utilized so that the varying texture and color of mangoes due to the surface defects canbe considered. Results show that the proposed technique performs better than the classical K-means segmentation. Theperformance of segmentation step has a considerable influence on the precision of the classification model. Segmentedand not segmented images were trained using KNN, SVM, MLP and CNN. The experiments showed that the modelsperformed better when trained with segmented images.