摘要
稀疏表示分类方法在训练样本空间较大的情况下具有良好的分类效果,但是计算的时间成本较高。针对此问题,考虑构造对重构样本的l2-范数进行约束,使得重构样本中各类别分量之间的竞争加强,以起到组稀疏的效果,最后提高分类正确率。由于该方法可以直接得到闭式解,使得求解的计算成本大大减小,并且得到的系数稀疏程度与传统方法类似。在公开的人脸和物体图像数据集上和同类型方法的对比实验结果表明,该方法在复杂的条件下具有优秀的图像识别效果。
Sparse representation classification(SRC)has a good performance of classification when the feature space spanned by training samples is sufficient,but the computational cost is expensive.To solve this problem of SRC,this paper considered the constraint of reconstruction samples.It introduced a group sparsity effect to enhance the competitions between different subjects in reconstruction procedure,and improved the accuracy of classification finally.Since the proposed method had a closed-form solution,the computational cost was very low.Moreover,the sparsity of the coefficient produced by the new approach was the same as that obtained by SRC.The experiment results on public face and object image datasets demonstrate that the proposed method has a good performance comparing with other same kind approaches.
作者
米建勋
林志凯
Mi Jianxun;Lin Zhikai(College of Computer Science&Technology,Chongqing University of Posts&Telecommunications,Chongqing 400065,China;Chongqing Key Laboratory of Image Cognition,Chongqing University of Posts&Telecommunications,Chongqing 400065,China)
出处
《计算机应用研究》
CSCD
北大核心
2020年第4期1252-1255,共4页
Application Research of Computers
基金
国家自然科学基金资助项目(61472055)
重庆市自然科学基金资助项目(cstc2018jcyjAX0532)。
关键词
稀疏表示
人脸识别
联合表示
重构样本
sparse representation
face recognition
collaborative representation
reconstruction sample