A machine learning system to identify progress level of dry rot disease in potato tuber based on digital thermal image processing.

This study proposed a quick and reliable thermography-based method for detection of healthy potato tubers from those with dry rot disease and also determination of the level of disease development. The dry rot development inside potato tubers was classified based on the Wiersema Criteria, grade 0 to 3. The tubers were heated at 60 and 90 °C, and then thermal images were taken 10, 25, 40, and 70 s after heating. The surface temperature of the tubers was measured to select the best treatment for thermography, and the treatment with the highest thermal difference in each class was selected. The results of variance analysis of tuber surface temperature showed that tuber surface temperature was significantly different due to the severity of disease development inside the tuber. Total of 25 thermal images were prepared for each class, and then Otsu's threshold method was employed to remove the background. Their histograms were extracted from the red, green, and blue surfaces, and, finally, six features were extracted from each histogram. Moreover, the co-occurrence matrix was extracted at four angles from the gray level images and five features were extracted from each co-occurrence matrix. Totally, each thermograph was described by 38 features. These features were used to implement the artificial neural networks and the support vector machine in order to classify and diagnose the severity of the disease. The results showed that the sensitivity of the models in the diagnosis of healthy tubers was 96 and 100%, respectively. The overall accuracy of the models in detecting the severity of tuber tissue destruction was 93 and 97%, respectively. The proposed methodology as an accurate, nondestructive, fast, and applicable system reduces the potato loss by rapid detection of the disease of the tubers.