DocumentCode :
3235052
Title :
Recognition of pests based on compressive sensing theory
Author :
Han, Antai ; Peng, Hui ; Li, Jianfeng ; Han, Jianqiang ; Guo, Xiaohua
Author_Institution :
Inst. of Electr. Eng. & Electron. Technol., China Jiliang Univ., Hangzhou, China
fYear :
2011
fDate :
27-29 May 2011
Firstpage :
263
Lastpage :
266
Abstract :
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.
Keywords :
agriculture; feature extraction; matrix decomposition; optimisation; sparse matrices; Ll-norm optimization problem; compressive sensing theory; pests recognition; representative training samples; sparse decomposition representation; training samples matrix; Approximation methods; Matching pursuit algorithms; Optimization; Sparse matrices; Testing; Training; Vectors; compressive sensing; feature parameters; pests; recognition; recognition precision; sparse decomposition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communication Software and Networks (ICCSN), 2011 IEEE 3rd International Conference on
Conference_Location :
Xi´an
Print_ISBN :
978-1-61284-485-5
Type :
conf
DOI :
10.1109/ICCSN.2011.6014437
Filename :
6014437
Link To Document :
بازگشت