Abstract：Two-dimensional images may be analyzed at mutliple resolution with the wavelet decomposition. This paper discusses the wavelet packet analysis and its applications to catalyst surface SEM image recognition. In the study on classification and recognition of catalyst surfaces, features were computed for each wavelet packet and they fully describe the information distribution of surface images at multiple scales space. Experiment results show that the wavelet packet tree is a good description about pattern features, and provides a new approach to image texture classification.
1 Grossmann A,Morlet J.Decomposition of Hardy Functions into Square Integrable Wavelets of Constant Shape.SIAMJ Math Anal,1984,15(4):723～736 2 Grossmann A,Morlet J,Paul T.Transforms Associated to Square Integrable Group Representations I:General Results,J Math Physics,1985,26:2473～2479 3 王积分,吴勇,张洪峰,段世铎,韩顺路.空间灰度共生矩阵法催化剂表面图象的纹理分析.模式识别与人工智能,1992,5(2):163～168 4 Mallat S G.A Theory for Multiresolution Signal Decomposition:The Wavelet Representation.IEEE Trans Pattern Anal Machine Intell,1989,11(7):674～693 5 Daubechies I.Orthonormal Bases of Compactly Supported Wavelets.Comm Pure and Applied Math,1988, LI:909～996 6 边肇祺等.模式识别.北京,清华大学出版社,1988 7 Andrew L,Jian R.Texture Classification by Wavelet Packet Signatures.IEEE Trans Pattern Anal Machie Intell,1993,15(11):1186～1191