• The KIPS Transactions:PartD
• /
• v.15D no.4
• /
• pp.581-588
• /
• 2008

Old films or photographs usually have damages from physical or chemical effects, and the damage and digitalization make stain, scratch, scribbling, noise, and digital drop out in frames. Damages include global damage and local damage, and it is well known that local damage restoration is a main factor for improving image quality. Previous researches have focused on impairment localization (esp. for line scratch impairments) and restoration techniques for line scratch, dirt, blob, and intentional scratch. Inpainting is a key technique using partial derivatives to restore damages in images. It does not show good quality for the complex images because it is based on finite order for partial derivatives, and it takes much time complexity. In this paper, we present a modified inpainting scheme, where we use Sobel edge operator's and angle to compute isophotes, and compare our scheme with Bertalmio's scheme. We experiment our scheme with two old Korean films, and Simulation results show that our scheme requires smaller time complexity than Bertalmio's scheme with comparable reconstructed image quality.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.1019-1022
• /
• 2019

최근의 영상 처리 분야는 딥러닝 기법들의 성능이 입증됨에 따라 다양한 분야에서 이와 같은 기법들을 활용해 영상에 대한 분류, 분석, 검출 등을 수행하려는 시도가 활발하다. 그중에서도 의료 진단 보조 역할을 할 수 있는 의료 영상 분석 소프트웨어에 대한 기대가 증가하고 있는데, 본 연구에서는 캡슐내시경 영상에 주목하였다. 캡슐내시경은 주로 소장 촬영을 목표로 하며 식도부터 대장까지 약 8~10시간 동안 촬영된다. 이로 인해 CT, MR, X-ray와 같은 다른 의료 영상과 다르게 하나의 데이터 셋이 10~15만 장의 이미지를 갖는다. 일반적으로 캡슐내시경 영상을 판독하는 순서는 위장관 교차점(Z-Line, 유문판, 회맹판)을 기준으로 위장관 랜드마크(식도, 위, 소장, 대장)를 구분한 뒤, 각 랜드마크 별로 병변 정보를 찾아내는 방식이다. 그러나 워낙 방대한 영상 데이터를 가지기 때문에 의사 혹은 의료 전문가가 영상을 판독하는데 많은 시간과 노력이 소모되고 있다. 본 논문의 목적은 캡슐내시경 영상의 판독에서 모든 환자에 대해 공통으로 수행되고, 판독하는 데 많은 시간을 차지하는 위장관 랜드마크를 찾는 것에 있다. 이를 위해, 위장관 랜드마크를 식별할 수 있는 CNN 학습 모델을 설계하였으며, 더욱 효과적인 학습을 위해 전처리 과정으로 학습에 방해가 되는 학습 노이즈 영상들을 제거하고 위장관 랜드마크 별 특징 분석을 진행하였다. 총 8명의 환자 데이터를 가지고 학습된 모델에 대해 평가 및 검증을 진행하였는데, 무작위로 환자 데이터를 샘플링하여 학습한 모델을 평가한 결과, 평균 정확도가 95% 가 확인되었으며 개별 환자별로 교차 검증 방식을 진행한 결과 평균 정확도 67% 가 확인되었다.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.132-142
• /
• 2021

The purpose of this study is to present an effective methodology that can measure heart rate, heart rate variability, oxygen saturation, respiration rate, mental stress level, and blood pressure using mobile front camera that can be accessed most in real life. Face recognition was performed in real-time using Blaze Face to acquire facial image data, and the forehead was designated as ROI (Region Of Interest) using feature points of the eyes, nose, and mouth, and ears. Representative values for each channel of the ROI were generated and aligned on the time axis to measure vital signs. The vital signs measurement method was based on Fourier transform, and noise was removed and filtered according to the desired vital signs to increase the accuracy of the measurement. To verify the results, vital signs measured using facial image data were compared with pulse oximeter contact sensor, and TI non-contact sensor. As a result of this work, the possibility of extracting a total of six vital signs (heart rate, heart rate variability, oxygen saturation, respiratory rate, stress, and blood pressure) was confirmed through facial images.

• Journal of the Korea Computer Graphics Society
• /
• v.8 no.2
• /
• pp.15-22
• /
• 2002

Image segmentation methods partition an image into meaningful regions. For image composition and analysis, it is desirable for the partitioned regions to represent meaningful objects in terms of human perception and manipulation. Despite the recent progress in image understanding, however, most of the segmentation methods mainly employ low-level image features and it is still highly challenging to automatically segment an image based on high-level meaning suitable for human interpretation. The concept of HCI (Human Computer Interaction) can be applied to operator-assisted image segmentation in a manner that a human operator provides guidance to automatic image processing by interactively supplying critical information about object boundaries. Intelligent Scissors and Snakes have demonstrated the effectiveness of human-assisted segmentation [2] [1]. This paper presents a method for interactive image segmentation for more efficient and effective detection and tracking of object boundaries. The presented method is partly based on the concept of Intelligent Scissors, but employs the well-established Canny edge detector for stable edge detection. It also uses "sewing method" for including weak edges in object boundaries, and 5-direction search to promote more efficient and stable linking of neighboring edges than the previous methods.

• The Journal of the Petrological Society of Korea
• /
• v.24 no.3
• /
• pp.153-164
• /
• 2015

Jurassic granite from Geochang was analysed with respect to the characteristics of the rock cleavage. we have mainly discussed the structual anisotropy formed by microcracks. The phases of distribution of microcracks were well evidenced from the enlarged photomicrographs(${\times}6.7$) of the thin section. The planes of principal set of microcracks are parallel to the rift plane and those of secondary set are parallel to the grain plane. These rift and grain microcracks are mutually near-perpendicular on the hardway planes. From the directional angle(${\theta}$) - total length($L_t$), number(N) and density(${\rho}$) chart, the curve patterns of the above microcrack parameters reflect the phases of distribution of microcracks. Microcrack parameters such as number, length and density show an order of rift > grain > hardway. These results indicate a relative magnitude of the rock cleavage. Meanwhile, brazilian tensile strengths were measured with respect to the six directions. The results revealed a strong correlation between mechanical property with the above microcrack parameters. These general results correspond to those of the previous study for Jurassic granites from Pocheon and Hapcheon. Image processing technique for the enlarged photomicrograph of the thin section was carried out. The grain 1(G1) microcrack arrays developed in quartz and feldspar grains show excellent distribution on the photomicrograph. In particular, the directional angle of each microcrack set can be ascertained easily by brief image processing for the above photomicrograph.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.634-642
• /
• 2020

With the proliferation of Internet of Things (IoT) devices, using the Linux operating system in various architectures has increased. Also, security threats against Linux-based IoT devices are increasing, and malware variants based on existing malware are constantly appearing. In this paper, we propose a system where the binary data of a visualized Executable and Linkable Format (ELF) file is applied to Local Binary Pattern (LBP) image processing techniques and a median filter to classify malware in a Convolutional Neural Network (CNN). As a result, the original image showed the highest accuracy and F1-score at 98.77%, and reproducibility also showed the highest score at 98.55%. For the median filter, the highest precision was 99.19%, and the lowest false positive rate was 0.008%. Using the LBP technique confirmed that the overall result was lower than putting the original ELF file through the median filter. When the results of putting the original file through image processing techniques were classified by majority, it was confirmed that the accuracy, precision, F1-score, and false positive rate were better than putting the original file through the median filter. In the future, the proposed system will be used to classify malware families or add other image processing techniques to improve the accuracy of majority vote classification. Or maybe we mean "the use of Linux O/S distributions for various architectures has increased" instead? If not, please rephrase as intended.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.95-97
• /
• 2010

Recently, CAN network technology and MOST network are introduced in vehicle to control many electronic devices and to provide entertainment service. Many interconnected devices operate in MOST network which has ring topology such as CD-ROM(DVD), AMP, VIDEO CAMERA, VIDEO DISPLAY, GPS NAVIGATION and so on. In this paper, The input image of CAMERA in the MOST network is used for determining the movement direction of vehicle. Even though the position information was received from GPS, it is difficult to directly determine the direction of moving vehicle in certain areas such as the parallel road structure. This paper designs and implements the method to determine vehicle's direction by real-time matching between CAMERA image and object image base on image DB.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2004.10a
• /
• pp.274-277
• /
• 2004

Fuel/air mixing in air turbo ramjet(ATR) combustor is a significant parameter of combustion stability and efficiency. In this study, fuel distribution in the ATR model combustor was measured to compare the degree of mixing with respect to the velocity ratio$(r=v_a/v_f)$ between fuel gas and air. Planar laser-induced fluorescence(PLIF) and image processing method were used to obtain two dimensional fuel distribution. Fuel mixing went bad with approaching to r=1.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.160-161
• /
• 2019

As a method for modeling a three-dimensional object, there are a method using a 3D scanner, a method using a motion capture system, and a method using a Kinect system. Through this method, a portion that is not captured due to occlusion occurs in the process of creating a three-dimensional object. In order to implement a perfect three-dimensional object, it is necessary to arbitrarily fill the obscured part. There is a technique to fill the unexposed part by various image processing methods. In this study, we propose a method using GANs, which is the latest trend of unsupervised machine learning, as a method for more natural hole-filling.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1277-1282
• /
• 2006

본 논문에서는 배경과 오브젝트 합성 시 사실적인 그림자 효과를 표현하기 위해 HDR 영상을 기반으로 한 소수의 방향성 광원을 추정하는 기법을 제안한다. 실 세계 정보를 모두 포함하는HDR 영상을 가시화 하기 위해 톤 맵핑(tone mapping)하여 그 영상으로부터 광원의 위치가 되는 밝은 영역들을 찾아내고 그 위치들로부터 방향성 광원을 추정한다. 카메라의 노출시간을 짧게 하여 촬영한 영상에서 나타나는 부분을 실제 광원이 위치하는 부분으로 볼 수 있으므로 톤 맵핑한 영상을 이미지 프로세싱을 거쳐 노출 시간을 짧게 하여 촬영한 영상과 비슷한 결과를 얻을 수 있도록 한 후 밝은 영역만 표현 되도록 한다. 전 처리를 거친 영상을 기반으로 밝은 영역을 추정하기 때문에 보다 정확한 광원의 위치 추정이 가능하며, 추정된 밝은 영역과 일치하는 HDR 영상의 데이터를 사용하기 때문에 정확한 광원의 위치와 데이터를 얻을 수 있다. 또한 추정된 광원은 실제 렌더링에 곧바로 사용이 가능하며, 이를 통해 사실적인 shadowing 효과를 얻을 수 있다.