【作者】 顾华； 苏光大； 杜成；

【Author】 Gu Hua Su Guang-Da Du Cheng Department of Electronic Engineering, Tsinghua University, Beijing, 100084

【机构】 清华大学电子工程系图像图形研究所；

【摘要】 本文针对人脸识别中的特征提取问题,提出一种自动定位眼角的方法,在人脸图像中精确定位两眼瞳孔和内外眼角等关键特征点的位置,定位准确率达到98％。眼角的自动定位能够给后续的人脸特征自动提取和识别算法研究奠定良好的基础,帮助提高人脸识别算法的识别率。并将定位结果应用到人脸图像的预处理工作,提出以两眼外眼角为基准进行归一化校正,与通常的利用两眼瞳距方法相比较,更加准确和稳定,能够取得更好的预处理效果。更多还原

【Abstract】 A fast and exact approach was presented to extract the corners of eyes on human faces automatically. It can locate the positions of eyes with its near and far corners exactly by over 98% correct. This approach would help to extract the vital feature points on human face automatically and improve the accuracy of face recognition. Then, applying the results on the pretreatment of the face images, a method using the distance of two far corners of eyes to normalize the face images was presented. It could get more exact and steady outcomes than that using the distance of two irises commonly.更多还原