David C. Wyld et al. (Eds) : CCSIT, SIPP, AISC, PDCTA, NLP - 2014 pp. 477–485, 2014. © CS & IT-CSCP 2014 DOI : 10.5121/csit.2014.4242         Onifade O.F.W. 1 and Akinyemi J.D. 2 1 Department of Computer Science University of Ibadan olufadeo@gmail.com 2 Department of Computer Science University of Ibadan akinyemijd@gmail.com ABSTRACT In this paper, we propose a framework for Age Estimation which uses a correlated ageing pattern to rank images and makes necessary inferences from the image ranks to estimate the exact age of images. We use AAM and LBP as complementary feature extraction techniques for extracting facial features in low dimensionality. Our correlated ageing pattern model learns the ageing patterns of different individuals across ages and uses these to determine an agerank for each image. Subsequently, the learned age rank of a reference image set is used to determine the ranks of test images in order to deduce relevant inferences for age estimation. Our approach is significantly different from the previous ranking approaches in that it determines age ranks that do not only represent the correlation of ages of different individuals but also the correlation of ageing patterns of different individuals. Our initial findings look promising with the intuitive manner with which we employ correlated ageing patterns. KEYWORDS Age Estimation, Ageing Pattern, Age Rank, Ranking 1. INTRODUCTION Human age estimation is a challenging task for humans as well as for machines. Although, humans possess the ability early in life to estimate the age of a person from his/her appearance [1], [2], the task is a subjective one which is largely based on the previous experience of the estimator. On the part of the estimated face image, several factors – external (eating habits, drugs, sickness, injuries, weather etc.) as well as internal (genetic or hereditary factors, ethnicity, gender) – could greatly cause variations in the pattern of aging of different individuals, thus making it more challenging to find a unique solution to the Age estimation problem. Therefore, whatever solution is to be proffered to the Age Estimation problem must be an adaptive one. Human Age Estimation has recently received attention in the research community and as such, several approaches and insights have been developed over the years to combat the problem. It continues to gain research interest especially due to its wide application in Adaptive Computing Methodologies such as Age-Specific Human Computer Interaction (ASHCI) [3], [4], [5]. A major motivation for this research from our own point of view is the fact that certain professions (Sports, Military etc.) require the knowledge of the actual age of individuals/professionals, hence, a medium of verifying the ages presented in such professions will be invaluable as it could be able to reduce the compromise in the ages supplied by these professionals.