基于变换域与高斯混合模型聚类的煤岩识别方法

Coal and Rock Recognition Method Based on Transform Domain and Clustering of Gaussian Mixture Model

借助图像处理技术及特征提取方法,提出了基于变换域与高斯混合模型聚类的煤岩识别方法。采用离散余弦变换和离散小波变换分别提取煤岩图像的内容和纹理信息,组成的特征向量经过高斯混合模型聚类进行分类识别。通过仿真分析,有效获得煤岩图像的主要特征,提高了识别准确率。

With the aid of image processing technology and feature extraction method, a coal and rock recognition method based on the transform domain and Gaussian mixture model clustering is proposed. The discrete cosine transform and discrete wavelet transform are used to extract the content and texture information of coal and rock images respectively. The feature vectors are classified and recognized by Gaussian mixture model clustering.Through the simulation analysis, the main features of coal and rock images can be effectively obtained, and the recognition accuracy is improved.