Application of maximum likelihood classification Based on minimal risk in crop interpretation

Yubin Song, Xiufeng Yang, Yancang Wang, Zihui Zhao, Xuhong Ren, Longfang Duan
2015 Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015   unpublished
In crop interpretation by remote sensing, Gray distribution of crop is overlapped in some intervals. The non-target crops fall into the target crop, which would greatly increase the workload in post classification. To reduce these classification errors, and improve accuracy of clarification, maximum likelihood classification based on minimal risk is used. And the relationship between extraction rate and accuracy were analyzed. Experiments show that this method can improve the accuracy of
more » ... ing target crops, reduce the workload of the post classification, and improve efficiency.
doi:10.2991/icmmcce-15.2015.516 fatcat:lyrcjhdfhnfbtmdxeszxeijrxy