.png){kind=icon}
返回
Improved image representation and sparse representation for face recognition
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-022-13203-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Sparse representation is of great significance to the research of face recognition. Due to factors such as illumination, angle, and facial features, different face images of the same subject have great differences under different conditions, which will cause great difficulties in image classification. To solve this problem, this paper proposes a novel image classification algorithm. The algorithm uses an improved image representation method to generate virtual samples that not only better preserve the large-scale information and global features of the original training samples, but can also be regarded as another representation of objects. Combining multiple representations of images can effectively improve the accuracy of image classification. Moreover, this paper designs a simple and efficient weight fusion scheme to fuse the original training samples and virtual samples and obtain the final classification distance of the test sample. Experimental results on multiple face databases show that the proposed algorithm has higher classification accuracy than other state-of-the-art algorithms.
Keyword:
Sparse representation
Face recognition
Image representation
Weight fusion
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
Copper ferrocyanide loaded track etched membrane: an effective cesium adsorbent负载亚铁氰化铜的径迹蚀刻膜: 一种有效的铯吸附剂
PREAI
分享收藏
Multi-resolution dictionary learning for face recognition用于人脸识别的多分辨率字典学习.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏A micromachined efficient parametric array loudspeaker with a wide radiation frequency band具有宽辐射频带的微机械高效参量阵列扬声器
PREAI
分享收藏Real-World and Rapid Face Recognition Toward Pose and Expression Variations via Feature Library Matrix通过特征库矩阵对姿势和表情变化的真实世界和快速人脸识别
PREAI
分享收藏
查看更多内容