• Journal of Biomedical Engineering Research
• /
• v.32 no.3
• /
• pp.257-263
• /
• 2011

Sparse-view CT imaging is considered to be a solution to reduce x-ray dose of CT. Sparse-view CT imaging may have severe streak artifacts that could compromise the image qualities. We have compared quality of sparseview images reconstructed with two representative iterative reconstruction techniques, SIRT and TV-minimization, in terms of image error and edge preservation. In the comparison study, we have used the Shepp-Logan phantom image and real CT images obtained with a micro-CT. In both phantom image and real CT image tests, TV-minimization technique shows the best performance in error reduction and preserving edges. However, the excessive computation time of TV-minimization is a technical challenge for the practical use.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.439-441
• /
• 2019

Deep learning has become a powerful and robust algorithm in Artificial Intelligence. One of the most impressive forms of Deep learning tools is that of the Convolutional Neural Networks (CNN). CNN is a state-of-the-art solution for object recognition. For instance when we utilize CNN with MNIST handwritten digital dataset, mostly the result is well. Because, in MNIST dataset, all digits are centralized. Unfortunately, the real world is different from our imagination. If digits are shifted from the center, it becomes a big issue for CNN to recognize and provide result like before. To solve that issue, we have created frequency images from spatial images by a Fast Fourier Transform (FFT).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.757-770
• /
• 2022

Palmprint recognition has drawn increasingly attentions in the past decade due to its uniqueness and reliability. Traditional palmprint recognition methods usually use high-resolution images as the identification basis so that they can achieve relatively high precision. However, high-resolution images mean more computation cost in the recognition process, which usually cannot be guaranteed in mobile computing. Therefore, this paper proposes an improved low-resolution palmprint image recognition method based on residual networks. The main contributions include: 1) We introduce a channel attention mechanism to refactor the extracted feature maps, which can pay more attention to the informative feature maps and suppress the useless ones. 2) The ResStage group structure proposed by us divides the original residual block into three stages, and we stabilize the signal characteristics before each stage by means of BN normalization operation to enhance the feature channel. Comparison experiments are conducted on a public dataset provided by the Hong Kong Polytechnic University. Experimental results show that the proposed method achieve a rank-1 accuracy of 98.17% when tested on low-resolution images with the size of 12dpi, which outperforms all the compared methods obviously.

• Korean Journal of Digital Imaging in Medicine
• /
• v.5 no.1
• /
• pp.78-84
• /
• 2002

To evaluate the relative time required to perform a CT(computed tomography) examination in a filmless versus a film-based system and helical versus nonhelical studies. Time and Motion studies were performed in 175 consecutive CT examinations. Images from 85 examinations were electronically transferred to a PACS, and 90 were printed to film. The time required to obtain and electronically transfer the images or print the images to film and make the current and previous studies available to the radiologists for interpretation was recorded. The time required for a radiological technologist to complete a CT examination was reduced by 43% with the PACS compared with the film-based system and nonhelical was reduced 10-20% with helical studies. This reduction was due to the elimination of a transfer and printing, such as the printing at window or level settings. The use of PACS can result in the elimination of time tasks for the radiological technologist, resulting in marked reduction in examination time. This reduction can result in decreased cost and increased productivity in PACS operation.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.397-400
• /
• 2004

Synthetic Aperture Radar(SAR) is an active micro­wave instrument that performs high-resolution observation under almost all weather conditions. Although there are many advantages of SAR instrument, many complicated steps are involved in order to generate SAR image products. Many research and algorithms have been proposed to process radar signal and to increase the quality of SAR products. However, it is hard to find research which compare the quality of SAR products generated with different algorithms and processing methods. In our previous research, a SAR processing s/w was developed for a ground station. In addition, quality assessment procedures and their test parameters inside a SAR processor was proposed. The purpose of this paper is to evaluate the quality of SAR images generated from the developed SAR processing s/w. However, If there are no direct measurements such as radar reflector or scattering field measurement values it is difficult to compare SAR images generated with different methods. An alternative procedures and parameters for SAR image quality evaluation are presented and the problems involved in the comparison methods are discussed. Experiments based on real data have been conducted to evaluate and analyze quality of SAR images.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.3
• /
• pp.213-220
• /
• 2023

Face recognition is a very important process in video monitoring and is a type of biometric technology. It is mainly used for identification and security purposes, such as ID cards, licenses, and passports. The recognition process has many variables and is complex, so development has been slow. In this paper, we proposed a face recognition method using CNN, which has been re-examined due to the recent development of computers and algorithms, and compared with the feature comparison method, which is an existing face recognition algorithm, to verify performance. The proposed face search method is divided into a face region extraction step and a learning step. For learning, face images were standardized to 50×50 pixels, and learning was conducted while minimizing unnecessary nodes. In this paper, convolution and polling-based techniques, which are one of the deep learning technologies, were used for learning, and 1,000 face images were randomly selected from among 7,000 images of Caltech, and as a result of inspection, the final recognition rate was 98%.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.2
• /
• pp.31-40
• /
• 2012

Face recognition refers to the process of identifying individuals based on their facial features. It has recently become one of the most popular research areas in the fields of computer vision, machine learning, and pattern recognition because it spans numerous consumer applications, such as access control, surveillance, security, credit-card verification, and criminal identification. However, illumination variation on face generally cause performance degradation of face recognition systems under practical environments. Thus, this paper proposes an novel face recognition system using a fusion approach based on local binary pattern and two-dimensional principal component analysis. To minimize illumination effects, the face image undergoes the local binary pattern operation, and the resultant image are divided into two sub-images. Then, two-dimensional principal component analysis algorithm is separately applied to each sub-images. The individual scores obtained from two sub-images are integrated using a weighted-summation rule, and the fused-score is utilized to classify the unknown user. The performance evaluation of the proposed system was performed using the Yale B database and CMU-PIE database, and the proposed method shows the better recognition results in comparison with existing face recognition techniques.

• IE interfaces
• /
• v.15 no.4
• /
• pp.439-443
• /
• 2002

In this paper, we study to evaluate the relative time required to perform the CT scanning in the PACS versus a film-based system and helical versus non-helical studies. Time studies were performed in 175 consecutive CT scanning. Images from 85 examinations were electronically transferred to a PACS, and 90 were printed to film. The time required to obtain and electronically transfer the images or print the images to film and make the current and previous studies available to the radiologists for interpretation was recorded. The time required for a radiological technologist to complete a CT test was reduced by 43% with the PACS compared with the film-based system and nonhelical was reduced 10~20% with helical studies. This reduction was due to the elimination of a transfer and printing, such as the printing at window or level settings. The use of PACS can result in the elimination of time tasks for the radiological technologist, resulting in marked reduction in examination time. This reduction can result in decreased cost and increased productivity in PACS operation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.1
• /
• pp.71-80
• /
• 2011

Thresholding is important step for detecting binary change/non-change information in the unsupervised change detection. This study proposes new unsupervised change detection method using Hyperion hyperspectral images, which are expected with data increased demand. A graph is drawn with applying the range average method for the result value through pixel-based similarity measurement, and thresholding value is decided at the maximum distance point from a straight line. The proposed method is assessed in comparison with expectation-maximization algorithm, coner method, Otsu's method using synthetic images and Hyperion hyperspectral images. Throughout the results, we validated that the proposed method can be applied simply and had similar or better performance than the other methods.

• Korean Institute of Interior Design Journal
• /
• v.13 no.3
• /
• pp.162-170
• /
• 2004

The purpose of this study is to analyze the emotional color of home office and the trendy color with special comparison of office and library colors, and to suggest the harmony of color combination of home office based on the emotional color of this analytical data. this study, the Color Syntax Program, digital tool for color analysis of images is used. The results of this study are as follows. Firstly, the main color of home office images shows three color classifications of YR-Y, Y-GY, R-YR, and with relatively high ratios of YR-Y in the color of home offices, and B-PB, GY-G in offices and libraries. Secondly, from the point of emotional aspect, the trendy color of the home office can be classified into four color image categories: 'natural', 'peaceful', 'mild', and 'noble'. Under those categories this paper proposes 10 color harmony scheme that can be applied to color of home office interior design.