基于LBP的特征融合猴魁茶叶叶尖和叶柄识别研究

Research on recognition of leaf tip and petiole of Houkui tea leaf based on LBP feature fusion

针对猴魁茶叶在原有自动化加工做形过程叶尖叶柄朝向不统一,影响加工做形效率问题。利用摄像头采集茶叶图像并进行图像预处理,运用图像处理技术提取猴魁茶叶形状特征及茶叶纹理特征,进行2种特征融合,在SVM中完成对叶尖和叶柄的识别。结果表明新特征对于叶尖和叶柄识别准确率达到98.5%。研究为进一步统一茶叶叶尖和叶柄方向提供参考。

For the problem of non-uniform orientation of leaf tips and petioles of Houkui tea in the original automatic processing and shaping process,which affects the processing and shaping efficiency,the camera was used to collect tea images and preprocess them,image processing technology was used to extract the shape features of Houkui tea leaves and tea texture features,and the two features were fused.the leaf tips and petioles were recognized in SVM.The results show that the new feature has an accuracy of 98.5%for leaf tip and petiole recognition.This study provides a reference for further unifying the orientation of leaf tip and petiole of tea leaves.