Eye Semantic Segmentation with a Lightweight Model

Van Thong Huynh, Soo-Hyung Kim, Gueesang Lee, Hyung-Jeong Yang

ICCVW 2019 pp. 3694-3697

doi:10.1109/ICCVW.2019.00457 /iccvw/2019/huynh2019iccvw-eye/

Abstract

In this paper, we present a multi-class eye segmentation method that can run the hardware limitations for real-time inference. Our approach includes three major stages: get a grayscale image from the input, segment three distinct eye region with a deep network, and remove incorrect areas with heuristic filters. Our model based on the encoder-decoder structure with the key is the depthwise convolution operation to reduce the computation cost. We experiment on OpenEDS, a large scale dataset of eye images captured by a head-mounted display with two synchronized eye facing cameras. We achieved the mean intersection over union (mIoU) of 94.85% with a model of size 0.4 megabytes.

PDF ICCVW Semantic Scholar

Cite

Text

Huynh et al. "Eye Semantic Segmentation with a Lightweight Model." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00457

Markdown

[Huynh et al. "Eye Semantic Segmentation with a Lightweight Model." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/huynh2019iccvw-eye/) doi:10.1109/ICCVW.2019.00457

BibTeX

@inproceedings{huynh2019iccvw-eye,
  title     = {{Eye Semantic Segmentation with a Lightweight Model}},
  author    = {Huynh, Van Thong and Kim, Soo-Hyung and Lee, Gueesang and Yang, Hyung-Jeong},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {3694-3697},
  doi       = {10.1109/ICCVW.2019.00457},
  url       = {https://mlanthology.org/iccvw/2019/huynh2019iccvw-eye/}
}