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

页码：51 / 56

页数：6

共 50 条

[41] Efficient document-image super-resolution using convolutional neural network [J].

Ram Krishna Pandey ;

A G Ramakrishnan .

Sādhanā, 2018, 43

[42] Efficient document-image super-resolution using convolutional neural network [J].

Pandey, Ram Krishna ;

Ramakrishnan, A. G. .

SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2018, 43 (02)

[43] Light-Field Image Super-Resolution Using Convolutional Neural Network [J].

Yoon, Youngjin ;

Jeon, Hae-Gon ;

Yoo, Donggeun ;

Lee, Joon-Young ;

Kweon, In So .

IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (06) :848-852

[44] High-resolution CT Image Retrieval Using Sparse Convolutional Neural Network [J].

Lei, Yang ;

Xu, Dong ;

Zhou, Zhengyang ;

Higgins, Kristin ;

Dong, Xue ;

Liu, Tian ;

Shim, Hyunsuk ;

Mao, Hui ;

Curran, Walter J. ;

Yang, Xiaofeng .

MEDICAL IMAGING 2018: PHYSICS OF MEDICAL IMAGING, 2018, 10573

[45] Image super-resolution using convolutional neural network with symmetric skip connections [J].

Zou, Yan ;

Xiao, Fujun ;

Zhang, Linfei ;

Chen, Qian ;

Wang, Bowen ;

Hu, Yan .

FOURTH INTERNATIONAL CONFERENCE ON PHOTONICS AND OPTICAL ENGINEERING, 2021, 11761

[46] Histopathological Breast-Image Classification With Image Enhancement by Convolutional Neural Network [J].

Abdullah-Al Nahid ;

Bin Ali, Ferdous ;

Kong, Yinan .

2017 20TH INTERNATIONAL CONFERENCE OF COMPUTER AND INFORMATION TECHNOLOGY (ICCIT), 2017,

[47] SKETCHPPNET: A JOINT PIXEL AND POINT CONVOLUTIONAL NEURAL NETWORK FOR LOW RESOLUTION SKETCH IMAGE RECOGNITION [J].

Zhu, Xianyi ;

Xiao, Yi ;

Zheng, Yan ;

Tan, Guanghua ;

Zhou, Shizhe .

2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, :2253-2257

[48] Modality Conversion from Pathological Image to Ultrasonic Image Using Convolutional Neural Network [J].

Ohnishi, Takashi ;

Kashio, Shu ;

Ogawa, Takuya ;

Ito, Kazuyo ;

Makhanov, Stanislav S. ;

Yamaguchi, Tadashi ;

Iwadate, Yasuo ;

Haneishi, Hideaki .

COMPUTATIONAL PATHOLOGY AND OPHTHALMIC MEDICAL IMAGE ANALYSIS, 2018, 11039 :103-111

[49] Sub-Pixel Convolutional Neural Network for Image Super-Resolution Reconstruction [J].

Shao, Guifang ;

Sun, Qiao ;

Gao, Yunlong ;

Zhu, Qingyuan ;

Gao, Fengqiang ;

Zhang, Junfa .

ELECTRONICS, 2023, 12 (17)

[50] Attentive Inception Module based Convolutional Neural Network for Image Enhancement [J].

Bhattacharya, Purbaditya ;

Zoelzer, Udo .

2020 DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA), 2020,

← 1 2 3 4 5 →