AN OPTIMIZED METHOD FOR SEGMENTATION AND CLASSIFICATION OF APPLE DISEASES BASED ON CONVOLUTIONAL NEURAL NETWORK

Computer Engineering

Agriculture is a major part of the world economy as it provides food safety. However, in recent years, it has been noted that plants are extensively infected by different diseases. This causes enormous economic losses in the agriculture industry around the world. The manual inspection of fruit diseases is a difficult process which can be minimized by using automated methods for detection of plant diseases at the earlier stage. In this article, a new method is implemented for apple diseases identification and recognition. Three pipeline procedures are followed preprocessing, spot segmentation and classification. In the first step, the apple leaf spots are enhanced by a hybrid method which is the conjunction of 3D box filtering, de-correlation, RGB color model. After that, the lesion spots are segmented by converting the red channel to black and white channel. Finally, the segmented red channel image is classified by CNN Classifier. The experimental results are performed on the Plant Village dataset. The proposed methodology is tested for four types of apple disease classes including healthy leaves, Black rot, Rust, and Scab. The classification results show the improvement of our method on selected apple diseases. Moreover, the good preprocessing step always produced prominent features which later achieved significant classification accuracy.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.