基于小波灰度共生矩阵的鲜骏枣裂纹分选

Classification of fresh jun-jujube crack based on wavelet transform and gray level co-occurrence matrix

针对阿克苏鲜骏枣中含部分裂果枣问题,使用基于小波灰度共生矩阵的方法进行分选。首先采集骏枣RGB图像,去除RGB图像中绿色着色区后,对其进行小波变换,并提取变换后子图像的灰度共生矩阵,构造熵、能量、相关性、平滑度、对比度等5个特征向量,对特征向量进行主成分分析,降维输入支持向量机,完成对鲜枣裂果与正常果的分类识别,分类准确率能达到89.92%。实验结果表明,小波变换与灰度共生矩阵结合能够更加有效地表达枣的裂纹信息,可用于鲜骏枣裂纹分选。

A method based on wavelet transform and gray level co-occurrence matrix(GLCM)is used to classify the normal and crack fresh jun-jujube native to Aksu.The RGB image of jun jujube is acquired,whose green colored regions are removed for wavelet transform.The GLCM of the transformed sub-image is extracted to construct the feature vectors of entropy,energy,correlation,smoothness and contrast.The dimensions of the feature vector are reduced by means of PCA,and the feature vector is input into the support vector machine,so as to realize the classification and recognition of the normal and crack fresh jun-jujube.The classification accuracy can reach up to 89.92%.The results show that the combination of wavelet transform and GLCM can describe the crack information of the jujube effectively,and is used for crack sorting of the fresh jun jujube.