一种改进的多任务级联卷积神经网络人脸检测算法  

An Improved Multi-Task Cascade Convolution Neural Network Face Detection Algorithm

作　　者：李艳灵[1] 王莎莎 杨志鹏 LI Yanling;WANG Shasha;YANG Zhipeng(College of Computer and Information Technology,Xinyang Normal University,Xinyang 464000,China;Library,Xinyang Normal University,Xinyang 464000,China)

机构地区：[1]信阳师范学院计算机与信息技术学院,河南信阳464000 [2]信阳师范学院图书馆,河南信阳464000

出　　处：《信阳师范学院学报（自然科学版）》2022年第4期651-655,共5页Journal of Xinyang Normal University(Natural Science Edition)

基　　金：国家自然科学基金项目(62002307);河南省高等学校重点科研项目(21A520039);河南省高校科技创新团队(19IRTSTHN014)。

摘　　要：多任务级联的卷积神经网络(Multi-task Convolutional Neural Network,MTCNN)人脸检测算法因兼顾了检测的速度与准确率经常被用在一些人脸识别任务上,但是面对一些复杂的人脸检测任务,该网络检测的实时性与准确性仍然达不到实际要求。为解决这一问题,提出了一种改进的多任务级联卷积神经网络人脸检测算法。该方法对MTCNN中的R-Net和O-Net模块进行了改进,将这两个网络模块的NMS算法优化成Better-NMS算法,即重新对图像候选框的分类置信度进行修改,避免了对于IOU大于预设阈值的人脸候选框的漏检。在WIDER Face和FDDB数据集上,将所提出的改进的级联卷积神经网络人脸检测算法及其他对比算法进行了训练与评测。实验结果表明:该改进算法能在人脸检测过程中更好地排除冗余的候选框,保留精准度更高的回归窗口,可以在不损耗其鲁棒性的同时提高了人脸检测的准确率。The Multi-Task Cascade Convolutional Neural Network(MTCNN) face detection algorithm is often used in some face recognition tasks because it takes into account the detection speed and accuracy. However, in the face of some complex face detection tasks, the real-time performance and accuracy of the network detection still cannot meet the practical requirements. In order to solve this problem, an improved multi-task cascade convolution neural network face detection algorithm is proposed. This method improves the R-Net and O-net modules in MTCNN, and optimizes the NMS algorithm of these two network modules into a better NMS algorithm, that is, the classification confidence of image candidate frames is modified again to avoid the missed detection for face candidate frames with IOUs larger than the preset threshold. The proposed MTCNN face detection algorithm and other comparative algorithms are trained and evaluated on WIDER Face and FDDB datasets. The experimental results show that the improved method can better eliminate the redundant candidate frames and retain the regression window with higher accuracy in the face detection process, which can improve the accuracy of face detection without losing its robustness.

关 键 词：级联卷积神经网络 非极大值抑制 人脸检测 算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]