Abstract: To overcome the limitations of traditional face recognition methods for single sample, a novel method of face recognition based on Laplace Filter and Center-symmetric Local Binary Pattern（LFCLBP） is proposed. Firstly, original face images are filtered by Laplace filter. Secondly, gradient magnitude maps and phase maps of a face image are calculated. A operator named Center-Symmetric Local Binary Pattern（CS-LBP） is proposed to encode the gradient magnitude, and gradient phase is quantized into sixteen regions, then the proposed LFCLBP is the combination of the binary codes of phase and CS-LBP of magnitude. Finally, LFCLBP feature maps are divided into several blocks, and the concatenated histogram calculates over all blocks are utilized as the feature descriptor of face recognition. The recognition is performed by using the nearest neighbor classifier. Experimental results on YALE and AR face databases validate that the LFCLBP algorithm is an outstanding method for single sample face recognition under different illumination conditions, different facial expression conditions and partial occlusion conditions.

Key words: face recognition, single sample, Laplace filter, Center-Symmetric Local Binary Pattern（CS-LBP）, nearest neighbor classifier

摘要： 针对传统的人脸识别算法在单训练样本的情况下识别率不佳的情况，提出一种结合拉普拉斯滤波与中心对称局部二值模式的人脸识别算法（LFCLBP）。对原始人脸图像进行拉普拉斯滤波处理；然后对图像提取梯度幅值和梯度相位信息，对梯度幅值用CS-LBP算子编码，再将梯度相位量化到16个区间进行编码，将二者融合成人脸图像的LFCLBP特征；分块统计直方图特征，将所有分块的直方图串联起来作为人脸图像的特征向量，并用最近邻分类器识别。在YALE人脸库和AR人脸库上进行测试，测试结果表明该算法有效，在光照变化、表情变化和部分遮挡等环境下对单样本人脸图像具有较好的识别效果。

关键词: 人脸识别, 单样本, 拉普拉斯滤波, 中心对称局部二值模式, 最近邻分类器