東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

CNN-Based Single Image Super-Resolut...

Bayram, Samet.

FindBook

Google Book

Amazon

博客來

CNN-Based Single Image Super-Resolution Network and Biomedical Image Applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	CNN-Based Single Image Super-Resolution Network and Biomedical Image Applications./
作者:	Bayram, Samet.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
面頁冊數:	55 p.
附註:	Source: Masters Abstracts International, Volume: 57-05.
Contained By:	Masters Abstracts International57-05(E).
標題:	Electrical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10745822
ISBN:	9780355762617

CNN-Based Single Image Super-Resolution Network and Biomedical Image Applications.
Bayram, Samet.

CNN-Based Single Image Super-Resolution Network and Biomedical Image Applications. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 55 p.

Source: Masters Abstracts International, Volume: 57-05.

Thesis (M.S.)--University of Delaware, 2018.

In this thesis, we propose a convolutional neural network (CNN) based single image super-resolution network model with sparse representation by combining three existing state-of-the-art methods SC, SRCNN and SCN models with a modified pre-processing step. Firstly, standard gaussian box filter is applied to test image, which is a low-resolution image (LR), to remove low-frequency noises. After that, the given low-resolution image is up-scaled by bicubic interpolation method to the same size with desired output high-resolution image (HR). Secondly, a convolutional neural network based dictionary learning method is employed to train input low-resolution image to obtain LR image patches. Also, a rectified linear unit (ReLU) thresholds the output of the CNN to get a better LR image dictionary. Thirdly, to get optimal sparse parameters, we adopted Learned Iterative Shrinkage and Thresholding Algorithm (LISTA) network to train LR image patches. LISTA is a sparse-based network that generates sparse coefficients from each LR image patches. Finally, in the reconstruction step, corresponding high-resolution image patches are obtained by multiplying low-resolution image patches with optimal sparse coefficients. Then corresponding high-resolution image patches are combined to get final HR image. The experimental results show that our proposed method demonstrates outstanding performance compare to other state-of-the-art. The proposed method generates clear and better-detailed output high-resolution images since it is important in real life applications. The advantage of the proposed method is to combine convolutional neural network based dictionary learning and sparse-based network training with better pre-processing to create efficient and flexible single-image-super-resolution network.

ISBN: 9780355762617Subjects--Topical Terms:

649834
Electrical engineering.

CNN-Based Single Image Super-Resolution Network and Biomedical Image Applications.
LDR:02774nmm a2200313 4500 001 2165112
005 20181129115239.5
008 190424s2018 ||||||||||||||||| ||eng d
020 $a 9780355762617
035 $a (MiAaPQ)AAI10745822
035 $a (MiAaPQ)udel:13225
035 $a AAI10745822
040 $a MiAaPQ $c MiAaPQ
100 1 $a Bayram, Samet. $3 3353175
245 1 0 $a CNN-Based Single Image Super-Resolution Network and Biomedical Image Applications.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 55 p.
500 $a Source: Masters Abstracts International, Volume: 57-05.
500 $a Advisers: Kenneth Eugene Barner; Mark Mirotznik.
502 $a Thesis (M.S.)--University of Delaware, 2018.
520 $a In this thesis, we propose a convolutional neural network (CNN) based single image super-resolution network model with sparse representation by combining three existing state-of-the-art methods SC, SRCNN and SCN models with a modified pre-processing step. Firstly, standard gaussian box filter is applied to test image, which is a low-resolution image (LR), to remove low-frequency noises. After that, the given low-resolution image is up-scaled by bicubic interpolation method to the same size with desired output high-resolution image (HR). Secondly, a convolutional neural network based dictionary learning method is employed to train input low-resolution image to obtain LR image patches. Also, a rectified linear unit (ReLU) thresholds the output of the CNN to get a better LR image dictionary. Thirdly, to get optimal sparse parameters, we adopted Learned Iterative Shrinkage and Thresholding Algorithm (LISTA) network to train LR image patches. LISTA is a sparse-based network that generates sparse coefficients from each LR image patches. Finally, in the reconstruction step, corresponding high-resolution image patches are obtained by multiplying low-resolution image patches with optimal sparse coefficients. Then corresponding high-resolution image patches are combined to get final HR image. The experimental results show that our proposed method demonstrates outstanding performance compare to other state-of-the-art. The proposed method generates clear and better-detailed output high-resolution images since it is important in real life applications. The advantage of the proposed method is to combine convolutional neural network based dictionary learning and sparse-based network training with better pre-processing to create efficient and flexible single-image-super-resolution network.
590 $a School code: 0060.
650 4 $a Electrical engineering. $3 649834
650 4 $a Medical imaging. $3 3172799
650 4 $a Artificial intelligence. $3 516317
690 $a 0544
690 $a 0574
690 $a 0800
710 2 $a University of Delaware. $b Department of Electrical and Computer Engineering. $3 1020805
773 0 $t Masters Abstracts International $g 57-05(E).
790 $a 0060
791 $a M.S.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10745822