Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Probability Maximum Margin Criterion for Crop Disease Recognition

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Applied Engineering in Agriculture. 32(6): 713-721. (doi: 10.13031/aea.32.11148) @2016
Authors:   Chuanlei Zhang, Shanwen Zhang, Xianfeng Wang, Xuqi Wang, Jucheng Yang
Keywords:   Classifying probability, Crop disease recognition, Maximum margin criterion (MMC), Prior probability, Probability MMC, Singular value decomposition (SVD).

Abstract. Crop disease seriously affects the yield and quality of crops and cause farmers to experience economic losses. Automatic detection of crop disease is an essential research topic to detect the disease symptoms as soon as they appear on the leaves. For crop disease management, it is important to automatically detect the crop diseases at a stage so as to treat them properly. In subspace dimension reduction-based data classification methods, the main topic is to design the between-class and within-class scatter matrices to obtain the mapping matrix from the training samples. But, there is much difference between the training samples. To eliminate the difference in designing the scatter matrices, in this article, based on the prior probability, a probability maximum margin criterion (MMC) is proposed for leaf spot image processing. Compared to the traditional MMC algorithm, in the proposed method, the two scatter matrices are expressed by the weighted mean vector of all training samples, which can overcome the influence of the outliers and the noise points, meanwhile improve the crop disease recognition rate. In this study, more than 100 classifying features are extracted from the disease leaf images of two kinds of cucumber diseases; probability MMC is performed for reduced dimensions in feature data processing, and then K-nearest-neighbor classifier is used to identify the cucumber diseases. The experimental results on a cucumber disease leaf image database show that the proposed method is effective for crop disease recognition.

(Download PDF)    (Export to EndNotes)