No abstract

No abstract

We present an automatic module that can determine the pose of a human face f r om a digitized p ortrait-style image. The module is integrated into a larger system called PersonSpotter, which is able to recognize people by their faces coming from a live video s t r eam of data. The Pose Estimation Module is based on Bunch Graph Matching and can distinguish between ve di erent degrees of rotation in depth. The system features close to real-time performance a n d c onsiderable decrease in data size as well as increase not only in speed o f p r ocessing but also in the accuracy of pose recognition compared to similar systems developed in the past. Pose estimation success rate of 98.5 has been reached f o r a set of 210 faces rotated in various degrees and directions.

No abstract

A successful face recognition system calculates similarity of face images based on the activation of multiscale and multiorientation Gabor kernels, but without utilizing any statistical properties of that representation [3]. A method has been developed to weight the contribution of each element (1920 kernels) in the representation according to their power of predicting similarity of faces. The same statistical method has also been used to assess how changes in orientation (horizontal and vertical), expression, illumination and background contribute to the overall variance in the kernel activations. Weighting the elements in the representation according to their discriminative power has shown to increase recognition performance on a Caucasian and on a Japanese test image-set. It has also been demonstrated that such weighting method is particularly useful when data compression is a key requirement.

No abstract

No abstract

No abstract