Next Article in Journal
The Effects of Filler Shape, Type, and Size on the Properties of Encapsulation Molding Components
Next Article in Special Issue
Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection
Previous Article in Journal
Determining Ultrasound Arrival Time by HHT and Kurtosis in Wind Speed Measurement
Previous Article in Special Issue
Study of Process-Focused Assessment Using an Algorithm for Facial Expression Recognition Based on a Deep Neural Network Model
Article

Real-Time Hair Segmentation Using Mobile-Unet

1
HRI Section, Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), 218 Gajung-ro, Yueseong-gu, Daejeon 34129, Korea
2
ICT Department, ETRI School, University of Science & Technology, Daejeon 34129, Korea
*
Author to whom correspondence should be addressed.
Electronics 2021, 10(2), 99; https://doi.org/10.3390/electronics10020099
Received: 1 December 2020 / Revised: 28 December 2020 / Accepted: 29 December 2020 / Published: 6 January 2021
(This article belongs to the Special Issue Human Face and Motion Recognition in Video)
We described a real-time hair segmentation method based on a fully convolutional network with the basic structure of an encoder–decoder. In one of the traditional computer vision techniques for hair segmentation, the mean shift and watershed methodologies suffer from inaccuracy and slow execution due to multi-step, complex image processing. It is also difficult to execute the process in real-time unless an optimization technique is applied to the partition. To solve this problem, we exploited Mobile-Unet using the U-Net segmentation model, which incorporates the optimization techniques of MobileNetV2. In experiments, hair segmentation accuracy was evaluated by different genders and races, and the average accuracy was 89.9%. By comparing the accuracy and execution speed of our model with those of other models in related studies, we confirmed that the proposed model achieved the same or better performance. As such, the results of hair segmentation can obtain hair information (style, color, length), which has a significant impact on human-robot interaction with people. View Full-Text
Keywords: computer vision; hair segmentation; FCN; deep learning; Mobile-Unet; HRI computer vision; hair segmentation; FCN; deep learning; Mobile-Unet; HRI
Show Figures

Figure 1

MDPI and ACS Style

Yoon, H.-S.; Park, S.-W.; Yoo, J.-H. Real-Time Hair Segmentation Using Mobile-Unet. Electronics 2021, 10, 99. https://doi.org/10.3390/electronics10020099

AMA Style

Yoon H-S, Park S-W, Yoo J-H. Real-Time Hair Segmentation Using Mobile-Unet. Electronics. 2021; 10(2):99. https://doi.org/10.3390/electronics10020099

Chicago/Turabian Style

Yoon, Ho-Sub, Seong-Woo Park, and Jang-Hee Yoo. 2021. "Real-Time Hair Segmentation Using Mobile-Unet" Electronics 10, no. 2: 99. https://doi.org/10.3390/electronics10020099

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop