TY - GEN
T1 - Auto coder-decoder (CODEC) model based sparse representation for image super resolution
AU - Zhang, Qieshi
AU - Gu, Liyan
AU - Cheng, Jun
AU - Wu, Xiaojun
AU - Kamata, Sei Ichiro
N1 - Funding Information:
ACKNOWLEDGMENT This research was supported by the Shenzhen Technology Project under Grant JCYJ20170413152535587, JSGG20160331185256983, JSGG20160229115709109, the Guangdong Technology Program under Grant 2016B010108010 and 2016B010125003, Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences under Grant 2014DP173025, Shenzhen Engineering Laboratory for 3D Content Generating Technologies (NO. [2017] 476), CAS Key Technology Talent Program, NSF of China (Grant no. 11772178?11372167, 11502133), Shaanxi Natural Science Foundation Project 2017JM6101, the Fundamental Research Funds for the Central Universities GK201703060.
Publisher Copyright:
© 2017 IEEE.
PY - 2018/2/22
Y1 - 2018/2/22
N2 - In our daily life, the high quality image is widely used in varieties of fields, but sometimes we cannot capture the image with idea resolution due to some influences. For solving the resolution limitation of imaging sensors, the image super resolution (SR) representation technology is widely researched. Considering the advantage of sparse representation, the dictionary learning based methods is widely studied. However, landmark atoms cannot provide the representations of images, since the general feature extractors is universally applicable in feature extraction. To overcome the drawbacks, an auto coder-decoder (CODEC) model is proposed to extract representative features from low resolution (LR) images. The experimental results indicate the proposed method can obtain better effect than other methods.
AB - In our daily life, the high quality image is widely used in varieties of fields, but sometimes we cannot capture the image with idea resolution due to some influences. For solving the resolution limitation of imaging sensors, the image super resolution (SR) representation technology is widely researched. Considering the advantage of sparse representation, the dictionary learning based methods is widely studied. However, landmark atoms cannot provide the representations of images, since the general feature extractors is universally applicable in feature extraction. To overcome the drawbacks, an auto coder-decoder (CODEC) model is proposed to extract representative features from low resolution (LR) images. The experimental results indicate the proposed method can obtain better effect than other methods.
KW - Auto Cdoer-Decoder (CODEC) Model
KW - Data-Dependent Feature Extractor (DDFE)
KW - Sparse Representation
KW - Super Resolution (SR)
UR - http://www.scopus.com/inward/record.url?scp=85047635693&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047635693&partnerID=8YFLogxK
U2 - 10.1109/CISP-BMEI.2017.8301950
DO - 10.1109/CISP-BMEI.2017.8301950
M3 - Conference contribution
AN - SCOPUS:85047635693
T3 - Proceedings - 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
SP - 1
EP - 6
BT - Proceedings - 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
A2 - Qiu, Song
A2 - Liu, Hongying
A2 - Sun, Li
A2 - Wang, Lipo
A2 - Li, Qingli
A2 - Zhou, Mei
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
Y2 - 14 October 2017 through 16 October 2017
ER -