Tea Diseases Detection Based on Fast Infrared Thermal Image Processing Technology

摘要： The overall goal of this study is to develop an effective, simple, aptly computer vision algorithm to detect tea disease area using infrared thermal image processing techniques and to estimate tea disease. This paper finds that the area of tea disease has certain regularity with its infrared image gray distribution. Using this rule, we extracted two characteristic parameters into a classifier to help achieve rapid tea disease detection, which increase the accuracy of detection a small amount. Tea plant images were taken from Jiangsu Tea Expo Park, China during daylight and the tea disease detection algorithm were tested on 116 images collected from 57 trees. The tea disease detection algorithm consisted of the following steps: classify canopy infrared thermal image, convert red, green and blue (RGB) image to hue, saturation and value (HSV), thresholding, color identification, noise filtering, binarization, closed operation and counting. A correlation coefficient of 0.97 was obtained between the tea disease detection algorithm and counting performed through human observation, 2% higher than traditional algorithms without classifiers.