CAJ | 학술논문

针对低分辨率人脸序列的识别这一问题,提出了一种超分辨率重构识别算法.该算法利用低分辨率序列中所提供的关于同一人脸的不同信息,先重构出一幅具有更高分辨率的人脸图像,然后再进行基于Gabor特征的人脸识别.实验结果表明,该算法能够显著提高人脸识别率.
침대저분변솔인검서렬적식별저일문제,제출료일충초분변솔중구식별산법.해산법이용저분변솔서렬중소제공적관우동일인검적불동신식,선중구출일폭구유경고분변솔적인검도상,연후재진행기우Gabor특정적인검식별.실험결과표명,해산법능구현저제고인검식별솔.
The recognition rate of normal face recognition algorithms drops dramatically when the resolution of face is too low.In this paper,a new hybrid face recognition algorithm is proposed to tackle the problem of face recognition from low resolution image sequences.The proposed approach first constructs a highresolution face image by fully utilizing the sub-pixel information provided in the low-resolution sequences,and then performs Gabor feature based recognition.Experimental results are also provided to demonstrate the effectiveness of the proposed algorithm.