Image super-resolution based on error compensation with convolutional neural network

Wei Ting Lu, Chien Wei Lin, Chih Hung Kuo, Ying Chan Tung

研究成果: Conference contribution

4 引文 斯高帕斯(Scopus)

摘要

Convolutional Neural Networks have been widely studied for the super-resolution (SR) and other image restoration tasks. In this paper, we propose an additional error-compensational convolutional neural network (EC-CNN) that is trained based on the concept of iterative back projection (IBP). The residuals between interpolation images and ground truth images are used to train the network. This CNN model can compensate the residual projection in the IBP more accurately. This CNN-based IBP can be further combined with the super-resolution CNN(SRCNN). Experimental results show that our method can significantly enhance the quality of scale images as a post-processing method. The approach can averagely outperform SRCNN by 0.14 dB and SRCNN-EX by 0.08 dB in PSNR with scaling factor 3.

原文English
主出版物標題Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1160-1163
頁數4
ISBN(電子)9781538615423
DOIs
出版狀態Published - 2017 7月 2
事件9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, Malaysia
持續時間: 2017 12月 122017 12月 15

出版系列

名字Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
2018-February

Other

Other9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
國家/地區Malaysia
城市Kuala Lumpur
期間17-12-1217-12-15

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 人機介面
  • 資訊系統
  • 訊號處理

指紋

深入研究「Image super-resolution based on error compensation with convolutional neural network」主題。共同形成了獨特的指紋。

引用此