Recognition of pests based on compressive sensing theory

In order to improve the performance of the existing recognition methods of pests, the limitations of these methods are analyzed in this paper. Based on the analysis, the novel recognition method of pests by using compressive sensing theory is presented in this paper. In the proposed method, a large number of representative training samples of pests are used to construct the training samples matrix, then the sparse decomposition representation of the testing samples of pests is obtained by solving the L1-norm optimization problem, which contains distinct class information and could be used for the different species of pests recognition directly. The 12 species of stored-grain pests and the 110 species of common pests are separately recognized by the proposed method. The experimental results prove that the application of compressive sensing theory in the recognition of pests is practical and feasible.