高级检索
    李 宽 殷建平 李 永 刘发耀. 基于Gabor系数分块统计和自适应特征选择的人脸描述与识别[J]. 计算机研究与发展, 2012, 49(4): 777-784.
    引用本文: 李 宽 殷建平 李 永 刘发耀. 基于Gabor系数分块统计和自适应特征选择的人脸描述与识别[J]. 计算机研究与发展, 2012, 49(4): 777-784.
    Li Kuan, Yin Jianping, Li Yong, and Liu Fayao. Local Statistical Analysis of Gabor Coefficients and Adaptive Feature Extraction for Face Description and Recognition[J]. Journal of Computer Research and Development, 2012, 49(4): 777-784.
    Citation: Li Kuan, Yin Jianping, Li Yong, and Liu Fayao. Local Statistical Analysis of Gabor Coefficients and Adaptive Feature Extraction for Face Description and Recognition[J]. Journal of Computer Research and Development, 2012, 49(4): 777-784.

    基于Gabor系数分块统计和自适应特征选择的人脸描述与识别

    Local Statistical Analysis of Gabor Coefficients and Adaptive Feature Extraction for Face Description and Recognition

    • 摘要: 提出一种新的人脸描述及识别方法,首先对归一化后的人脸图像进行多方向多尺度Gabor变换;然后对人脸区域进行分块,以块为单位统计Gabor系数的均值和方差,求得块特征矢量(block feature vector, BFV),按先行后列的顺序将各块的BFV拼接,构成整幅人脸图像特征矢量(face feature vector, FFV).在分类器设计阶段,引入两两比对和投票机制,用多个两类分类器组合成多类分类器.在训练某个具体的两类分类器时,根据隶属训练样本计算FFV中每项的分辨力,以分辨力大小为依据选出最优特征子集(best subset feature vector, BSFV).基于Yale人脸数据集展开实验,与已发表的算法和结果进行对比,证明了该方法的有效性.

       

      Abstract: Many researches have shown that Gabor feature is robust to illumination and expression variations and has been successfully used in face recognition. However, Gabor-based methods suffer from the high dimensional problem, also known as the curse of dimensionality. A novel method for face description and recognition based on Gabor filters is proposed in this paper. The normalized face image is first decomposed by convolving with multi-scale and multi-orientation Gabor filters, and then separated into several blocks. Through statistical techniques, including mean and variance of Gabor coefficients inside each block, the block feature vector (BFV) can be obtained. The face feature vector (FFV) of the whole image is then constructed by conjugating the BFVs in row column order. Thus FFV can be used to describe the face, and the high dimensional problem is effectively solved. In the classification stage, a robust face recognition system which performs multi-class classification is built based on several two-class classifiers using voting mechanism. For each two-class classifier, a feature extraction module adaptively selects the most important features. Therefore, only the most distinguishable features in FFV are picked out, called best subset feature vector (BSFV). The results compared with the published results on Yale face database verify the validity of the proposed method.

       

    /

    返回文章
    返回