Abstract:An algorithm is presented for face detection based on Haar-Like T features which are the extension of Haar-Like features. Due to the distributions of facial organs, a lot of T structure features on face models can be found. Based on the principle of Haar-Like features, 4 Haar-Like T features are presented which are similar to Haar-Like features. Haar-Like T features and Haar-Like features are all input into Adaboost algorithm to generate weak classifiers for feature selection. Finally, a strong classifier is constructed by cascading those weak classifiers for face detection. Extensive face detection experiments are conducted for the proposed algorithm. Compared with the traditional face detection classifier, such as Haar-Like classifier and LBP classifier, the superior experimental results prove the effectiveness and the superiority of the proposed algorithm.
王庆伟,应自炉. 一种基于Haar-Like T特征的人脸检测算法*[J]. 模式识别与人工智能, 2015, 28(1): 35-41.
WANG Qing-Wei, YING Zi-Lu. A Face Detection Algorithm Based on Haar-Like T Features. , 2015, 28(1): 35-41.
[1] Viola P, Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, USA, 2001, I: 511-518 [2] Viola P, Jones M. Robust Real-Time Face Detection. International Journal of Computer Vision, 2004, 57(2): 137-154 [3] Lienhart R, Maydt J. An Extended Set of Haar-Like Features for Rapid Object Detection // Proc of the IEEE International Conference on Image Processing. New York, USA, 2002, I: 900-903 [4] Navabifar F, Yusof R, Emadi M. Using Rotated Asymmetric Haar-Like Features for Non-frontal Face Detection. Advanced Science Letters, 2013, 19(12): 3520-3524 [5] Zhao X W, Chai X J, Niu Z H, et al. Context Modeling for Facial Landmark Detection Based on Non-adjacent Rectangle (NAR) Haar-like Feature. Image and Vision Computing, 2012, 30(3): 136-146 [6] Ge K B, Wen J, Fang B. Adaboost Algorithm Based on MB-LBP Features with Skin Color Segmentation for Face Detection // Proc of the IEEE International Conference on Wavelet Analysis and Pattern Recognition. Guilin, China, 2011: 40-43 [7] He Z X, Ding X Q, Fang C, et al. Multiview Face Detection Based on LBP and CCS-AdaBoost. Journal of Zhejiang University: Engineering Science, 2013, 47(4): 622-629 (in Chinese) (何智翔,丁晓青,方 驰,等.基于LBP和CCS-Adaboost的多视角人脸检测.浙江大学学报:工学版, 2013, 47(4): 622-629) [8] Chang H L, Wen J. Entropy-Directed AdaBoost Algorithm with NBBP Features for Face Detection. Information Technology Journal, 2011, 10(8): 1518-1526 [9] Zakaria Z, Suandi S A. Face Detection Using Combination of Neural Network and Adaboost // Proc of the TENCON 2011-2011 IEEE Region 10 Conference. Bali, Indonesia, 2011: 335-338 [10] Guo S, Gu G C, Cai Z S, et al. Multi-pose Face Detection Based on Feature Fusion and Decision Tree Cascade Structure. Journal of Shenyang University of Technology, 2012, 34(2): 203-208 (in Chinese) (郭 耸,顾国昌,蔡则苏,等.基于特征融合与决策树级联结构的多姿态人脸检测.沈阳工业大学学报, 2012, 34(2): 203-208) [11] Zhang X P, Wei J. Human Face Detection Based on Multi-stage Asymmetric Boosting and Genetic Algorithm. Electronic Design Engineering, 2012, 20(5): 122-125 (in Chinese) (张向鹏,魏 江.基于多级联不对称增强和遗传算法的人脸检测.电子设计工程, 2012, 20(5): 122-125) [12] Cai C H, Zhu J Q. Real-Time Face Detection Using Gentle AdaBoost and Nesting Cascade Structure. Journal of Signal Processing, 2013, 29(8): 956-963 (in Chinese) (蔡灿辉,朱建青.采用Gentle AdaBoost和嵌套级联结构的实时人脸检测.信号处理, 2013, 29(8): 956-963)