Entity

Time filter

Source Type


Tang Z.,Central South University | Su Y.,Central South University | Er M.J.,Nanyang Technological University | Qi F.,Central South University | And 2 more authors.
Neurocomputing | Year: 2015

For tea processing production lines, different fresh tea leaves require different processing parameters for the control systems of tea machines. Hence, an effective algorithm for classification of tea leaves will be important for automatic tea processing. However, most of tea classification researches were focused on gross tea, instead of fresh tea leaves. In this paper, a texture extraction method combing a non-overlap window local binary pattern (LBP) and Gray Level Co-Occurrence Matrix (GLCM) has been proposed for green tea leaves classification. By taking advantages of both LBP and GLCM for texture extraction, this method is able to effectively extract texture of tea leaves for classification at low computational cost to meet automatic tea production line requirements. The experiments have been conducted to prove the effectiveness of the proposed method. © 2015 Elsevier B.V. Source


Tang Z.,Central South University | Qi F.,Central South University | Zhou Y.,Singapore Institute of Manufacturing Technology | Pan F.,Central South University | Zhou J.,Changsha Xiangfeng Tea Machinery Manufacturing Co.
Lecture Notes in Electrical Engineering | Year: 2015

An SVM with texture analysis-based feature extraction classification method is presented for identification of fresh tea leaves in this paper. This method is proved to be very efficient and effective in the identification of fresh tea leaves through real experiments. First, the texture characteristic parameters of tea leave images are obtained by texture feature extraction. After that, different categories of fresh tea leaves are identified through SVM training. These texture parameters for texture classification include energy, correlation, and contrast obtained from graylevel co-occurrence matrix (GLCM). Experimental results show that the use of SVM for classification of tea leaves can achieve very good results, and the successful classification rate can be as high as 83%. © Springer-Verlag Berlin Heidelberg 2015. Source


Tang Z.,Central South University | Jiang C.,Central South University | Zhang L.,Changsha Xiangfeng Tea Machinery Manufacturing Co. | Zhou J.,Changsha Xiangfeng Tea Machinery Manufacturing Co.
Gaojishu Tongxin/Chinese High Technology Letters | Year: 2014

A classification method based on texture analysis and support vector machine (SVM) was applied to automatic identification of fresh tea leaves to realize the fast, accurate online classification of fresh tea leaves. The texture characteristic parameters of tea leaves were obtained through the digital image processing technology, and different models for identification of fresh tea leaves were derived through SVM to realize the fast online classification of fresh tea leaves. The texture parameters including energy, correlation, contrast and homogeneity were obtained through the gray level co-occurrence matrix (GLCM), and they were used for SVM training and classification. The experimental results showed that the SVM application for tea classification achieved very good results, and the accuracy rate for classification can reach as high as 90%. Source

Discover hidden collaborations