基于SFA和GLCM的影像特征提取方法_鄢圣藜.pdfVIP

第37 卷 第20 期 计 算 机 工 程 2011 年10 月 Vol.37 No.20 Computer Engineering October 2011 ·人工智能及识别技术· 文章编号：1000—3428(2011)20—0175—03 文献标识码：A 中图分类号：TP391.41 基于SFA 和GLCM 的影像特征提取方法 鄢圣藜，霍 宏，方 涛 (上海交通大学图像处理与模式识别研究所，上海 200240) 摘 要：针对遥感影像中同类样本差异性较大的缺点，提出一种基于SFA 和灰度共生矩阵(GLCM)的遥感影像特征提取方法。对原始图像 进行SFA 变换，利用SFA 的生物视觉特性消除图像中的同类差异性，对变换得到的图像进行GLCM 计算，获得基于SFA 和GLCM 的新 型特征。实验结果证明，SFA 预处理能降低遥感影像的同类差异性，提高特征的可区分性，其效果优于传统的GLCM 特征提取方法。 关键词：图像解译；SFA 变换；灰度共生矩阵；特征提取；支持向量机 Image Feature Extraction Method Based on SFA and GLCM YAN Sheng-li, HUO Hong, FANG Tao (Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200240, China) 【Abstract 】As there are still many difference between the remote sensing image from the same class, this paper proposes a new method of extracting features based on Slow Feature Analysis(SFA) and Gray Level Co-occurrence Matrix(GLCM). The image is first processed with SFA algorithm. It can eliminate the difference of the object from the same class as the biological characteristics of SFA. Then the GLCM feature is extracted from the SFA data. Results indicate that with the preprocessing of SFA, it can effectively reduce the diversity of samples from the same class and increase the distinguishability of the feature, the method is more effective and competitive than the conventional GLCM feature extraction method. 【Key words 】image interpretation; Slow Feature Analysis(SFA) transformation; Gray Level Co-occurrence Matrix(GLCM); feature extraction; Support Vector Machine(SVM) DOI: 10.3969/j.issn.1000-3428.2011.