计算机技术与发展2017，Vol.27Issue(12)：7-10,4.DOI:10.3969/j.issn.1673-629X.2017.12.002
基于特征融合与稀疏表示的人耳识别
Ear Recognition Based on Feature Fusion and Sparse Representation
摘要
Abstract
Ear recognition is an emerging biometric recognition technology,with high theoretical research value and market prospect,and develops gradually with the development of image processing,pattern recognition and other fields. Feature extraction is the key to this technology which plays a decisive role in the accuracy of the final classification result. Therefore,in order to improve the accuracy of clas-sification result in the technology of ear recognition,a method of ear recognition based on feature fusion and sparse representation is pres-ented. In this method,the Sobel operator from four direction is adopted to detect the edges and extract their feature. At the same time the GLCM ( Gray Level Co-occurrence Matrix) is used to extract texture feature of ear images. Finally sparse representation model is utilized to conduct classification recognition of ear in combination of edge and texture features. The experiment shows that the proposed method can improve ear recognition accuracy greatly,thus confirming its effectiveness in the survey of ear recognition.关键词
人耳识别/模式识别/特征融合/稀疏表示/图像处理Key words
ear recognition/mode recognition/feature fusion/sparse representation/image processing分类
信息技术与安全科学引用本文复制引用
张雅倩,曾卫明,石玉虎..基于特征融合与稀疏表示的人耳识别[J].计算机技术与发展,2017,27(12):7-10,4.基金项目
上海市科委计划重点项目(14590501700) （14590501700）
