Identification of Pecan Weevils through Image Processing | Science Publications

American Journal of Agricultural and Biological Sciences

P. Weckler¹  S. M. Al-Saqer¹  A. Wayadande¹  J. Solie¹  M. Stone¹ 

关键词: Insects identification;    pecan weevils;    image processing;    monitoring insects;    recognition system;   

DOI  :  10.3844/ajabssp.2011.69.79

学科分类：农业科学（综合）

来源: Science Publications

【 摘 要 】

Problem Statement: Pecan weevil is one of the most destructive pests of Oklahoma. Thescope of this study is to develop a recognition system that can serve in a wireless imaging network formonitoring pecan weevils. Approach: The recognition methods used in this study are based ontemplate matching. Five recognition methods were implemented: Normalized cross-correlation,Fourier descriptors, Zernike moments, String matching and Regional properties. The training setconsisted of 205 pecan weevils and the testing set included 30 randomly selected pecan weevils and 74other insects which typically exist in pecan habitat. Results: It was found that Region-based methodswere better in representing and recognizing biological objects such as insects. Different recognitionrates were obtained at different order of Zernike moments. The optimum result among the tested ordersof Zernike moments was found to be at the order 3. The results also showed that using differentnumber of Fourier descriptors may not significantly increase the recognition rate of this method.Conclusion: The most robust and reliable recognition rate was achieved when the Zernike momentsand Region properties recognition methods were used in a combination. A positive match from eitherof these two independent tests would yield reliable results. Therefore, 100% recognition could beachieved by adopting the proposed algorithm. The processing time for such recognition is 0.44 sec.

【 授权许可】

Unknown