Age face simulation using aging functions on global and local features with residual images. (1st September 2017)

• Record Type: Journal Article
• Authors: Choi, Sung Eun; Jo, Jaeik; Lee, Sanghak; Choi, Heeseung; Kim, Ig-Jae; Kim, Jaihie
• Is Part Of: Expert systems with applications. Volume 80(2017)
• Page Start: 107
• Page End: 125
• Publication Date: 2017-09-01
• Subjects: Age face simulation -- Aging function -- Global feature -- Local feature -- Residual image -- Local image table; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2017.03.008
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Age simulation method using global, local features and residual image is proposed. The residual image represents the personal characteristics of the input image. Local features represent the local aging characteristics of wrinkle and skin. Abstract: In many previous methods for facial age simulation, the shape and appearance features of Active Appearance Models (AAM) are widely used to model the global facial characteristics. However, they cannot sufficiently represent facial details such as spots, scars, fine wrinkles, and skin blemishes, because many of them are removed from the AAM features during the dimension reduction process. Therefore, previous methods are not suitable for real-world applications, such as forensics, face recognition, and entertainment production systems, which require more accurate and realistic age simulation. To overcome the limitation, this paper proposes an automatic age simulation method based on a synergetic combination of the residual image, local features, and AAM global features. The residual image, which is the difference between a facial image and its reconstructed image by using AAM features, contains facial details of the input image that are not included in the AAM features. Representation of facial details in the age simulation process is achieved by generating and adding a targeted age-weighted residual image to the facial image synthesized by the AAM features. Further, facial details such as wrinkles and skin blemishes that have not yet appeared at the current age but normally appear as aging proceeds, are supplemented, and represented by local features that show locally different aging characteristics. The experimental results show that the proposed method simulates a face more accurately and realistically than previous methods, thereby confirming that it is more suitable for the real-world applications.