Automatic pose estimation system for human faces based on bunch graph matching technology

We present an automatic module that can determine the pose of a human face from a digitized portrait-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 stream of data. The pose estimation module is based on bunch graph matching and can distinguish between five different degrees of rotation in depth. The system features close to real-time performance, considerable decrease in data size and increase in the accuracy of pose recognition compared to similar systems developed in the past. Pose estimation success rate of 98.5% has been reached for a set of 210 faces rotated in various degrees and directions.