基于能量分解的影像纹理多尺度分析

Energy Decomposition Based Multiscale Approach to Image Texture

按照二维Ｇａｂｏｒ函数的特点和视觉机制，提出了用来捕捉纹理基元的纹理检测器函数．基于纹理检测器和扩展的小波变换，提出了基于能量分解的影像纹理多尺度分析方法，并按照神经动力学的侧抑制和端点抑制等理论，实现了对多尺度纹理特征的融合．这一多尺度分析方法直接将影像纹理能量在时间一尺度空间分解，包含了相位信息，避免了基于线性变换多尺度分解引起的能量与相位分离，为纹理分析提供了一个层次性的框架，有效提高了纹理的识别能力．

In this paper, a textural detector based on 2D Gabor function and visual textural perception isestablished first. then based on the textural detector and recent developed theory of time-scale space decomposition, a general class extending wavelet transform, an energy distribution based mtlltiscale texture analysis methodis proposed. The multiscale texture analysis techniqUe gives textural energy representation between spatial spaceand scale space, and provides a hierarchical analysis framework for image texture. They can detect different scaletexture features, correspond to the visual texture perception , and have the ability to recognize texture image effectively.