关键词: 计数, 分割, 支持向量机（SVM）, 纹理特征, 网格模型

Abstract: In the silkworm ovum image，the traditional method on counting the number of the silkworm ovum needs separation of these objects.However，there are many overlapping or conglutinating silkworm ova existing in the image，and it leads to the half-baked situation for segmentation and much trouble for the following process.To solve this problem，a new algorithm based on mesh model is proposed.It makes full use of machine-learning to avoid the process of segmentation，and the counting result is given directly by SVM.It also gives an extraction of effective texture feature and improves the precision of SVM.Compared with the traditional algorithm based on segmentation，experimental results show the high performance in both robustness and precision of the proposed method.

Key words: counting, segmentation, Support Vector Machines（SVM）, texture feature, mesh model