KR101427854B1 - 단일 영상의 초고해상도 영상 복원 장치 및 방법 - Google Patents
단일 영상의 초고해상도 영상 복원 장치 및 방법 Download PDFInfo
- Publication number
- KR101427854B1 KR101427854B1 KR1020120105926A KR20120105926A KR101427854B1 KR 101427854 B1 KR101427854 B1 KR 101427854B1 KR 1020120105926 A KR1020120105926 A KR 1020120105926A KR 20120105926 A KR20120105926 A KR 20120105926A KR 101427854 B1 KR101427854 B1 KR 101427854B1
- Authority
- KR
- South Korea
- Prior art keywords
- image
- resolution image
- resolution
- low
- patch
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000014509 gene expression Effects 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000002457 bidirectional effect Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005293 physical law Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
Description
도 2 및 3은 본 발명의 일 실시예에 따른 초고해상도 영상 복원 방법을 나타낸 흐름도이다.
Claims (12)
- 저해상도의 영상을 입력받는 단계;
상기 단계에서 입력된 상기 영상을 희소 표현법을 이용하여 복원하는 단계;
상기 단계에서 복원된 상기 영상을 양방향 필터를 이용하여 전처리하는 단계; 및
상기 단계에서 전처리된 상기 영상에 역투영을 반복적으로 실행하여 초고해상도로 복원하는 단계를 포함하고,
상기 전처리하는 단계는 도메인 필터와 레인지 필터를 이용하여 상기 고해상도 영상의 노이즈를 제거하고 에지를 강화하고,
상기 전처리 단계에서 양방향 필터에 의해 노이즈가 제거되고 에지가 강화된 영상은
으로 표현되는 초고해상도 영상 복원 방법(여기서, H는 입력영상, h는 결과 영상, c(χ,ξ)는 χ와 ξ의 기하학적 근접 정도, s(H(χ),H(ξ))는 χ와ξ의 픽셀값의 광학적 유사도, 상수 κ는 임). - 제 1 항에 있어서,
상기 희소 표현법을 이용하여 복원하는 단계는,
상기 단계에서 입력받은 상기 영상의 패치의 희소 계수 벡터 α산출하는 단계; 및
상기 희소 계수 벡터 α를 이용하여 고해상도 영상 패치를 생성하는 단계를 포함하는 초고해상도 영상 복원 방법. - 제 3 항에 있어서,
상기 영상의 특징을 뽑는 함수는 CBP(Centralized Binary Pattern) 방식을 이용하는 초고해상도 영상 복원 방법. - 제 4 항에 있어서,
상기 CBP 방식은 중앙값을 중심으로 4방향(0°, 45°, 90°, 135°) 픽셀들의 차이 값과 전체 평균과 중앙값과의 차이값을 특징 벡터로 하는 초고해상도 영상 복원 방법. - 삭제
- 삭제
- 삭제
- 삭제
- 삭제
- 삭제
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020120105926A KR101427854B1 (ko) | 2012-09-24 | 2012-09-24 | 단일 영상의 초고해상도 영상 복원 장치 및 방법 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020120105926A KR101427854B1 (ko) | 2012-09-24 | 2012-09-24 | 단일 영상의 초고해상도 영상 복원 장치 및 방법 |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20140040322A KR20140040322A (ko) | 2014-04-03 |
KR101427854B1 true KR101427854B1 (ko) | 2014-08-07 |
Family
ID=50650532
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020120105926A Active KR101427854B1 (ko) | 2012-09-24 | 2012-09-24 | 단일 영상의 초고해상도 영상 복원 장치 및 방법 |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101427854B1 (ko) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101638022B1 (ko) * | 2015-09-21 | 2016-07-12 | 광주과학기술원 | 다수의 렌즈를 이용한 촬상장치 |
KR101692428B1 (ko) * | 2016-04-25 | 2017-01-03 | 광주과학기술원 | 다수의 렌즈를 이용한 촬상장치 |
KR20200026549A (ko) | 2018-09-03 | 2020-03-11 | 인천대학교 산학협력단 | 에지 컴퓨팅용 초고해상도 영상을 복원하기 위한 초고해상도 영상 복원 장치 및 방법 |
KR102132690B1 (ko) | 2019-01-30 | 2020-07-13 | 인천대학교 산학협력단 | 초고해상도 영상 복원 시스템 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102077215B1 (ko) | 2018-04-06 | 2020-02-13 | 경희대학교 산학협력단 | 국부 이진 패턴 분류 및 선형 매핑을 이용한 초해상화 방법 |
CN116109487B (zh) * | 2023-03-04 | 2024-08-20 | 淮阴师范学院 | 一种基于细节保持的图像超分辨率复原方法 |
CN116385318B (zh) * | 2023-06-06 | 2023-10-10 | 湖南纵骏信息科技有限公司 | 一种基于云桌面的图像画质增强方法及系统 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120103878A (ko) * | 2011-03-11 | 2012-09-20 | 이화여자대학교 산학협력단 | 영상에서의 잡음 제거 방법 |
-
2012
- 2012-09-24 KR KR1020120105926A patent/KR101427854B1/ko active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120103878A (ko) * | 2011-03-11 | 2012-09-20 | 이화여자대학교 산학협력단 | 영상에서의 잡음 제거 방법 |
Non-Patent Citations (4)
Title |
---|
Centralized Binary Patterns Embedded with Image Euclidean Distance for Facial Expression Recognition, ICNC. Fourth International Conference on,18-20 Oct. 2008 * |
Centralized Binary Patterns Embedded with Image Euclidean Distance for Facial Expression Recognition, ICNC. Fourth International Conference on,18-20 Oct. 2008* |
Image Super-Resolution as Sparse Representation of Raw Image Patches, CVPR. IEEE Conference on, 23-28 June 2008 * |
Image Super-Resolution as Sparse Representation of Raw Image Patches, CVPR. IEEE Conference on, 23-28 June 2008* |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101638022B1 (ko) * | 2015-09-21 | 2016-07-12 | 광주과학기술원 | 다수의 렌즈를 이용한 촬상장치 |
WO2017052203A1 (ko) * | 2015-09-21 | 2017-03-30 | 광주과학기술원 | 다수의 렌즈를 이용한 촬상장치 |
US10605962B2 (en) | 2015-09-21 | 2020-03-31 | Gwangju Institute Of Science And Technology | Imaging device using plurality of lenses |
KR101692428B1 (ko) * | 2016-04-25 | 2017-01-03 | 광주과학기술원 | 다수의 렌즈를 이용한 촬상장치 |
KR20200026549A (ko) | 2018-09-03 | 2020-03-11 | 인천대학교 산학협력단 | 에지 컴퓨팅용 초고해상도 영상을 복원하기 위한 초고해상도 영상 복원 장치 및 방법 |
KR102132690B1 (ko) | 2019-01-30 | 2020-07-13 | 인천대학교 산학협력단 | 초고해상도 영상 복원 시스템 |
Also Published As
Publication number | Publication date |
---|---|
KR20140040322A (ko) | 2014-04-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101427854B1 (ko) | 단일 영상의 초고해상도 영상 복원 장치 및 방법 | |
Zhang et al. | A super-resolution reconstruction algorithm for surveillance images | |
Starck et al. | The undecimated wavelet decomposition and its reconstruction | |
Zhang et al. | Image super-resolution based on structure-modulated sparse representation | |
Vekkot et al. | A novel architecture for wavelet based image fusion | |
CN109360157B (zh) | 基于tv和小波正则化的空间变化模糊图像复原方法 | |
KR101829287B1 (ko) | 비부표본 윤곽선 변환의 적외선 영상 초고해상도 방법 및 장치 | |
Thapa et al. | A performance comparison among different super-resolution techniques | |
Makwana et al. | Single image super-resolution via iterative back projection based Canny edge detection and a Gabor filter prior | |
Zhao et al. | Single depth image super-resolution with multiple residual dictionary learning and refinement | |
Yoshikawa et al. | Super resolution image reconstruction using total variation regularization and learning-based method | |
Sarmadi et al. | A new approach in single image super resolution | |
He et al. | A Hybrid Frequency-Spatial Domain Model for Sparse Image Reconstruction in Scanning Transmission Electron Microscopy | |
Wang et al. | Super-resolution image with estimated high frequency compensated algorithm | |
Sreeja et al. | Single image super-resolution based on compressive sensing and TV minimization sparse recovery for remote sensing images | |
Nawaz et al. | Variational regularization for multi-channel image denoising | |
Lukes et al. | Objective image quality assessment of multiframe super-resolution methods | |
Kim et al. | Super resolution reconstruction based on block matching and three‐dimensional filtering with sharpening | |
Jiang et al. | Super-resolution reconstruction based on structure tensor's eigenvalue and classification dictionary | |
Shuai et al. | Application of Edge Detection for Enhancing Object Boundary Clarity in Satellite Image Super-Resolution | |
Sharma et al. | An Iterative Block Image Compressive Sensing Method for Hybrid TV Image De-Noising | |
Quan | Image Denoising of Gaussian and Poisson Noise Based on Wavelet Thresholding | |
Vardar | Deep Learning Methods for Blind Super Resolution Using Self-Attention Transformers and Degradation Estimations | |
Silva et al. | Multi-frame super-resolution for mixed Gaussian and impulse noise based on blind inpainting | |
Alvarez et al. | Multi-channel reconstruction of video sequences from low-resolution and compressed observations |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
PA0109 | Patent application |
Patent event code: PA01091R01D Comment text: Patent Application Patent event date: 20120924 |
|
PA0201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
PE0902 | Notice of grounds for rejection |
Comment text: Notification of reason for refusal Patent event date: 20131028 Patent event code: PE09021S01D |
|
PG1501 | Laying open of application | ||
PE0701 | Decision of registration |
Patent event code: PE07011S01D Comment text: Decision to Grant Registration Patent event date: 20140731 |
|
GRNT | Written decision to grant | ||
PR0701 | Registration of establishment |
Comment text: Registration of Establishment Patent event date: 20140801 Patent event code: PR07011E01D |
|
PR1002 | Payment of registration fee |
Payment date: 20140801 End annual number: 3 Start annual number: 1 |
|
PG1601 | Publication of registration | ||
FPAY | Annual fee payment |
Payment date: 20170628 Year of fee payment: 4 |
|
PR1001 | Payment of annual fee |
Payment date: 20170628 Start annual number: 4 End annual number: 4 |
|
PR1001 | Payment of annual fee |
Payment date: 20180622 Start annual number: 5 End annual number: 5 |
|
FPAY | Annual fee payment |
Payment date: 20190701 Year of fee payment: 6 |
|
PR1001 | Payment of annual fee |
Payment date: 20190701 Start annual number: 6 End annual number: 6 |
|
PR1001 | Payment of annual fee |
Payment date: 20200701 Start annual number: 7 End annual number: 7 |
|
PR1001 | Payment of annual fee |
Payment date: 20210623 Start annual number: 8 End annual number: 8 |
|
PR1001 | Payment of annual fee |
Payment date: 20220621 Start annual number: 9 End annual number: 9 |
|
PR1001 | Payment of annual fee |
Payment date: 20230703 Start annual number: 10 End annual number: 10 |
|
PR1001 | Payment of annual fee |
Payment date: 20240723 Start annual number: 11 End annual number: 11 |