Two classification and identification methods based on pattern discrimination models and the majority-vote technique were investigated for implementing a World Wide Web-based system for the identification of rice dise...Two classification and identification methods based on pattern discrimination models and the majority-vote technique were investigated for implementing a World Wide Web-based system for the identification of rice diseases. The experiment was carried out using color and shape patterns in 425 images of three rice diseases, which were classified into four classes： two classes of leaf blast, and one class each of sheath blight and brown spot. A method consisting of two discrimination steps involving application of multiple discrimination models of a support vector machine gave the best result because of its capacity to evaluate the similarity of disease types. This accuracy of the method was 88% for leaf blast （A-type）, 94% for sheath blight, and 80% for leaf blast （B-type） and brown spot; on average, the accuracy of this method was 5% greater than that of the other method when three classes were used in the model. Although the accuracy of both methods was inadequate, the results of this study show that it is possible to estimate the least number of possible or similar diseases from a large number of diseases. Therefore, we conclude that there is merit in grouping classes into subgroups rather than attempting to discriminate between all classes simultaneously and that these methods are effective in identifying diseases for web-based diagnosis.展开更多
文摘Two classification and identification methods based on pattern discrimination models and the majority-vote technique were investigated for implementing a World Wide Web-based system for the identification of rice diseases. The experiment was carried out using color and shape patterns in 425 images of three rice diseases, which were classified into four classes： two classes of leaf blast, and one class each of sheath blight and brown spot. A method consisting of two discrimination steps involving application of multiple discrimination models of a support vector machine gave the best result because of its capacity to evaluate the similarity of disease types. This accuracy of the method was 88% for leaf blast （A-type）, 94% for sheath blight, and 80% for leaf blast （B-type） and brown spot; on average, the accuracy of this method was 5% greater than that of the other method when three classes were used in the model. Although the accuracy of both methods was inadequate, the results of this study show that it is possible to estimate the least number of possible or similar diseases from a large number of diseases. Therefore, we conclude that there is merit in grouping classes into subgroups rather than attempting to discriminate between all classes simultaneously and that these methods are effective in identifying diseases for web-based diagnosis.
