반도체디스플레이기술학회지 (Journal of the Semiconductor & Display Technology)

한국반도체디스플레이기술학회 (The Korean Society Of Semiconductor & Display Technology)
권호 표지

딥 러닝 기반 이미지 압축 기법의 성능 비교 분석

Comparison Analysis of Deep Learning-based Image Compression Approaches

  • 이용환 (원광대학교 디지털콘텐츠공학과) ;
  • 김흥준 (경상국립대학교 컴퓨터과학부)
  • Yong-Hwan Lee (Dept. of Digital Contents, Wonkwang University) ;
  • Heung-Jun Kim (School of Computer Sciences, Gyeongsang National University)
  • 투고 : 2023.03.16
  • 심사 : 2023.03.23
  • 발행 : 2023.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Image compression is a fundamental technique in the field of digital image processing, which will help to decrease the storage space and to transmit the files efficiently. Recently many deep learning techniques have been proposed to promise results on image compression field. Since many image compression techniques have artifact problems, this paper has compared two deep learning approaches to verify their performance experimentally to solve the problems. One of the approaches is a deep autoencoder technique, and another is a deep convolutional neural network (CNN). For those results in the performance of peak signal-to-noise and root mean square error, this paper shows that deep autoencoder method has more advantages than deep CNN approach.

키워드

과제정보

본 연구는 2023년도 정부(미래창조과학부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(과제번호: 2021R1A2C1012947).

참고문헌

  1. Manish I. Patel, Sirali Suthar, Jil Thakar, "Survey on Image Compression using Machine Learning and Deep Learning", Proceedings of the International Conference on ICICCS, pp.1103-1105, 2019.
  2. Baba Fakruddin Ali, Prakash R., "Overview on Machine Learning in Image Compression Techniques", Innovations in Power and Advanced Computer Technologies, 2021.
  3. Hajar Maseeh Yasin, Adnan Mohsin Abdulazeez, "Image Compression based on Deep Learning: A Review", Asian Journal of Research in Computer Science, vol.8, issue.1, pp.62-76, 2021. https://doi.org/10.9734/ajrcos/2021/v8i130193
  4. David Alexandre, Chih-Peng Chang, Wen-Hsiao Peng, Hsueh-Ming Hang, "An Autoencoder-based Learned Image Compressor: Description of Challenge Proposal by NCTU", Workshop on Computer Vision and Pattern Recognition (CVPR), 2019. [Available at] https://arxiv.org/abs/1902.07385v1
  5. Lukas Cavigelli, Pascal Hager, Luca Benini, "CASCNN : A Deep Convolutional Neural Network for Image Compression Artifact Suppression", International Joint Conference on Neural Networks (IJCNN), 2017.
  6. Website; https://wiki.pathmind.com/deep-autoencoder
  7. Website; https://wiki.pathmind.com/convolutional-network
  8. Y.H. Lee, "Study on Image Compression Algorithm with Deep Learning", Journal of the Semiconductor & Display Technology, vol.21, no.4, 2022.
  9. Rikiya Yamashita, Mizuho Nishio, Richard Kinh Gian Do, Kaori Togashi, "Convolutional neural networks: an overview and application in radiology", Insights into Imaging, vol.9, pp.611-629, 2018. https://doi.org/10.1007/s13244-018-0639-9
  10. Guoan Cheng, Ai Matsune, Qiuyu Li, Leilei Zhu, Huaijuan Zang, Shu Zhan, "Encoder-Decoder Residual Network for Real Super-resolution", Conference on Computer Vision and Pattern Recognition, 2019.
  11. Shervin Mimaee, Yuri Boykov, Fatih Porikli, Antonio Plaza, Nasser Kehtarnavaz, "Image Segmentatioin using Deep Architecture: ASurvey", IEEE Transaction on Pattern Analysis and Machine Intelligence, vol.44, issue.7, 2022.
  12. Ian H. Witten, Eibe Frank, Mark A. Hall, Christopher J. Pal, Data Mining (Fourth Edition), Practical Machine Learning Tools and Techniques, 2017.
  13. Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang, "Learning a Deep Convolutional Network for Image Super-Resolution", Lecture Notes in Computer Science, vol.8692, pp.184-199, 2014.
  14. Pavel Svoboda, Michal Hradis, David Barina, Pavel Zemcik, "Compression Artifacts Removal Using Convolutional Neural Networks", International Conference in Central Europe on Computer Graphics and Visualization (WSCG), 2016.
  15. Jonathan Long, Evan Shelhamer, Trevor Darrell, "Fully Convolutional Networks for Semantic Segmentation", Computer Vision and Pattern Recognition (CVPR), 2015.
  16. Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, "cuDNN: Efficient Primitives for Deep Learning", https://arxiv.org/abs/1410.0759, 2014.
  17. Zhangyang Wang, Ding Liu, Shiyu Chang, Qing Ling, Yingzhen Yang, Thomas S. Huang, "D3: Deep Dual-Domain Based Fast Restoration of JPEGCompressed Images", IEEE Conference on Computer Vision and Pattern Recognition, 2016.
  18. Huibin Chang, Michael K. Ng, Tieyong Zeng, "Reducing Artifacts in JPEG Decompression Via a Learned Dictionary", IEEE Transactions on Signal Processing, Vol.62, Issue.3, 2014.
  19. Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao, "Multiple Description Convolutional Neural Networks for Image Compression", IEEE Transactions on Circuits and Systems for Video Technology, Vol.29, Issue.8, 2019.
  20. Zhengxue Cheng, Heming Sun, Masaru Takeuchi, Jiro Katto, "Energy Compaction-Based Image Compression Using Convolutional AutoEncoder", IEEE Transactions on Multimedia, Vol.22, Issue.4, 2020.
  21. Ruslan Salakhutdinov, Hugo Larochelle, "Efficient Learning of Deep Boltzmann Machines", Proceeding of International Conference on Artificial Intelligence and Statistics (AISTATS), 2010.
  22. Ruslan Salakhutdinov, Geoffrey Hinton, "A Better Way to Pretrain Deep Boltzmann Machines", Advances in Neural Information Processing Systems (NIPS), 2012.
  23. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei, "ImageNet: A large-scale hierarchical image database", IEEE Conference on Computer Vision and Pattern Recognition, 2009.
  24. Website; https://www.image-net.org/download.php
  25. Giuseppe Valenzise, Andrei Purica, Vedad Hulusic, Marco Cagnazzo, "Quality Assessment of Deep-Learning-Based Image Compression", IEEE International Workshop on Multimedia Signal Processing (MMSP), 2018.
  26. Y.K. Lee, Y.H. Lee, "Implementation of Moving Object Recognition based on Deep Learning", Journal of the Semiconductor & Display Technology, vol.17, no.2, 2018.
  27. H.C. Ahn, Y.H. Lee, "A Research of CNN-based Object Detection for Multiple Object Tracking in Image", Journal of the Semiconductor & Display Technology, vol.18, no.3, pp.110-114, 2019.