Abstract: Identification of stem and blemish is a thorny problem in apple grading.If the stem is incorrectly classified as blemish，a false grade will be assigned to the fruit.A new method based on Support Vector Machine（SVM） is proposed to identify blemish and stem on Fuji apples.An Ostu algorithm is adopted，indicating region boundary of stem and blemish.The texture features of stem and blemish are fed as input of SVM to distinguish stem and blemish.The test results on Fuji apples shows that an average of 90.7% classification accuracy is achieved by using the proposed method.

Key words: apple identification, texture analysis, support vector machines, features selection

摘要： 苹果梗蒂和缺陷的识别是苹果检测中的难点，两者的误分类会造成苹果等级的误判。提出了一种基于SVM的苹果梗蒂和缺陷识别方法，用Ostu算法进行区域分割，实现初始目标分割，再把目标区域的纹理特征作为支持向量机的输入向量，对其进行训练识别。用富士苹果进行实验，得到的平均识别正确率为90.7%。

关键词: 苹果识别l, 纹理分析, 支持向量机, 特征选择