Generalized Gaussian Density: An Efficient Tool for Medical Images Texture Analysis
摘要
Generalized Gaussian Density (GGD) is mainly a wavelet decomposition based technique. As wavelet transform is recognized as a technique for multi-resolution analysis, where image textures are processed by applying both low-pass and high-pass filters to the rows and columns of the image, wavelet coefficients distribution can provide highly discriminative features for images segmentation. In this chapter, we introduce the GGD technique as a tool for medical images texture analysis. First of all, we introduce the GGD analysis technique with theoretical details, and then we describe related works before giving details about the GGD based approach proposed to detect lung nodules, bone sarcoma and breast abnormalities. The results of using GGD analysis on these several tumors detection are illustrated and compared to other existing techniques.