The Recognition of Cucumber Disease Based on Image Processing and Support Vector Machine

Abstract

A new method of recognizing cucumber leaf disease based on computer image processing and Support Vector Machine (SVM) is studied to improve recognition accuracy and efficiency. At first, vector median filter was applied to remove noise of the acquired color images of cucumber disease leaf. Then a method of statistic pattern recognition and mathematics morphology was introduced to segment images of cucumber disease leaf. At last texture, shape and color features of color image of cucumber disease spot on leaf were extracted, and classification method of SVM for recognition of cucumber disease was used. Experimental results indicate that the classification performance by SVM is better than that of neural networks. Recognition correct rate of cucumber disease based on SVM of shape and texture feature is better than that of only using the shape feature. Cucumber disease is recognized more correct and faster based on color feature.