@article{ART002880855},
author={Hyeyoung Moon and Namgyu Kim},
title={Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2022},
volume={27},
number={9},
pages={21-32},
doi={10.9708/jksci.2022.27.09.021}
TY - JOUR
AU - Hyeyoung Moon
AU - Namgyu Kim
TI - Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings
JO - Journal of The Korea Society of Computer and Information
PY - 2022
VL - 27
IS - 9
PB - The Korean Society Of Computer And Information
SP - 21
EP - 32
SN - 1598-849X
AB - Image labeling must be preceded in order to perform object detection, and this task is considered a significant burden in building a deep learning model. Tens of thousands of images need to be trained for building a deep learning model, and human labelers have many limitations in labeling these images manually. In order to overcome these difficulties, this study proposes a method to perform object detection without significant performance degradation, even though labeling some images rather than the entire image. Specifically, in this study, low-resolution oriental painting images are converted into high-quality images using a super-resolution algorithm, and the effect of SSIM and PSNR derived in this process on the mAP of object detection is analyzed. We expect that the results of this study can contribute significantly to constructing deep learning models such as image classification, object detection, and image segmentation that require efficient image labeling.
KW - object detection;deep learning;image labeling;super resolution;SSIM
DO - 10.9708/jksci.2022.27.09.021
ER -
Hyeyoung Moon and Namgyu Kim. (2022). Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings. Journal of The Korea Society of Computer and Information, 27(9), 21-32.
Hyeyoung Moon and Namgyu Kim. 2022, "Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings", Journal of The Korea Society of Computer and Information, vol.27, no.9 pp.21-32. Available from: doi:10.9708/jksci.2022.27.09.021
Hyeyoung Moon, Namgyu Kim "Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings" Journal of The Korea Society of Computer and Information 27.9 pp.21-32 (2022) : 21.
Hyeyoung Moon, Namgyu Kim. Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings. 2022; 27(9), 21-32. Available from: doi:10.9708/jksci.2022.27.09.021
Hyeyoung Moon and Namgyu Kim. "Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings" Journal of The Korea Society of Computer and Information 27, no.9 (2022) : 21-32.doi: 10.9708/jksci.2022.27.09.021
Hyeyoung Moon; Namgyu Kim. Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings. Journal of The Korea Society of Computer and Information, 27(9), 21-32. doi: 10.9708/jksci.2022.27.09.021
Hyeyoung Moon; Namgyu Kim. Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings. Journal of The Korea Society of Computer and Information. 2022; 27(9) 21-32. doi: 10.9708/jksci.2022.27.09.021
Hyeyoung Moon, Namgyu Kim. Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings. 2022; 27(9), 21-32. Available from: doi:10.9708/jksci.2022.27.09.021
Hyeyoung Moon and Namgyu Kim. "Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings" Journal of The Korea Society of Computer and Information 27, no.9 (2022) : 21-32.doi: 10.9708/jksci.2022.27.09.021
