改进的多目标回归实时人脸检测算法-计算机工程与应用.PDF

Computer Engineering and Applications 计算机工程与应用 2018 ，54（11） 1 ⦾热点与综述⦾ 用 改进的多目标回归实时人脸检测算法 应 吴志洋，卓 勇，廖生辉 与 WU Zhiyang, ZHUO Yong, LIAO Shenghui 程 g 厦门大学 航空航天学院，福建 厦门 361005 r 工 o College of Aerospace Engineering, Xiamen University, Xiamen, Fujian 361005, China . 机 j a WU Zhiyang, ZHUO Yong, LIAO Shenghui. Improved multi-objective regressive real-time face detection algorithm. e Computer Engineering and Applications, 2018, 54 （11）：1-7. 算 c 计 . Abstract ：Real-time multi-objective regression algorithm optimizes four location parameters respectively and separates w four location variables. It makes localization less accurate and training hard to converge. Based on the problems, this paper w proposes a real-time multi-object regression face detection algorithm, combining detection evaluation function Intersection w over Union （IoU ）as loss function. Based on multi-objective regression algorithm model proposed by Redmond etc., it adopts its real-time detection mechanism. Then IoU is introduced as loss function of location parameter. Four independent location parameters in real-time multi-object regression model are integrated into one unit and optimized, avoiding the defects of the base model. The algorithm is tested in face detection benchmark FDDB. The results indicate that this algo- rithm is superior to a mainstream traditional one in terms of face detection ’s effectiveness, and it outperforms other classical deep learning methods in terms of detection speed. The algorithm achieves a balance between fac