Face pose estimation in uncontrolled environments

Automatic estimation of head pose from a face image is a sub-problem of human face analysis with widespread applications such as gaze direction detection and human com-puter interaction. Most current methods estimate pose in a limited range or treat pose as a classification problem by assigning the face to one of many discrete poses. Moreover they have mainly been tested on images taken in controlled environments. We address the problem of estimating pose as a continuous regression problem on “real world ” images with large variations in background, illumination and expression. We propose a prob-abilistic framework with a general representation that does not rely on locating facial features. Instead we represent a face with a non-overlapping grid of patches. This rep-resentation is used in a generative model for automatic estimation of head pose ranging from −90 ◦ to 90 ◦ in images taken in uncontrolled environments. Our methods achieve a correlation of 0.88 with the human estimates of pose.