Computer Engineering and Applications 计算机工程与应用 2011 ,47 (20 ) 151
⦾图形、图像、模式识别⦾
利用灰度纹理分析方法识别蛋白质空间结构
1 2 3
施建宇 ,雷朝霞 ,方智裕
1 2 3
SHI Jianyu ,LEI Zhaoxia ,FANG Zhiyu
1.西北工业大学 生命科学院,西安 710072
2.鄱阳县第一中学 计算机教研组,江西 上饶 333100
3.鄱阳县广播电视台 多媒体管理中心,江西 上饶 333100
1.School of Life Science ,Northwestern Polytechnical University ,Xi ’an 710072 ,China
2.Group of Computer Science ,No. 1 High School of Poyang ,Shangrao ,Jiangxi 333100 ,China
3.Administration of Multimedia ,Broadcasting Station of Poyang ,Shangrao ,Jiangxi 333100 ,China
SHI Jianyu ,LEI Zhaoxia ,FANG Zhiyu.Spatial structure recognition of protein based on gray texture analysis.Computer
Engineering and Applications ,2011 ,47 (20 ):151-154.
Abstract :The intrinsic complexity of Protein Spatial Structure (PSS )brings a heavy difficulty to its structural classification.
In this paper ,PSS is mapped into 2-D distance matrix and further regarded as texture image of which textural directions are
detected by Radon transform.Consequently ,a novel method of feature extraction of PSS with low dimension is proposed
based on gray level co-occurrence matrix and Radon transform project matrix.The experiments and the comparison results
demonstrate that the presented method can not only product low-dimensional feature and also achieve effective classification
of PSS.
Key words :distance matrix ;gray level co-occurrence matrix ;Radon transform ;support vector machines ;feature extraction
摘 要:蛋白质三维空间结构固有的复杂性给其结构分类带来了较大的困难。将蛋白质空间结构映射成为二维距离矩阵,并进
一步视作灰度纹理图像,使用拉冬变换分析了该图像的纹理方向特性,基于灰度共生矩阵和Radon 投影矩阵提出了一种低维的
蛋白质结构特征提取方法。实验结果与对比表明,该方法不仅具有低维的特征,而且有效地实现了多类蛋白质结构分类识别。
关键词:距离矩阵;灰度共生矩阵;拉冬变换;支持向量机;特征提取
DOI :10.3778/j.issn. 1002-8331.2011.20.043 文章编号:1002-8331(2011 )20-0151-04 文献标识码:A 中图分类号:TP391
1 前言 定的,