ABSTRACT
For applications based on facial image processing, pose variation is a difficult problem. In this paper, we propose a gender and age estimation system that is robust against pose variations. The acceptable facial pose range is a yaw (left-right) from -30 degrees to +30 degrees and a pitch (up-down) from -20 degrees to +20 degrees. According to our experiments on several large databases collected under real environments, the gender estimation accuracy is 84.8% and the age estimation accuracy is 80.9% (subjects are divided into 5 classes). The average processing time is about 70 ms/frame for gender estimation and 95 ms/frame for age estimation (Pentium4 3.2 GHz). The system can be used to automatically analyze shopping customers and pedestrians using surveillance cameras.
- Erina Takikawa, Satoshi Hosoi, Masato Kawade, User Adaptive Intelligent Interface using Facial Attribute Estimation. MIRU2005,(July.20), pp1604--1605. (in Japanese).Google Scholar
- Satoshi Hosoi, Erina Takikawa, Masato Kawade, Gender and Adult Estimation System with Gabor Wavelet and Support Vector Machines. SSII2002, (July.2002), pp243--246. (in Japanese).Google Scholar
- Takayoshi Yamashita, et al. A Fast Omni Directional Face Detection System. Demo program of Int. Conf. Computer Vision, 2005.Google Scholar
- Koichi Kinoshita et.al. A Fast and Robust Facial Points Localization and Pose Estimation System. Proc. Int. Conf. Computer Vision, 2005.Google Scholar
- F.Smeraldi and J.Bigun, Facial feature detection by Saccadic Exploration of the Gabor Decomposition. Proceedings of the 1998 International Conference on Image Processing, Octorber, 1998.Google Scholar
Index Terms
- Gender and age estimation system robust to pose variations
Recommendations
A fast and robust 3D head pose and gaze estimation system
ICMI '06: Proceedings of the 8th international conference on Multimodal interfacesWe developed a fast and robust head pose and gaze estimation system. This system can detect facial points and estimate 3D pose angles and gaze direction under various conditions including facial expression changes and partial occlusion. We need only one ...
Automatic Age Estimation Based on Facial Aging Patterns
While recognition of most facial variations, such as identity, expression and gender, has been extensively studied, automatic age estimation has rarely been explored. In contrast to other facial variations, aging variation presents several unique ...
Single-view-based 3D facial reconstruction method robust against pose variations
The 3D Morphable Model (3DMM) and the Structure from Motion (SfM) methods are widely used for 3D facial reconstruction from 2D single-view or multiple-view images. However, model-based methods suffer from disadvantages such as high computational costs ...
Comments