Cited 0 time in webofscience Cited 0 time in scopus

Real-time Face Segmentation Using Progressive Growing of Convolutional Neural Networks

Title
Real-time Face Segmentation Using Progressive Growing of Convolutional Neural Networks
Authors
Sohn, Myoung-KyuLee, Sang-HeonKim, Hyunduk
DGIST Authors
Sohn, Myoung-KyuLee, Sang-Heon; Kim, Hyunduk
Issue Date
2020-03
Citation
Journal of Industrial Electronics Technology and Application, 3(1), 145-149
Type
Article
Author Keywords
semantic segmentationdeep learningconvolutional neural networksneural networks
ISSN
2635-635X
Abstract
Semantic segmentation on an image is increasingly required in more and more fields such as scene understanding, inference of object relationships for autonomous driving and object extraction of interest. This technique gives the ability to segment different parts and objects from an image. Recently, there have also been many improvements in segmentation based on deep learning techniques. In particular, SegNet has improved the noisy image from the results of pixel-wise labelling. In this paper, a deep learning method for the segmentation of each area in an image is proposed. We introduce a progressive growing of convolutional neural networks that can learn quickly and increase the recognition rate using various resolutions. Then we compare our results to the learning methods using conventional convolutional neural networks architecture. We also show that our segmentation network works in real-time.
URI
http://hdl.handle.net/20.500.11750/12765
https://jieta.org/articles/real-time-face-segmentation-using-progressive-growing-of-convolutional-neural-networks
Publisher
Journal of Industrial Electronics Technology and Application
Related Researcher
Files:
There are no files associated with this item.
Collection:
Division of Automotive Technology1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE