Browse > Article
http://dx.doi.org/10.9708/jksci.2022.27.09.021

Selective labeling using image super resolution for improving the efficiency of object detection in low-resolution oriental paintings  

Moon, Hyeyoung (Graduate School of Business IT, Kookmin University)
Kim, Namgyu (Graduate School of Business IT, Kookmin University)
Publication Information
Journal of the Korea Society of Computer and Information / v.27, no.9, 2022 , pp. 21-32 More about this Journal
Abstract
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.
Keywords
object detection; deep learning; image labeling; super resolution; SSIM;
Citations & Related Records
Times Cited By KSCI : 7  (Citation Analysis)
연도 인용수 순위
1 K. Shin, J. Lee, and J. Kim, "Thermal Image Processing and Synthesis Technique Using Faster-RCNN," Journal of Convergence for Information Technology, Vol. 11, No. 12 , pp. 30-38, December 2021.   DOI
2 H. Kim and D. Choi, "A Perimeter-Based IoU Loss for Efficient Bounding Box Regression in Object Detection," Journal of KIISE, Vol. 48, No. 8, pp. 913-919, August 2021.   DOI
3 J. Song, S. Lee, and S. Park, "A Study on the Industrial Application of Image Recognition Technology," Journal of the korea contents association, Vol. 20, No. 7, pp. 86-96, July 2020.   DOI
4 Y Li, C Ma, T. Zhang, J. Li, Z. Ge, Y. Li, and S Serikawa, "Underwater Image High Definition Display Using the Multilayer Perceptron and Color Feature-Based SRCNN," IEEE Access, pp. 83721-83728, June 2019. DOI: 10.1109/ACCESS.2019.2925209   DOI
5 X. Wang, K. Yu1, and S. Wu, "ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks," arXiv:1809.00219 v2, September 2018.
6 X. Wang and L. Xie, C. Dong, and Y. Shan, "Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data," International Conference on Computer Vision Workshops IEEE/CVF, July 2021.
7 U. Sara, M. Akter, and MS. Uddin, "Image quality assessment through FSIM, SSIM, MSE and PSNR-a comparative study," Journal of Computer and Communications, Vol.7 No.3, March 2019.
8 M. Laavanya and V. Vijayaraghavan, "Residual Learning of Transfer-learned AlexNet for Image Denoising," IEIE Transactions on Smart Processing and Computing, Vol. 9, No. 2, April 2020. DOI : 10.5573/IEIESPC.2020.9.2.135   DOI
9 S. Jeon, D. Kim, and H. Jung, "YOLO-based lane detection system," Journal of the Korea Institute of Information and Communication Engineering, Vol. 25, No. 3, pp. 464-470, March 2021.   DOI
10 W. Kim, F. Dehghan, and S. Ch, "Vehicle License Plate Recognition System using SSD-Mobilenet and ResNet for Mobile Device," Smart media journal, Vol. 9, No. 2, pp. 92-98, September 2020.   DOI
11 S. Hong, D. Kim, and B. Kim, "Image Labeling Technology Analysis and Training Set Generation Model for Detecting Damage and Cracks in Road Pavement," Journal of Korean Society for Geospatial Information Science, Vol. 28, No. 4, pp. 119-125, December 2020.   DOI
12 H. Gu, J. Seo, and S. Choo, "A Development of Facde Dataset Construction Technology Using Deep Learning-based Automatic Image Labeling," Architectural Institute of korea, Vol. 35, No. 12, pp. 43-53, December 2019.
13 R. Lee, R. Jang, and M. Park, "An Auto-Labeling based Smart Image Annotation System," Journal of the korea contents association, Vol. 21, No. 6, pp. 701-715, June, 2021.   DOI
14 C. Lee, S. Youn, and C. Cho, "License Plate Image Enhancement Based on Enhanced Super-resolution Generative Adversarial Networks," Journal of Next-generation Convergence Technology Association, Vol. 6, No. 1, pp. 5-11, January 2022.   DOI
15 Y. Cho and S. Kim, "Labeling of Facility Crops Using Instance Segmentation of Deep Learning," Journal of Korean Institute of Intelligent Systems, Vol. 31, No. 4, pp. 305-310, August 2021.   DOI
16 J. Kang and J. Gwak, "Adaptive Face Mask Detection System based on Scene Complexity Analysis," Journal of The Korea Society of Computer and Information, Vol. 26, No. 5, pp. 1-8, May 2021.   DOI
17 K. Choi, "Conceptual Design of Data Labeling System based on Metaverse for the Military Artificial Intelligence using the Modified Functional Analysis Method," Korean Journal of Military Art and Science, Vol. 78, No. 1, pp. 375-390, February 2022.   DOI
18 W. Jeon and S. Rhee, "An Annotation Method of Vegetable Fruits and Leaves using a Depth Map," Journal of Korean Institute of Intelligent Systems, Vol. 31, No. 6, pp. 465-474, December 2021.   DOI
19 T. Mensink, J. Verbeek, and G. Csurka, "Learning structured prediction models for interactive image labeling," CVPR, August 2011.
20 A. Diaz-Pinto, S. Alle, A. Ihsani, and M. Asad, "Monai label: A framework for ai-assisted interactive labeling of 3d medical images," arXiv:2203.12362, March 2022.
21 J. Lee, "PSNR Analysis of Ultrasound Images for Follow-up of Hepatocellular Carcinoma," Journal of the Korean Society of Radiology, Vol. 9, No. 5, pp. 263-267, August 2015.   DOI
22 J. Yoon, T. Kim, and Y. Choe, "GAN based Single Image Super-Resolution via Spatially Adaptive De-normalization," The Transactions of the Korean, Vol. 70, No. 2, pp. 402~407, February 2021.
23 J. Yu, Y. Han, J. Kim, and H. Hahn, "Ensemble Deep Network for Dense Vehicle Detection in Large Image," The Korean Society Of Computer And Information, Vol. 26, No. 1, pp. 45-55, January 2021.
24 Y. Lee and H. Park, "A Study of Lightening SRGAN Using Knowledge Distillation," Journal of Korea Multimedia Society, Vol. 24, No. 12, pp. 1598-1605, December 2021.   DOI
25 C. Han, H. Hayashi, L. Rundo, R. Araki, "GAN-based synthetic brain MR image generation," 2018 IEEE 15th International Symposium on Biomedical Imaging, May 2018. DOI: 10.1109/ISBI.2018.8363678   DOI
26 H. Lim, "Overview of Image-based Object Recognition AI technology for Autonomous Vehicles," Journal of the Korea Institute of Information and Communication Engineering, Vol. 25, No. 8, pp. 1117-1123, August 2021.   DOI
27 Aitimes, "Don't worry about running out of data," https://www.aitimes.com/news/articleView.html?idxno=143907, April 2022.
28 LC. Chen, S. Fidler, and AL. Yuille, "Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision," CVPR, pp. 3198-3205, 2014.
29 Q. Junlong, J. Shin, and J. Ko, "A Study on Energy Consumption Prediction from Building Energy Management System Data with Missing Values Using SSIM and VLSW Algorithms," The transactions of The Korean Institute of Electrical Engineers, Vol. 70, No. 10, pp. 1540-1547, October 2021.   DOI