Multiple Classifier Combination For Recognition Of Wheat Leaf Diseases

Wheat industry is an important constituent of Northern China’s overall agricultural economy. Proper disease detection using computer vision and pattern recognition has being investigated to minimize the loss, and finally achieve intelligent healthy farming. This paper proposes a new strategy of Multi-Classifier System based on SVM (support vector machine) for pattern recognition of wheat leaf diseases for higher recognition accuracy. Diseased leaf samples with Powdery Mildew, Rust Puccinia Triticina, Leaf Blight, Puccinia Striiformis were collected in the field and images were captured before a uniform black background. Three feature sets including color feature set, shape feature set and texture feature set were created for classification analysis. The proposed combination strategy was based on stacked generalization and included twolevel structure: base-level was a module of three kinds of SVM-based classifiers trained by three feature sets and meta-level was one module of SVM-based decision classifier trained by meta-feature set which are generated through a new data fusion mechanism. Compared with other single classifiers and other strategy of classifier ensembles for wheat leaf diseases, this approach is more flexible and has higher success rate of recognition.