Comparative Evaluation of Automatic Age Progression Methodologies

Abstract

Automatic age-progression is the process of modifying an image showing the face of a person in order to predict his/her future facial appearance. In this paper, we compare the performance of two age-progression methodologies reported in the literature against two novel approaches to the problem. In particular, we compare the performance of a method based on age prototypes, a method based on aging functions defined in a low-dimensional parametric model space, and two methods based on the distributions of samples belonging to different individuals and different age groups. Quantitative comparative results reported in the paper are based on dedicated performance evaluation metrics that assess the ability of each method to produce accurate predictions of the future/previous facial appearance of subjects. The framework proposed in this paper promotes the idea of a standardized performance evaluation protocol for age-progression methodologies, using images from a publicly available image database.

When age-progressed images are unreliable: The roles of external features and age range

“…Software engineering research has aimed to combat the aging problem specifically in the forensic context when a target is missing and has an outdated last known photograph [20,29]. Such a technique could potentially eliminate the need for an artist to be involved in the construction of age-progressions at all.…”

“…Often such comparisons are also made by computers as well, as these techniques are most useful for automated security systems. Specific techniques vary and may be differentially optimal depending on circumstance (see [20] for an experimental comparison). Such approaches do produce believable likenesses over a lifespan of aging, but aesthetically pleasing likenesses are not necessarily accurate.…”

Consistency of Optimized Facial Features through the Ages

“…The research in age estimation has increase significantly since 2002 [17][18][19][20][21]. There huge numbers of research works are already done and still running on age classification field because of its dynamicity.…”

Face Verification Across Age Progression Using Discriminative Methods

“…Most of these works focus on age estimation [14], [15], [30], [43], [41], [8], [10], [11], [9], [24], [40] and age simulation [18], [35], [36], [38]. In addition, some researchers study the effect of age progression on face profiles and appearances [31], [37], [32], [16].…”