基于多标签的自动人脸年龄估计分析-analysis of automatic face age estimation based on multi - tags.docxVIP

AbstractAge estimation is a novel and significant research direction in the area of biometric identification, and there is plenty of age concerned information contained in facial images. However, because of the difficulties in getting enough training samples as well as the special characteristics of aging process, the estimation results based on facial images still need to be improved. As a result, motivated by the slow and continuous aging process, multi-label based model, which is fitter for aging characteristics, is introduced to represent the facial images in age estimation.In most of the previous work, age estimation is generally formulated as a single-label based problem. However, since aging is a gradual process and people are always in transition period between ages, labeling a facial example with an exact age is a difficult problem. Meanwhile, sufficient training data is lack for many ages. In this paper, to improve the accuracy of age estimation, a novel approach by applying Multi-Label Learning to the age features is proposed. In that approach, each facial image is treated as an example associated with the origin label as well as its neighboring ages, which makes the data more reliable and sufficient. The motivation comes from the observation that, with age changes slowly and smoothly, people would look quite like themselves before and after several years. And in this paper, in order to capture comprehensive information in facial images and further better the previous approach, multi-instance model is also introduced in the representation of facial images.Experiments show that the proposed multi-label approach outperforms the traditional age estimation approaches. Though the multi-instance improvement doesnt achieve better results, analysis as well as the future work is shown in this paper.Key words: Age Estimation, Multi-Label Learning, Multi-Instance Multi-Label Learning目录摘要.........................................................................