| Title |
Image Segmentation Method using Image Processing and Deep Network Techniques |
| Authors |
정홍구(Hong-Gu Jeong) ; 정현우(Hyun-Woo Jeong) ; 윤병현(Byung-Hyun Yoon) ; 최강선(Kang-Sun Choi) |
| DOI |
https://doi.org/10.5573/ieie.2021.58.1.67 |
| Keywords |
Superpixel; Machine learning; Semantic segmentation; Clustering |
| Abstract |
Deep neural network (DNN)-based image segmentation has performed well at the image semantic segmentation challenges. However, iterative sampling in the network causes inaccurate and uncertain segment boundaries. On the other hand, conventional image segmentation based on image processing tends to extract well-aligned object boundaries, but has been difficult in the semantic segmentation. In this paper, we propose image segmentation method that exploits both image processing techniques and the DNN to extract semantic objects with well-aligned boundaries. In the experiments, it is confirmed that the proposed algorithm improves DNN-based segmentation effectively. |