• International Journal of Computer Science & Network Security
• /
• 제21권11호
• /
• pp.17-22
• /
• 2021

Recently, image super-resolution techniques used in convolutional neural networks (CNN) have led to remarkable performance in the research area of digital image processing applications and computer vision tasks. Convolutional layers stacked on top of each other can design a more complex network architecture, but they also use more memory in terms of the number of parameters and introduce the vanishing gradient problem during training. Furthermore, earlier approaches of single image super-resolution used interpolation technique as a pre-processing stage to upscale the low-resolution image into HR image. The design of these approaches is simple, but not effective and insert the newer unwanted pixels (noises) in the reconstructed HR image. In this paper, authors are propose a novel single image super-resolution architecture based on synchronized depthwise separable convolution with Dense Skip Connection Block (DSCB). In addition, unlike existing SR methods that only rely on single path, but our proposed method used the synchronizes path for generating the SISR image. Extensive quantitative and qualitative experiments show that our method (SDCN) achieves promising improvements than other state-of-the-art methods.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권3호
• /
• pp.266-274
• /
• 2007

본 논문에서는 하향식 기계 학습 및 반복적 오차 역투영음 이용하여 한 장의 저해상도 얼굴 영상으로부터 고해상도 얼굴 영상을 복원하는 방법을 제안한다. 먼저 얼굴 영상을 독립된 형태 기저와 질감 기저의 선형 중첩으로 표현하고, 주어진 저해상도 얼굴 영상을 형태 기저와 질감 기저의 선형 중첩으 로 최대한 근사하게 표현할 수 있는 계수를 추정한다. 이 추정된 계수를 고해상도 얼굴 영상의 형태 기저 와 질감 기저의 선형 중첩 계수로 사용함으로써 고해상도 얼굴 영상을 복원한다. 또한, 복원된 고해상도 얼굴 영상의 정확도를 개선하기 위하여 학습 기반 오차 역투영 과정을 반복적으로 적용한다. 다양한 실험을 통하여, 제안된 방법이 저해상도 얼굴 영상으로부터 고해상도 얼굴 영상을 효과적으로 복원함을 입증하였으며, 이 방법을 사용하여 원거리 감시 시스템에서 획득된 저해상도 얼굴 영상을 고해상도 얼굴 영상으로 합성함으로써, 얼굴 인식 시스템의 성능을 높일 수 있음을 확인하였다.

• Journal of Electrical Engineering and Technology
• /
• 제10권2호
• /
• pp.659-669
• /
• 2015

Face Recognition assumes much significance in the context of security based application. Normally, high resolution images offer more details about the image and recognizing a face from a reasonably high resolution image would be easier when compared to recognizing images from very low resolution images. This paper addresses the problem of recognizing faces from a very low resolution image whose size is as low as $8{\times}8$. With the use of CCTV(Closed Circuit Television) and with other surveillance camera-based application for security purposes, the need to overcome the shortcomings with very low resolution images has been on the rise. The present day face recognition algorithms could not provide adequate performance when employed to recognize images from VLR images. Existing methods use super-resolution (SR) methods and Relation Based Super Resolution methods to construct from very low resolution images. This paper uses a learning based super resolution method to extract and construct images from very low resolution images. Experimental results show that the proposed SR algorithm based on relationship learning outperforms the existing algorithms in public face databases.

• 대한원격탐사학회지
• /
• 제16권1호
• /
• pp.87-98
• /
• 2000

상업위성에서 공급되는 고해상도영상의 활용을 증대하기 위한 영상합성에 대한 관심이 증가하고 있다. 합성에 사용된 고해상도 흑백영상과 저해상도 다중분광영상은 항공기탑재 다중분광 주사기에 의해 촬영된 네 밴드의 영상을 이용하여 모의 제작하였다. 모의 합성된 2rl 해상도의 흑백 영상과 Bnl 해상도의 네 밴드 영상에 대하여 다섯 가지 합성방법(MWD, ItIS, PCA, HPF, CN, PCA) 을 적용하였다. 합성된 영상에 대해서 원래 영상들이 가지고 있던 공간해상도와 분광정보 측면의 특성을 분석하고자, 육안판독, 통계치비교, semivariogram, 분광반사특성 등을 비교하였다. MWD 변환방법에 의하여 합성된 영상이 공간해상도 및 분광정보 측면에서 모두 합성에 사용된 원래 영상과 근접한 결과를 보였다.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 춘계학술발표회 논문집
• /
• pp.181-185
• /
• 2003

Recently, in accordance with supplying high-resolution satellite images which as IKONOS, KVR-1000, and Quick Bird, the use of satellite images have increased in the study which extraction of features from high-resolution satellite images is becoming a new research focus. In this study, using generally involves such as image segmentation, filtering and sobel operator and thinning in image processing for extraction of feature from satellite image. We apply this method to extraction of feature which need to the revision of map from high-resolution IKONOS satellite image data, we verified the capability of extraction of feature and application using satellite image and proposed a plan for the study in the future.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.481-484
• /
• 2005

Inherent opportunities on research for restoring high resolution image from low resolution images are increasing in these days. Super resolution image reconstruction is the process of combining multiple low resolution images to form a higher resolution one. To achieve super resolution reconstruction, proper observation model which is based on subpixel shift information is required. In this context, the importance of the subpixel registration cannot be estimated because subpixel shift information cannot be obtained from original image. This paper presents a regularized adaptive super resolution reconstruction method based on phase correlated subpixel registration, where the Constrained Least Squares(CLS) Restoration is adopted as a post process.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1998년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.218-224
• /
• 1998

The coefficients of variation obtained from three typical vegetation indices of eight levels of multi-spatial resolution images in urban areas were employed to identify the optimum spatial resolution in terms of maintaining information quality. These multi-spatial resolution images were prepared by degrading 1 meter simulated, 16 meter ADEOS/AVNIR, and 30 meter Landsat-TM images. Normalized Difference Vegetation Index (NDVI), Perpendicular Vegetation Index (PVI) and Soil Adjusted Ratio Vegetation Index (SARVI) were applied to reduce data redundancy and compare the characteristics of multi-spatial resolution image of vegetation indices. The threshold point on the curve of the coefficient of variation was defined as the optimum resolution level for the analysis with multi-spatial resolution image sets. Also, the results from the image segmentation approach of region growing to extract man-made features were compared with these multi-spatial resolution image sets.

• 전자공학회논문지B
• /
• 제33B권8호
• /
• pp.81-95
• /
• 1996

In this paper, we propose a motio estiamtion algorithm using low-resolution quantization to reduce the computation of the full search algorithm. The proposed algorithm consists of the low-resolution search which determins the candidate motion vectors by comparing the low-resolution image and the full-resolution search which determines the motion vector by comparing the full-resolution image on the positions of the candidate motion vectors. The low-resolution image is generated by subtracting each pixel value in the reference block or the search window by the mean of the reference block, and by quantizing it is 2-bit resolution. The candidate motion vectors are determined by counting the number of pixels in the reference block whose quantized codes are unmatched to those in the search window. Simulation results show that the required computational cost of the proposed algorithm is reduced to 1/12 of the full search algorithm while its performance degradation is 0.03~0.12 dB.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.657-660
• /
• 2009

영상 보간법은 다양한 영상 처리를 위하여 사용되는 기반 기술로서, 보간 과정에서 발생하는 화질열화를 최소화하기 위한 연구가 활발히 진행되고 있다. 본 논문에서는 손실 정보 추정을 이용하여 개선된 양선형 보간법을 제안한다. 제안하는 방법에서는 획득된 저해상도 영상의 다운 샘플링 및 보간을 통하여 저해상도 영상 생성시 발생하는 손실 정보를 추정하고, 추정한 손실 정보를 고해상도로 보간된 영상에 적용하여 화질 열화를 최소화한다. 동일한 영상을 이용한 실험을 통해서 기존 방법들 보다 0.97~1.79dB의 PSNR이 향상된 것을 알 수 있었고, 윤곽선을 비롯한 주관적 화질 향상을 역시 확인하였다. 제안하는 방법은 영상 해상도 개선과 영상 복원을 위한 다양한 응용 환경에서 유용하게 사용될 수 있다.

• 한국인공지능학회지
• /
• 제12권1호
• /
• pp.1-6
• /
• 2024

Recently, various techniques are being applied through the development of medical AI, and research has been conducted on the application of super-resolution AI models. In this study, evaluate the results of the application of the super-resolution AI model to brain CT as the basic data for future research. Acquiring CT images of the brain, algorithm for brain and bone windowing setting, and the resolution was downscaled to 5 types resolution image based on the original resolution image, and then upscaled to resolution to create an LR image and used for network input with the original imaging. The SRCNN model was applied to each of these images and analyzed using PSNR, SSIM, Loss. As a result of quantitative index analysis, the results were the best at 256×256, the brain and bone window setting PSNR were the same at 33.72, 35.2, and SSIM at 0.98 respectively, and the loss was 0.0004 and 0.0003, respectively, showing relatively excellent performance in the bone window setting CT image. The possibility of future studies aimed image quality and exposure dose is confirmed, and additional studies that need to be verified are also presented, which can be used as basic data for the above studies.