Automatic Segmentation Method of Touching Corn Kernels in Digital Image Based on Improved Watershed Algorithm
in order to separate touching corn kernels in digital image, this paper made the improvement to the watershed algorithm, this improved method can resolve the problems of algorithm-over-segmentation and leakage, and realized automatic segmentation of touching com kernels. Firstly, in order to get the pretreatment image, Wiener filter and mathe-matical morphology were adopted to reduce noises and clarify background of the image; secondly, by combining with tow edge detection operators, the boundary of touching corn ker-nels was determined in the image, which can serve as water-shed of the algorithm; thirdly, erode transform was used to construct basin of the algorithm; at last, the algorithm of purifying image background was proposed, solving the problem of leakage. The results of experiment showed that the cor-rection rate of segmentation is 94％ by this automatic seg-mentation method.
corn kernels Touching automatic segmentation method watershed algorithm
Quan Longzhe Jiang Encben
Engineering College of Engineering Northeast Agricultural University Harbin.china Engineering College of Engineering Northeast Agricultural University Harbin,china
国际会议
山东淄博
英文
34-37
2011-05-27（万方平台首次上网日期，不代表论文的发表时间）