Real-time Segmentation and Facial Skin Tones Grading
Ling Luo, Dingyu Xue, Xinglong Feng, Yichun Yu, Peng Wang

TL;DR
This paper introduces an efficient deep learning-based method for real-time facial skin and hair segmentation, achieving high accuracy and speed, and utilizing color features for skin tone grading, suitable for CPU environments.
Contribution
The authors propose a lightweight segmentation network (HLNet) that balances speed and accuracy and incorporate color moment features for skin tone classification, demonstrating effectiveness on multiple datasets.
Findings
Achieves 90.73% pixel accuracy on Figaro1k dataset at 16 FPS on CPU.
Effective skin tone grading with approximately 80% accuracy.
Model generalizes well across different datasets.
Abstract
Modern approaches for semantic segmention usually pay too much attention to the accuracy of the model, and therefore it is strongly recommended to introduce cumbersome backbones, which brings heavy computation burden and memory footprint. To alleviate this problem, we propose an efficient segmentation method based on deep convolutional neural networks (DCNNs) for the task of hair and facial skin segmentation, which achieving remarkable trade-off between speed and performance on three benchmark datasets. As far as we know, the accuracy of skin tones classification is usually unsatisfactory due to the influence of external environmental factors such as illumination and background noise. Therefore, we use the segmentated face to obtain a specific face area, and further exploit the color moment algorithm to extract its color features. Specifically, for a 224 x 224 standard input, using our…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Video Surveillance and Tracking Methods · Color Science and Applications
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
