智能系统学报2024，Vol.19Issue(2)：472-481,10.DOI:10.11992/tis.202208034
高低频通道特征交叉融合的低光人脸检测算法
Low-light face detection method based on the cross fusion of high-and low-frequency channel features
摘要
Abstract
Face images captured under low-light conditions suffer from significant noise and low contrast,which negat-ively impact the accuracy of existing face detection systems.In addition,existing low-light image detection algorithms struggle to extract information from small facial areas.To tackle these issues,this paper proposes a two-stage face detec-tion algorithm based on deep learning.This algorithm enhances low-light images before initiating the detection process using an established low-light image enhancement method.The objective is to enhance the ability of the detection meth-od to extract facial information.Thus,a new cross-fusion method of high-and low-frequency channel features is de-signed.The first step involves using a separable module for high-and low-frequency channel features,enabling the sep-aration of different scale features.These separated features are then cross-fused to improve the ability of the network to extract high-frequency details and low-frequency color information.This,in turn,improves the performance of the de-tection network.The comparative and ablation experiments validate the effectiveness of the proposed method.The ex-perimental results demonstrate that our method surpasses the baseline method by 4.0%mAP.关键词
低光人脸检测/高低频通道特征/低光增强/多尺度特征融合/计算机视觉/图像处理/深度学习/频率域分析Key words
low-light face detection/features of high-and low-frequency channels/low-light enhancement/multiscale feature fusion/computer vision/image processing/deep learning/frequency domain analysis分类
信息技术与安全科学引用本文复制引用
许皓,钱宇华,王克琪,刘畅,李俊霞..高低频通道特征交叉融合的低光人脸检测算法[J].智能系统学报,2024,19(2):472-481,10.基金项目
科技创新2030-"新一代人工智能"重大项目(2021-ZD0112400) （2021-ZD0112400）
国家自然科学基金项目(62136005) （62136005）
山西省揭榜挂帅项目(202201020101006). （202201020101006）
