Receptive field spaces and class-based generalization from a single view in face recognition
Receptive field spaces and class-based generalization from a single view in face recognition
复制标题
DOI：
10.1088/0954-898x_6_4_003
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
M. Lando;S. Edelman
中科院分区：
文献类型：
--
作者：
M. Lando;S. Edelman
阿布特拉特。我们描述了一种人脸识别的计算模型，该模型通过利用其他人脸的先验经验，从单一的人脸视图进行推广。在更广泛的观看条件下观看。该模型用分级重叠感受野(M)的活动向量来表示人脸图像。它依赖于高空间频率信息来估计观察条件，然后使用该条件来归一化(通过特定于人脸的变换)，并识别输入的低空间频率表示。特定类别的msformatian方法允许该模型复制一系列关于人脸识别的心理物理发现，并构成了对cmnt人脸识别方法的进步，后者不能从单个示例中进行概括。
Abtraet. We describe a computational model of face recognition, which generalizes from single views of faces by taking advantage of prior experience with other faces. seen under a wider range of viewing conditions. The model represents face images by veclo~s of activities of graded overlapping receptive fields (m). It relies on high-spatial-frequency information to estimate the~viewing conditions, which are then used to normalize (via a h’ansfonnation specific for faces), and identify, the low-spatial-frequency representation of the input. The class-specific msformatian approach allows the model to replicate a series of psychophysical findings on face recognition and constitutes an advance over cmnt face-recognition methods, which are incapable of generalization from a single example.