The Research On Age Estimation For Facial Images

Age estimation has been widely used and became more and more important, for its usefulness in various applications. As a common consensus that the appearances of different persons with the same age diverge widely, we have an opinion that the estimated result of a facial image should be a dynamic range or discrete candidate ages, not a specific one or classified into predefined age groups. Therefore, this paper presents a new method to estimate a set of possible ages of a facial image for large image database with a novel measurement.1) By transferring the shape and appearance features of a face into a set of Landmark-Terms, then the famous technology TFIDF in information retrieval and text mining fields is introduced to build a weight matrix of these Landmark-Terms for all age groups, and then some possible ages of a facial image are estimated by this matrix.2) A new clustering method is also used to find the density peaks for each age group by processing the LBP features, then according to the distances of the facial image to the peaks, we obtain another possible estimated ages.3) A novel dynamic range estimation method is proposed. Firstly, we estimate the facial image with two special methods. Then we proposed a dynamic range estimation method to confuse the results produced by two single method. The result of the proposed method is a dynamic age range rather than a predefined age group or a special age.The experiments show the method performs better than a single methods.4) A novel measurement is proposed to evaluate the performance for methods that provide more than one possible estimated ages. The proposed measurements are BPMAE, NBPMAE and CI/CL(Confidence Interval/Confidence Level).The experiments show that our method is promising, and the best BPMAE and NBPMAE also indicate the top possible ages could cover the neighborhood of the ground-truth age with small errors, and the best CI/CL also can reach an acceptable results.