Video-based face model fitting using adaptive active appearance model

• NCJ Number: 305623
• Journal: Image and Vision Computing Volume: 28 Issue: 7 Dated: July 2010 Pages: 1162-1172
• Author(s): Xiaoming Liu
• Date Published: 2010
• Length: 11 pages
• Grant Number(s): 2007-DE-BX-K191; 2005-IJ-CX-K060
• Agencies: NIJ-Sponsored
• Publication Type: Research (Applied/Empirical)
• Award: Site-Adaptive Face Recognition at a Distance; High Quality 3D Facial Images From Surveillance Video

Annotation

This paper proposes the fitting of an Adaptive Active Appearance Model (AAAM) to video sequences for improved quality of real-world video content.

Abstract

For many applications, effectively fitting an AAM to video sequences is of critical importance and challenging, especially considering the varying quality of real-world video content. While the generic AAM component is held fixed, the subject-specific model component is updated during the fitting process by selecting the frames that can be best explained by the generic model. Experimental results from both indoor and outdoor representative video sequences demonstrate the faster fitting convergence and improved fitting accuracy.  (Publisher abstract provided)