A cotton recognition method was proposed based on Hough transform in order to recognize the hidden cotton. For reducing the computation complexity, first of all, the image was segmented by R-B channel in RGB color model. The minimum external rectangle was obtained by labeling its region. Then, according to the contour information from the boundary trace, the randomized Hough transform was realized. The experimental results showed that the proposed recognition method presented good performance even the cotton contour loss rated up to 50%. It met the requirements of the precision and rating for the cotton-harvesting-robot.
參考文獻
相似文獻
引證文獻
引用本文
劉坤,費樹岷,汪木蘭,邢燦華,王祝青.基于改進隨機Hough變換的棉桃識別技術[J].農(nóng)業(yè)機械學報,2010,41(8):160-165.Cotton Recognition Based on Randomized Hough Transform[J]. Transactions of the Chinese Society for Agricultural Machinery,2010,41(8):160-165.