Gender Classification of Complex Face Images Based on AdaBoost
Junrui Wang, Qichuan Tian, Manli Wang, Xiaohui Wu · 2017
This paper proposes a face-based gender classifier which is based on Adaboost, and selects the face database with different color, angle and illumination.A variety of feature extraction methods are used to reduce the dimension, noise and calculation of the sample, and ensure a high recognition rate.The simulation results show that the proposed classifier can complete the gender classification work with the interference of skin color, angle and illumination, and the error rate is only 7.5%, what is more, the training and recognition speed is also get improved.