Research on the Image Feature Extraction and Recognition Algorithm for Vegetable Pests and Diseases

This paper aims at the problems existing in the process of the feature extraction and recognition for the vegetable pest and disease images, then the cucumber leaf images have been taken as the research object, and the histogram feature extraction algorithm has been adopted to extract the color and texture features of the samples to generate the corresponding feature vectors. Then the weighted distance-based K nearest neighbor algorithm has been adopted to classify and identify the sample images. Finally, the diagnostic results of the diseases and pests have been obtained. The recognition rate of all kinds of diseases is above 87% and even up to 93%.