首页|高低频通道特征交叉融合的低光人脸检测算法

高低频通道特征交叉融合的低光人脸检测算法

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
低光条件下捕获的人脸图像存在着噪声严重、对比度低等不足,极大影响了现有人脸检测器的准确性,另外,现有的低光图像检测算法欠缺小区域人脸信息的提取能力.为此,提出一种基于深度学习的两阶段人脸检测算法,即利用现有的低光图像增强算法对人脸图像进行增强后再进行检测.为提升检测算法对人脸信息的提取能力,设计一种新型的高低频通道特征交叉融合方法,该方法首先使用高低频通道特征可分离模块分离出不同尺度特征的高低频信息,然后对上述信息进行交叉融合,提升网络提取高频细节信息和低频色域信息的能力,进而提高检测网络的性能.对比试验和消融试验验证了该研究方法的有效性,试验结果表明该方法优于基准方法4.0%mAP.
Low-light face detection method based on the cross fusion of high-and low-frequency channel features
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.

low-light face detectionfeatures of high-and low-frequency channelslow-light enhancementmultiscale feature fusioncomputer visionimage processingdeep learningfrequency domain analysis

许皓、钱宇华、王克琪、刘畅、李俊霞

展开 >

山西大学 大数据科学与产业研究院, 山西 太原 030006

山西大学 计算机与信息技术学院, 山西 太原 030006

山西大学 计算智能与中文信息处理教育部重点实验室, 山西 太原 030006

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

科技创新2030新一代人工智能重大项目国家自然科学基金山西省揭榜挂帅项目

2021-ZD011240062136005202201020101006

2024

10.11992/tis.202208034

智能系统学报
中国人工智能学会　哈尔滨工程大学

智能系统学报

CSTPCD北大核心
影响因子：0.672
ISSN：1673-4785
年,卷(期)：2024.19(2)
  • 40