• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.703-712
• /
• 2019

Single image Super-Resolution (SISR) aims to generate a visually pleasing high-resolution image from its degraded low-resolution measurement. In recent years, deep learning - based super - resolution methods have been actively researched and have shown more reliable and high performance. A typical method is WaveletSRNet, which restores high-resolution images through wavelet coefficient learning based on feature maps of images. However, there are two disadvantages in WaveletSRNet. One is a big processing time due to the complexity of the algorithm. The other is not to utilize feature maps efficiently when extracting input image's features. To improve this problems, we propose an efficient single image super resolution method, named RDB-WaveletSRNet. The proposed method uses the residual dense block to effectively extract low-resolution feature maps to improve single image super-resolution performance. We also adjust appropriated growth rates to solve complex computational problems. In addition, wavelet packet decomposition is used to obtain the wavelet coefficients according to the possibility of large scale ratio. In the experimental result on various images, we have proven that the proposed method has faster processing time and better image quality than the conventional methods. Experimental results have shown that the proposed method has better image quality by increasing 0.1813dB of PSNR and 1.17 times faster than the conventional method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.2
• /
• pp.178-184
• /
• 2004

In this paper, we designed an image processing system for the high speed line-scan camera which adopts the new memory model we proposed. As a resolution and a data rate of the line-scan camera are becoming higher, the faster image processing systems are needed. But many conventional systems are not sufficient to process the image data from the line-scan camera during a very short time. We designed the memory controller which eliminates the time for transferring image data from the line-scan camera to the main memory with high-speed SRAM and has a dual-port configuration therefore the DSP can access the main memory even though the memory controller are writing the image data. The memory controller is implemented by VHDL and Xilinx SPARTAN-IIE FPGA.

• Electronics and Telecommunications Trends
• /
• v.35 no.4
• /
• pp.91-102
• /
• 2020

Recently, generative adversarial networks (GANs) is a field of research that has rapidly emerged wherein many studies conducted shows overwhelming results. Initially, this was at the level of imitating the training dataset. However, the GAN is currently useful in many fields, such as transformation of data categories, restoration of erased parts of images, copying facial expressions of humans, and creation of artworks depicting a dead painter's style. Although many outstanding research achievements have been attracting attention recently, GANs have encountered many challenges. First, they require a large memory facility for research. Second, there are still technical limitations in processing high-resolution images over 4K. Third, many GAN learning methods have a problem of instability in the training stage. However, recent research results show images that are difficult to distinguish whether they are real or fake, even with the naked eye, and the resolution of 4K and above is being developed. With the increase in image quality and resolution, many applications in the field of design and image and video editing are now available, including those that draw a photorealistic image as a simple sketch or easily modify unnecessary parts of an image or a video. In this paper, we discuss how GANs started, including the base architecture and latest technologies of GANs used in high-resolution, high-quality image creation, image and video editing, style translation, content transfer, and technology.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.343-345
• /
• 2003

This paper describes the system development for the Ground Control Point collection and management through the major coastline region in KOREA, which will collect and manage the ground control point based on high resolution satellite image database. The module of this system is following 1) GCP/Coarstline research plan module 2) GCP/Coarstline ground collection module 3) GCP/Coarstline post processing module Our team developed the core components of ‘High Resolution Satellite Image Processing Technique’ project, and this system, among applications of our project, is constructed to apply to practical use. In this application, you will also see how to apply core components of our project.

• Journal of Korea Multimedia Society
• /
• v.14 no.11
• /
• pp.1392-1400
• /
• 2011

In most digital imaging applications, high-resolution images or videos are usually desired for later image processing and analysis. The image signal obtained from general imaging system occurs image degradation during the process of image acquirement caused by the optics, physical constraints and the atmosphere effects. Super-resolution reconstruction, one of the solution to address this problem, is image reconstruction technique that produces a high-resolution image from several low-resolution frames in video sequences. In this paper, we propose an improved super-resolution method using Projection onto Convex Sets (POCS) method based on Shift & Add (S&A). The image using conventional algorithms is sensitive to noise. To solve this problem, we propose a fusion algorithm of S&A and POCS. Also we solve the problem using BLPF (Butterworth Low-pass Filter) in frequency domain as optical blur. Our method is robust to noise and has sharpness enhancement ability. Experimental results show that the proposed super-resolution method has better resolution enhancement performance than other super-resolution methods.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.4
• /
• pp.469-478
• /
• 1994

In this paper, a high speed, high resolution information processing digital- analog converter was designed for high definition color graphic, digital image signal processing, HDTV. For high speed operation, matrix type current cell array, latch which is not use pipelined, and two dimensional structure decoder using transmission gate were designed. It is adopted to fast-conversion, low-power implementation and exhibited high performance at linearity and accuracy. To reduce silicon area and to maintain resolution, current cell array composed of weighted and non-weighted current cells. In this paper, deglitching current cell design for high accuracy, new switching algorithm assert to reduce switching error. It's This circuit dissipates 130W with a 5-V power supply, and operate above 100MHz with 10 bit resolution.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.10a
• /
• pp.763-764
• /
• 2013

A three-dimensional image capturing device and its signal processing algorithm and apparatus are presented. Three dimensional information is one of emerging differentiators that provides consumers with more realistic and immersive experiences in user interface, game, 3D-virtual reality, and 3D display. It has the depth information of a scene together with conventional color image so that full-information of real life that human eyes experience can be captured, recorded and reproduced. 20 Mega-Hertz-switching high speed image shutter device for 3D image capturing and its application to system prototype are presented[1,2]. For 3D image capturing, the system utilizes Time-of-Flight (TOF) principle by means of 20MHz high-speed micro-optical image modulator, so called 'optical resonator'. The high speed image modulation is obtained using the electro-optic operation of the multi-layer stacked structure having diffractive mirrors and optical resonance cavity which maximizes the magnitude of optical modulation[3,4]. The optical resonator is specially designed and fabricated realizing low resistance-capacitance cell structures having small RC-time constant. The optical shutter is positioned in front of a standard high resolution CMOS image sensor and modulates the IR image reflected from the object to capture a depth image (Figure 1). Suggested novel optical resonator enables capturing of a full HD depth image with depth accuracy of mm-scale, which is the largest depth image resolution among the-state-of-the-arts, which have been limited up to VGA. The 3D camera prototype realizes color/depth concurrent sensing optical architecture to capture 14Mp color and full HD depth images, simultaneously (Figure 2,3). The resulting high definition color/depth image and its capturing device have crucial impact on 3D business eco-system in IT industry especially as 3D image sensing means in the fields of 3D camera, gesture recognition, user interface, and 3D display. This paper presents MEMS-based optical resonator design, fabrication, 3D camera system prototype and signal processing algorithms.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.417-420
• /
• 2006

In these days, mobile application dealing with information contents on mobile or handheld devices such as mobile communicator, PDA or WAP device face the most important industrial needs. The motivation of this study is the design and implementation of mobile application using high resolution satellite imagery, large-sized image data set. Although major advantages of mobile devices are portability and mobility to users, limited system resources such as small-sized memory, slow CPU, low power and small screen size are the main obstacles to developers who should handle a large volume of geo-based 3D model. Related to this, the previous works have been concentrated on GIS-based location awareness services on mobile; however, the mobile 3D terrain model, which aims at this study, with the source data of DEM (Digital Elevation Model) and high resolution satellite imagery is not considered yet, in the other mobile systems. The main functions of 3D graphic processing or pixel pipeline in this prototype are implemented with OpenGL|ES (Embedded System) standard API (Application Programming Interface) released by Khronos group. In the developing stage, experiments to investigate optimal operation environment and good performance are carried out: TIN-based vertex generation with regular elevation data, image tiling, and image-vertex texturing, text processing of Unicode type and ASCII type.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.3
• /
• pp.105-111
• /
• 2014

Image resolution enhancement is a technique to generate high-resolution image through improving resolution of low-resolution obtained image. It is important to estimate correctly missing pixel value in low-resolution obtained image for image resolution enhancement. In this paper, multiple shortfall estimation method for image resolution enhancement is proposed. The proposed method estimate separate multiple shortfall by predictive degradation-restoration processing in sub-images of obtained image, and generate result image combining the estimated shortfall and interpolated obtained-image. Lastly, final reconstruction image is generated by deblurring of the result image. The experimental results demonstrate that the proposed method has the best results of all compared methods in objective image quality index: PSNR, SSIM, and FSIM. The quality of reconstructed image is superior to all compared methods, and the proposed method has better lower computational complexity than compared methods. The proposed method can be useful for image resolution enhancement.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.3
• /
• pp.240-248
• /
• 2013

In this paper, we propose a super-resolution algorithm using an adaptive weighted interpolation(AWI) and discrete wavelet transform(DWT). In general, super-resolution algorithms for single-image, probability based operations have been used for searching high-frequency components. Consequently, the complexity of the algorithm is increased and it causes the increase of processing time. In the proposed algorithm, we first find high-frequency sub-bands by using DWT. Then we apply an AWI to the obtained high-frequency sub-bands to make them have the same size as the input image. Now, the interpolated high-frequency sub-bands and input image are properly combined and perform the inverse DWT. For the experiments, we use the down-sampled version of the original image($512{\times}512$) as a test image($256{\times}256$). Through experiment, we confirm the improved efficiency of the proposed algorithm comparing with interpolation algorithms and also save the processing time comparing with the probability based algorithms even with the similar performance.