To solve the problem of difficult face detection in a low illumination vehicle environment, a novel multi-scale retinex color restoration (MSRCR) approach exploiting the RGB three-channel decomposition and guided filtering (MSRCR-3CGF) is proposed. The MSRCR algorithm is employed to remove the artifacts and interference of low-light in the image based on the face detector using a multi-task cascaded convolutional neural network (MTCNN). The enhanced face image is decomposed into RGB, and GF is applied to each channel. The proposed method is tested on three widely used datasets: Dark Face, large-scale CelebFaces attributes (CelebA) and WIDER FACE, and an actual low-light scene in vehicles. The experimental results show that the proposed method suppresses the high-frequency noise of MSRCR, whilst improving the image enhancement and accuracy in the face detection in a low-light vehicle environment.
DeyMRanaSPSiarryP. A robust FLIR target detection employing an auto-convergent pulse coupled neural network. Remote Sens Lett2019; 10(7): 639–648.
2.
LaiXZhouLFuZ, et al. Enhanced pooling method for convolutional neural networks based on optimal search theory. IET Image Progress2019; 13(12): 2152–2161.
3.
VinkJPde HaanG. Comparison of machine learning techniques for target detection. Artif Intell Rev2015; 43(1): 125–139.
4.
ViolaPJonesMJ. Robust real-time face detection. Int J Comput Vis2004; 57(2): 137–154.
5.
DalalNTriggsB. Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), San Diego, CA, 20–25 June 2005, pp.886–893. New York: IEEE.
6.
SudhaNMohanARMeherPK. A self-configurable systolic architecture for face recognition system based on principal component neural network. IEEE Trans Circuits Syst Video Technol2011; 21(8): 1071–1084.
7.
WongYWSengKPAngLM. Radial basis function neural network with incremental learning for face recognition. IEEE Trans Syst Man Cybern2011; 41(4): 940–949.
8.
ElsaidSA. Reliable face recognition using artificial neural network. Int J Syst Dyn Appl2013; 2(2): 14–42.
9.
GirshickRDonahueJDarrellT, et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE conference on computer vision and pattern recognition, Columbus, OH, 23–28 June 2014, pp.580–587.
10.
GirshickR. Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015, pp: 1440–1448. New York: IEEE.
11.
RenSHeKGirshickR, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell2017; 39(6): 1137–1149.
12.
ZhangKZhangZLiZ, et al. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett2016; 23(10): 1499–1503.
13.
ZhangYHuaC. Driver fatigue recognition based on facial expression analysis using local binary patterns. Optik2015; 126(23): 4501–4505.
14.
LimSJungJKimSC, et al. Deep neural network-based In-vehicle people localization using ultra-wideband Radar. IEEE Access2020; 8: 96606–96612.
FuXZengDHuangY, et al. A weighted variational model for simultaneous reflectance and illumination estimation. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, 27–30 June 2016. New York: IEEE.
17.
XiaojieGYuLHaibinL. LIME: low-light image enhancement via illumination map estimation. IEEE Trans Image Process2017; 26(2): 982–993.
18.
ZhouMLinHYoungSS, et al. Hybrid sensing face detection and registration for low-light and unconstrained conditions. Appl Opt2018; 57(1): 69–78.
19.
OludareVKezebouLPanettaK, et al. Attention-guided cascaded networks for improved face detection and landmark localization under low-light conditions. In: Mobile multimedia/image processing, security, and applications 2020, vol. 11399, Online Only, USA, 27April–8May2020. Bellingham: Washington SPIE.
20.
ShenLYueZFengF, et al. MSR-net: low-light image enhancement using deep convolutional network, 2017. DOI: arXiv: 1711.02488.
21.
LiCGuoJPorikliF, et al. LightenNet: a convolutional neural network for weakly illuminated image enhancement. Pattern Recognit Lett2018; 104(1): 15–22.
22.
XiYXiaomingL. Multi-task convolutional neural network for pose-invariant face recognition. IEEE Trans Image Process2018; 27(2): 964–975.
23.
WuCZhangY. MTCNN and FACENET based access control system for face detection and recognition. Automa Control Comput Sci2021; 55(1): 102–112.
24.
WangDYangJDengJ, et al. FaceHunter: a multi-task convolutional neural network based face detector. Signal Process Image Commun2016; 47: 476–481.
25.
JobsonDJRahmanZWoodellGA. Properties and performance of a center/surround retinex. IEEE Trans Image Process1997; 6(3): 451–462.
26.
JobsonDJRahmanZWoodellGA. A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans Image Process1997; 6(7): 965–976.
LiuZPingLWangX, et al. Deep learning face attributes in the wild. IEEE International Conference on Computer Vision, Santiago, Chile, 2016.
29.
YangSLuoPLoyCC, et al. WIDER FACE: a face detection benchmark. In: IEEE conference on computer vision & pattern recognition, Las Vegas, NV, 27–30 June 2016, pp.5525–5533. New York: IEEE.
30.
MunteanuCRosaA. Color image enhancement using evolutionary principles and the Retinex theory of color constancy. In: Neural networks for signal processing XI: Proceedings of the 2001 IEEE signal processing society workshop, North Falmouth, MA, 12 September 2001, pp.393–402. New York: IEEE.
