Corn leaf disease identification based on multiple classifiers fusion

Abstract: Corn is one of the important grain crops and industrial raw materials in China. The corn diseases seriously affect its yield and quality. Early detection and prevention of corn diseases is critical to control the diseases. Therefore, it's necessary to study on how to recognize the corn diseases quickly and accurately. In order to overcome the limitation of single classifier recognition and the complexity of the corn leaf disease, this paper puts forward a method based on adaptive weighted multiple classifiers fusion for corn leaf disease identification. Firstly, the disease images sampled in natural environments are preprocessed by using a series of image pre-processing methods, such as image transforming, smoothing and segmentation. Secondly, the classifiers based on support vector machine (SVM) are built by 3 kinds of features extracted from the preprocessed images, including color moment, color co-occurrence matrix (CCM) and color completely local binary patterns (CCLBP). The 3 features can well describe the color and texture information of the corn leaf disease, and they are relatively independent, which can reduce the interference caused by information redundancy in the process of fusion. Thirdly, the Euclidean distance between the test sample and every training sample for each type of feature vector is computed to find out the k nearest neighbors of the test sample from the training set by the K-Nearest Neighbour (KNN) method. The similarity between every neighbor and the test sample is calculated by means of cluster analysis method in succession. Then, an appropriate threshold is set to exclude the invalid neighbor when the similarity is less than the threshold, after that, the effective neighborhood for each single classifier with the rest of the neighbor is built. Corresponding to the effective neighbor, the confusion matrix is constructed to calculate the accuracy. The weight of every single classifier is set dynamically according to the accuracy. Finally, the proposed method gets the ultimate classification result by linear weighted method. To verify the effectiveness of the method, the database including 7 different corn leaf diseases is constructed in this paper. The database contains 516 pictures, which are collected in fields under natural light illumination conditions. Experiments in the database show that 3 kinds of classifiers have excellent recognition effect respectively and the recognition rates are more than 85%, which means the 3 features are suitable for corn leaf diseases recognition. What's more, the recognition rate of the proposed method can achieve 94.71%, which takes about 1.382 s to identify an image. Compared with other algorithms, the recognition rate of our method is the highest. Besides, the recognition rate of the combined classifier is higher than the single classifier. The fusion process will be a little more complicated and the recognition time will be longer when more features are involved in the process, However, it is acceptable in practice. Above all, the proposed method has better performance and it can be used in intelligent corn leaf diseases recognition system, which improves the accuracy rate of the system. It has provided a technical support for the automatic recognition of crop diseases and insects with disease image obtained in fields.