• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• 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.

• Journal of KIISE:Software and Applications
• /
• v.34 no.3
• /
• pp.266-274
• /
• 2007

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on top-down machine learning and recursive error back-projection. A face is represented by a linear combination of prototypes of shape and that of texture. With the shape and texture information of each pixel in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those that of texture by solving least square minimizations. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. In addition, a recursive error back-projection procedure is applied to improve the reconstruction accuracy of high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution images captured at a distance.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.2
• /
• 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.

• Korean Journal of Remote Sensing
• /
• v.16 no.1
• /
• pp.87-98
• /
• 2000

Image merging techniques have been developed to integrate the advantage of different data type. The objective of this study is to present the optimal method for merging high spatial resolution panchromatic image, such as the latest commercial satellite data, and low spatial resolution mulitspectral images. For this study, a set of 2m resolution panchromatic and 8m resolution mulitspectral data were simulated by using airborne mulitspectral data. Five merging methods of MWD, IHS, PCA, HPF, and CN were applied to produce four bands of high spatial resolution mulitspectral data. Merging results were evaluated by visual interpretation, image statistics, semivariogram, and spectral characteristics. From the aspects of both spatial resolution and spectral information, the wavelet-based MWD merging method have shown very similar results compared with the original data used for the merging.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.04a
• /
• 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.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• 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.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• 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.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.657-660
• /
• 2009

An image interpolation is a basis technique for various image processing and is required to minimize approaches for image quality deterioration. In this paper, we propose an improved bilinear interpolation using loss information estimation. In the proposed algorithm, we estimate loss information of low resolution image using down-sampling and interpolation of acquisition low resolution. The estimated loss information is utilized interpolated image, and it decrease image quality deterioration. Our experiments obtained the average PSNR 0.97~1.79dB which is improved results better than conventional method for sensitive image quality. Also, subjective image quality with edge region is more clearness. The proposed method may be helpful for applications in various multimedia systems such as image resolution enhancement and image restoration.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.1
• /
• 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.