Active Appearance Model (AAM) - From theory to implementation

Abstract

Active Appearance Model (AAM) is a kind of deformable shape descriptors which is widely used in computer vision and computer graphics. This approach utilizes statistical model obtained from some images in training set and gray-value information of the texture to fit on the boundaries of a new image. In this paper, we describe a brief implementation, apply the method on hand object and finally discuss its performance in compare to Active Shape Model(ASM). Our experiments shows this method is more sensitive to the initialization and slower than ASM.

Publication
VISAPP 2008: PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 1