• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.630-632
• /
• 2012

Contemporary society has evolved in the digital information age. Because of this, use of various digital images has been increased. To process these images, various digital image processing methods are used. Edge detection methods, one of those, are utilized to various areas of application such as object recognition, line detection. To detect edge, there are many methods such as Sobel, Prewitt, Laplacian. Because images which are dealt with existing methods are processed in same methods regardless the distribution of gray-level in image, edge detection property is insufficient. Therefore, In this study, to improve shortcomings of existing methods an algorithm using modified expansion mask is proposed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.253-255
• /
• 2022

Thanks to the 4th industrial revolution and the development of various communication media, technologies such as artificial intelligence and automation are being grafted into industrial sites in various fields, and accordingly, the importance of data processing is increasing. Image noise removal is a pre-processing process for image processing, and is mainly used in fields requiring high-level image processing technology. Various studies have been conducted to remove noise, but various problems arise in the process of noise removal, such as image detail preservation, texture restoration, and noise removal in a special area. In this paper, we propose a switching mask filter based on the noise intensity to preserve the detailed image information during the impulse noise removal process. The proposed filter algorithm obtains the final output by switching to the extended mask when it is determined that the density is higher than the reference value when noise is determined in the area designated as the filtering mask. Simulation was conducted to evaluate the performance of the proposed algorithm, and the performance was analyzed compared to the existing method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.4
• /
• pp.394-400
• /
• 2019

Noise removal is one of the required step in processing digital video and there are many researches to develop algorithm that fits with its purpose and environment. However, present impulse noise removal methods are lacking in its function in terms of removing noise in edge and high frequency factors. Therefore, this research has Extended range of masks depending on density to determine noise so that high frequency factors can be preserved. The range of resolution is set based on median and standard deviation of inside resolution after removing impulse noise. afterwards, those resolution within the range are calculated by adding weight to have the final output value. The suggested algorithm has an enhanced function in removing noise in various areas with many edge and high frequency factors than present methods and their functions are compared through simulation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.350-356
• /
• 2012

The tension effect on fiber Bragg gratings was analyzed and the linearity of 1.24 nm/10kpsi was obtained when Bragg wavelength was varied within 3 nm by applied tension. Using tension control method, different center wavelength fiber Bragg grating(FBG) were fabricated by only single period phase mask. These serially connected four FBGs showed the transmission spectrum of 1.5 nm linewidth as a 3 dB bandwidth which was twice that of a conventional FBG.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.7-10
• /
• 2021

최근 스마트폰과 컴퓨터 등의 비중이 커지면서 거북목 증후군의 관심사가 커졌다. 거북목 증후군은 잘못된 자세로 인해 어깨의 근육과 인대가 늘어나 통증이 생기는 증상을 의미한다. 이러한 잘못된 자세에는 대표적으로 일자목과 역c자목이 있으며 일자목은 7개의 목뼈로 이루어진 경추라인이 c자 라인에서 일직선으로 뼈의 형태가 바뀌어 디스크가 일어나 통증을 유발하는 증상이고 역c자목은 정상의 목뼈 구조를 잃어버린 형태로 곧 디스크를 보이며 고개를 드는 것이 힘드며 구부정한 자세를 취하게 되는 증상이다. 본 연구에서는 컨볼루션 신경망 (CNN) 학습 모델을 구현하여 주어진 자세가 올바른 자세인지 일자목인지 c자목인지를 진단할 수 있는 분류기를 구현하였다. 또한, 최근 코로나 사태로 인해 마스크 장착이 일상화되고 있는데, 추가 데이터를 보강하여, 마스크 착용상태에서도 적용가능한 모델로 확장하였다.

• Journal of Broadcast Engineering
• /
• v.19 no.1
• /
• pp.109-117
• /
• 2014

This paper presents a superresolution restoration technique that can restore high-resolution images from differently blurred low resolution images rather than using the motion information between low-resolution images. In order to restore the super-resolution image the rotatable aperture mask lens system is proposed. The proposed technique does not need to estimate point spread function at each frame. In addition, it does not require image registration because there is no global translational motion between low resolution images. By using a rotatable rectangular aperture, two consecutive captured images provide sufficiently exclusive information for superresolution. Therefore, the proposed method can reduce the registration error between the low-resolution image as well as the calculation amount for superresolution restoration. The existing lens system of the camera can be extended to obtain a superresolution image by only adding an rotatable rectangular aperture mask. Finally, in order to verify the performance of the proposed system, experimental results are performed. By comparing with the existing superresolution methods, the proposed method showed the significant improvements in the sense of spatial resolution.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.119-127
• /
• 2019

This paper proposes a new authentication model to solve the problem of personal information takeover and personal information theft by service providers using centralized servers for user authentication and management of personal information. The centralization issue is resolved by providing user authentication and information storage space through a decentralize platform, blockchain, and ensuring confidentiality of information through user-specific symmetric key encryption. The proposed model was implemented using the public-blockchain Ethereum and the web-based wallet extension MetaMask, and users access the Ethereum main network through the MetaMask on their browser and store their encrypted personal information in the Smart Contract. In the future, users will provide their personal information to the service provider through their Ethereum Account for the use of the new service, which will provide user authentication and personal information without subscription or a new authentication process. Service providers can reduce the costs of storing personal information and separate authentication methods, and prevent problems caused by personal information leakage.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.2
• /
• pp.475-481
• /
• 2014

As the society develops to advanced digital information times, many studies are underway about digital video processing technology areas such as image restoration. There are typical methods to restore the image which have been damaged by the impulse noise like SM(standard median) filter and CWM(center weighted median) filter. These filters show excellent noise reduction capabilities in low noise density areas, but in high noise density areas, noise reduction capabilities are not sufficient. In this paper, in order to restore the degraded images in impulse(Salt & Pepper) noise environment, the image restoration filter algorithm was suggested which expands and subdivide the mask focusing on damaged pixels. And to demonstrate the superiority of the proposed algorithm used PSNR (peak signal to noise ratio) as the standard of judgement.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.352-357
• /
• 2006

매년 도로와 주차공간의 확장보다 차량의 수가 빠르게 증가하여 그에 따라 불법 주차 관리의 어려움이 증가하고 있다. 이러한 문제점을 해결하기 위해 지능형 주차 관리 시스템이 필요하게 되었다. 본 논문에서는 획득된 차량 영상에서 수직 에지의 특징을 이용하여 번호판 영역과 개별 코드를 추출하고, 추출된 개별 코드를 퍼지 신경망 알고리즘을 제안하여 학습 및 인식한다. 본 논문에서는 차량 번호판 영역을 검출하기 위해 프리윗 마스크를 적용하여 수직 에지를 찾고, 차량 번호판의 정보를 이용하여 잡음을 제거한 후에 차량 번호판 영역을 추출한다. 추출된 차량 번호판 영역은 반복 이진화방법을 적용하여 이진화하고, 이진화된 차량 번호판 영역에 대해서 수직 분포도와 수평 분포도를 이용하여 번호판의 개별 코드를 추출한다 추출된 개별 코드는 제안된 퍼지 신경망 알고리즘을 적용하여 인식한다. 제안된 퍼지 신경망은 입력층과 중간층간의 학습 구조로는 FCM 알고리즘을 적용하고 중간층과 출력층간의 학습 구조는 Max_Min 신경망을 적용한다. 제안된 방법의 추출 및 인식 성능을 평가하기 위하여 실제 차량 영상 150장을 대상으로 실험한 결과, 기존의 차량 번호판 인식 방법보다 효율적이고 인식 성능이 개선된 것을 확인하였다.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1213-1218
• /
• 2018

Recently introduced Mask R - CNN presents a conceptually simple, flexible, general framework for instance segmentation of objects. In this paper, we propose an algorithm for efficiently searching objects of images, while creating a segmentation mask of heat generation part for an instance which is a heating element in a heat sensed image acquired from a thermal infrared camera. This method called a mask R - CNN is an algorithm that extends Faster R - CNN by adding a branch for predicting an object mask in parallel with an existing branch for recognition of a bounding box. The mask R - CNN is added to the high - speed R - CNN which training is easy and fast to execute. Also, it is easy to generalize the mask R - CNN to other tasks. In this research, we propose an infrared image detection algorithm based on R - CNN and detect heating elements which can not be distinguished by RGB images. As a result of the experiment, a heat-generating object which can not be discriminated from Mask R-CNN was detected normally.