Artificial Neural Networks: A Tutorial
Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Age classification from facial images
Computer Vision and Image Understanding
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
Age and Gender Estimation Based on Wrinkle Texture and Color of Facial Images
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Modeling Age Progression in Young Faces
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Modeling Age Progression in Young Faces
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Age Synthesis and Estimation via Faces: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Comparing different classifiers for automatic age estimation
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
In this paper, a novel approach is proposed for age classification of face images. In consideration of the difference of adolescents and adults in aging mode, we utilize the facial feature ratios to classify face images into two groups: juveniles and adults. To eliminate the uncertainty lying in the face images, we elaborate a preprocessing procedure to the face images. Then, the Local Binary Pattern (LBP), which is a powerful texture description methods, will be used to describe the appearance of face images based the preprocessed images. Finally, a back-propagation (BP) network is learned automatically by facial LBP features and predetermined outputs. Through this method, we accomplish the task of age classification well, which is a problem of nonlinear system. Given a face image of an uncertain age, the age group will be predicted by the learned BP network. Our experimental results indicate that our approach can achieve the goal of age classification well. Besides, the influence of gender is studied and we find that considering gender independently in age classification is advisable.