CAN A LINEAR AUTOASSOCIATOR RECOGNIZE FACES FROM NEW ORIENTATIONS
CAN A LINEAR AUTOASSOCIATOR RECOGNIZE FACES FROM NEW ORIENTATIONS
复制标题
线性自动关联器可以从新方向识别人脸吗
DOI：
10.1364/josaa.13.000717
复制
发表时间：
1996
影响因子：
1.9
通讯作者：
H. Abdi
中科院分区：
文献类型：
--
作者：
D. Valentin;H. Abdi
在二维像素强度表示上操作的面部计算模型的一个经常注意到的限制是它们不能处理取向的变化。我们表明，这种限制可以克服使用多个视图的一个给定的脸，而不是一个单一的视图来表示的脸。具体来说，我们表明，一个线性autoassociator训练重建一组面孔的多个视图是能够识别的面孔从新的视角。对存储器的内部表示的分析（即，单元间连接权重矩阵的特征向量）示出了两种感知信息之间的分离：定向和身份信息。
An often noted limitation of computational models of faces operating on two-dimensional pixel intensity representations is that they cannot handle changes in orientation. We show that this limitation can be overcome by the use of multiple views of a given face instead of a single view to represent the face. Specifically, we show that a linear autoassociator trained to reconstruct multiple views of a set of faces is able to recognize the faces from new view angles. An analysis of the internal representation of the memory (i.e., eigenvectors of the between-unit-connection weight matrix) shows a dissociation between two kinds of perceptual information: orientation and identity information.