Quality Image Enhancement from Low Resolution Camera using Convolutional Neural Network

被引：0
作者：
Patmawati, Nopita Pratiwi [1 ]
Arifianto, Anditya [1 ]
Ramadhani, Kurniawan Nur [1 ]
机构：
[1] Telkom Univ, Fac Informat, Bandung, Indonesia
来源：
2019 7TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY (ICOICT) | 2019年
关键词：
image super-resolution; quality; convolutional neural network;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Images captured with various cameras have different qualities especially low-resolution images which generally have deficiencies in terms of quality. The uses of Convolutional Neural Network (CNN) in Super Resolution has been widely applied and has impressive performance results. It encourages the use of CNN to translate the captured images by low-resolution into a better resolution. In this paper, we propose a new architecture to perform image translation from low-resolution into a higher one using DenseNet with Skip-connections. The dataset used is taken from the DPED (DSLR-Photo Enhancement Dataset) which contains images captured from different cameras simultaneously. To get results that can be used by all camera models, a transfer learning scenario is added. Using our architecture, we were able to achieve results with average PSNR of 20,86 dB and 0,9307 SSIM which was better than the comparison architecture.
引用
收藏
页码：51 / 56
页数：6
相关论文
共 50 条
  • [31] Single ISAR Image Enhancement Based on Convolutional Neural Network
    Qi, Mingrui
    Chen, Chen
    Yang, Qingwei
    [J]. SEVENTH ASIA PACIFIC CONFERENCE ON OPTICS MANUFACTURE (APCOM 2021), 2022, 12166
  • [32] Text Detection in Low Resolution Scene Images Using Convolutional Neural Network
    Risnumawan, Anhar
    Sulistijono, Indra Adji
    Abawajy, Jemal
    [J]. RECENT ADVANCES ON SOFT COMPUTING AND DATA MINING, 2017, 549 : 366 - 375
  • [33] Improved image super-resolution algorithm based on convolutional neural network
    Xiao J.
    Liu E.
    Zhu L.
    Lei J.
    [J]. 1600, Chinese Optical Society (37):
  • [34] Image Synthesis using Convolutional Neural Network
    Bhat, Ganesh
    Dharwadkar, Shrikant
    Reddy, N. V. Subba
    Shivaprasad, G.
    [J]. 2017 2ND IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT), 2017, : 689 - 691
  • [35] Sandwich Convolutional Neural Network for Hyperspectral Image Classification Using Spectral Feature Enhancement
    Gao, Hongmin
    Chen, Zhonghao
    Li, Chenming
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 3006 - 3015
  • [36] Image Denoising using Convolutional Neural Network
    Mehmood, Asif
    [J]. PATTERN RECOGNITION AND TRACKING XXXI, 2020, 11400
  • [37] Computed Tomography Image Enhancement Using 3D Convolutional Neural Network
    Li, Meng
    Shen, Shiwen
    Gao, Wen
    Hsu, William
    Cong, Jason
    [J]. DEEP LEARNING IN MEDICAL IMAGE ANALYSIS AND MULTIMODAL LEARNING FOR CLINICAL DECISION SUPPORT, DLMIA 2018, 2018, 11045 : 291 - 299
  • [38] Evaluation of realistic blurring image quality by using a shallow convolutional neural network
    Li, Yaoqing
    Wang, Zhaoyang
    Dai, Guangzhe
    Wu, Shibin
    Yu, Shaode
    Xie, Yaoqin
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION (IEEE ICIA 2017), 2017, : 853 - 857
  • [39] Image Fusion and Super-Resolution with Convolutional Neural Network
    Zhong, Jinying
    Yang, Bin
    Li, Yuehua
    Zhong, Fei
    Chen, Zhongze
    [J]. PATTERN RECOGNITION (CCPR 2016), PT II, 2016, 663 : 78 - 88
  • [40] Convolutional Neural Network for Smoke Image Super-Resolution
    Liu, Maoshen
    Gu, Ke
    Qiao, Junfei
    [J]. PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND APPLICATION ENGINEERING (CSAE2018), 2018,
12345