Combining high-level and low-level visual tasks is a common technique in the field of computer vision. This work integrates the technique of image super resolution to semantic segmentation for document image binarization. It demonstrates that using image super-resolution as a preprocessing step can effectively enhance the results and performance of semantic segmentation.
@article{arxiv.2306.15218,
title = {Semantic Segmentation Using Super Resolution Technique as Pre-Processing},
author = {Chih-Chia Chen and Wei-Han Chen and Jen-Shiun Chiang and Chun-Tse Chien and Tingkai Chang},
journal= {arXiv preprint arXiv:2306.15218},
year = {2023}
}