• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.4
• /
• pp.634-640
• /
• 2018

In this paper, we propose an automatic extraction algorithm of region of interest(ROI) based on medical x-ray images. The proposed algorithm uses segmentation, feature extraction, and reference image matching to detect lesion sites in the input image. The extracted region is searched for matching lesion images in the reference DB, and the matched results are automatically extracted using the Kalman filter based fitness feedback. The proposed algorithm is extracts the contour of the left hand image for extract growth plate based on the left x-ray input image. It creates a candidate region using multi scale Hessian-matrix based sessionization. As a result, the proposed algorithm was able to split rapidly in 0.02 seconds during the ROI segmentation phase, also when extracting ROI based on segmented image 0.53, the reinforcement phase was able to perform very accurate image segmentation in 0.49 seconds.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.3
• /
• pp.111-121
• /
• 2016

In this study, measurements were conducted by image processing to do an in-depth evaluation of strain of rebar in a uniaxial tension test. The distribution of strain and the necking region were evaluated. The image processing is used to analyze the color information of a colored image, so that the parts consistent with desired targets can be distinguished from the other parts. After this process, the image was converted to a binary one. Centroids of each target region are obtained in the binary images. After repeating such process on the images from starting point to the finishing point of the test, elongation between targets is calculated based on the centroid of each target. The tensile test were conducted on grade 60 #7(D22) and #9(D29) rebars fabricated in accordance with ASTM A615 standards. Strain results from image processing were compared to the results from a conventional strain gauge, in order to see the validity of the image processing. With the image processing, the measuring was possible in not only the initial elastic region but also the necking region of more than 0.5(50%) strain. The image processing can remove the measuring limits as long as the targets can be video recorded. It also can measure strain at various spots because the targets can easily be attached and detached. Thus it is concluded that the image processing helps overcome limits in strain measuring and will be used in various ways.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.485-488
• /
• 2005

The comparison of 3 conventional binarization methods for insect footprints and the result of performance evaluation using a proposed performance criterion are introduced in this paper. The 3 different binarization algorithms for comparison are based on different category each, and the proposed performance criterion is based on the characteristics of insect footprints which have very smaller foreground area than background area. In the experiments, average performance results using 71 test images are compared and analyzed. The higher-order entropy binarization algorithm proposed by Abutaleb showed the best result for pattern recognition applications of insect footprints.

• Journal of the Korean Geotechnical Society
• /
• v.27 no.11
• /
• pp.93-101
• /
• 2011

High quality X-ray computed microtomography (micro-CT) imaging of internal microstructures and pore space in geomaterials is often hampered by some inherent noises embedded in the images. In this paper, we introduce image calibration techniques for removing the most common noises in X-ray micro-CT, cupping (brightness difference between the periphery and central regions) and ring artifacts (consecutive concentric circles emanating from the origin). The artifacts removal sequentially applies coordinate transformation, normalization, and low-pass filtering in 2D Fourier spectrum to raw CT-images. The applicability and performance of the techniques are showcased by describing extraction of 3D pore structures from micro-CT images of porous basalt using artifacts reductions, binarization, and volume stacking. Comparisions between calibrated and raw images indicate that the artifacts removal allows us to avoid the overestimation of porosity of imaged materials, and proper calibration of the artifacts plays a crucial role in using X-ray CT for geomaterials.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.2
• /
• pp.69-78
• /
• 2006

This paper is concerned with analyzing the images of Korean automobiles using, so called, sensory engineering, which adapts the sensory and subjective assessment of human beings in evaluating the quality of product. The methodology of analysis is suggested in this paper according to the following steps. First, 14 pairs of adjectives, which describe the image of object cars in view of the semantic differential method, are derived from consulting with several expert panels. Nextly, factor analysis is performed in order to obtain the axises, by which the images space of the object automobiles are specified, and then the images of the object automobiles are measured by the coordinate of all the object automobiles in the image space. In this paper, a sensory estimation experiment is performed to a panel consisting with In undergraduate students residing in the region of Daegu. From the result of analysis of this paper, target images, which the automobile manufacturers are intended, are achieved by and large except one company.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.246-249
• /
• 2001

본 연구는 온라인 지문 인식 기법의 속도 향상을 주목적으로 하여 기존의 지문 인식 기법과 비교하여 개선된 전처리 방법을 이용하여 적은 계산량으로 보다 높은 정확도를 확보하여 궁극적으로 지문 인식 및 대조 시스템이 적합한 특징점 추출 알고리즘 개발을 목적으로 한다. 먼저 방향성이미지에서 방향성추출에서는 4$\times$4화소를 하나의 Block으로 나눈 후, 3$\times$3의 Sobel 연산자를 이용하였고, 이 방향성 정보를 이용하여 지문영상의 품질 측정과 배경 분리를 하였으며, 또한 부분 영역간의 밝기 차이 등으로 발생하는 오류를 최소화하기 위하여 이진화 수행 과정에서 가장 애로점인 임계치(threshold value) 설정을 지문의 대상 영역의 밝기 등에 적응하여 스스로 변하도록 할 수 있게 Slit sum의 방법을 응용한 적응 이진화를 하였다. 세선화와 특징점 추출에서는 VHN(Vertical & horizontal Number)값을 이용하여 보정(Interpolation)효과를 주어 오류특징점을 배제하고, 자동 지문 인식 시스템의 인식성능을 향상시켰다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.91-94
• /
• 2019

스케치를 거쳐 생성되는 디지털 자료로 건축도면이나 제품 디자인시안 등은 수요가 많음에도 불구하고 디지털 도면 자동생성에 대한 영상처리는 아직 연구되지 않고 있다. 현행 필기인식에 대한 영상처리 연구는 주로 글자나 숫자에 국한되어 있어 본 연구에서는 선으로 이루어진 필기를 인식하여 도면이라는 이진영상의 특징을 이용해 특징점을 도출하고 디지털 도면을 생성하는 영상처리를 제안한다. 먼저 입력받은 아날로그 스캔이미지를 메디안블러링과 OSTU임계처리로 노이즈가 없는 이진영상으로 변환한 후 해리스코너검출기를 이용하여 특징점을 검출하고 좌표를 추출하고, 좌표값을 활용해 외곽선과 내부윤곽선까지 구현하여 디지털도면을 양산한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.184-188
• /
• 2007

본 논문에서는 기존에 상용화되거나 서비스되고 있는 만화 제작 시스템들의 장단점을 비교 분석한다. 그리고 일상생활에서 쉽게 활용할 수 있는 동영상 이미지를 이용하여, 흑백 만화를 제작하기 위한 시스템에 대해 논의한다. 동영상으로부터 추출한 이미지는 일반적으로 동영상 자체의 스토리를 내포하고 있기 때문에, 이 이미지들을 기반으로 흑백 만화를 제작하는 시스템을 개발한다면, 만화 초보자들도 손쉽게 흑백 만화를 제작할 수 있다. 본 논문에서 제안한 흑백 만화 제작 시스템은 먼저 1) 기존의 이미지를 이진화하고 2) 양식화된 스트록을 렌더링하여 만화적인 특징을 표현한다. 그리고 3) 다양한 만화적인 요소를 추가한 후 4) 완성된 만화 컷을 실제 만화에서 사용되는 레이아웃 템플릿에 따라 배치하여 한 장의 만화를 제작한다. 논문에서 제안한 시스템을 활용함으로써, 만화 초보자들이 만화를 제작할 때 직면하게 되는 문제점들(스토리 보드 설정과 그림 실력의 부재)을 해결할 수 있었다.

• The KIPS Transactions:PartD
• /
• v.10D no.3
• /
• pp.541-546
• /
• 2003

We present a random bit generator that uses fingerprint image as the source of random, and the random bit generator is the first generator in the world that uses biometric information for the source of random in the world. The generator produces, on the average, 9,334 bits a fingerprint image in 0.03 second, and the produced bit sequence passes all 16 statistical tests that are recommended by NIST for testing the randomness.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.703-706
• /
• 2003

이 논문은 입력 지문 영상에 대하여 블록 이진화와 병렬 세선화를 거친 이미지에 4개의 각기 다른 방향 성분 요소를 이용하여 각 블록에 대한 대표 방향 성분들을 추출하여 방향 성분 이미지를 얻었다. 추출된 대표 방향성분 이미지에 정의된 방향성 패턴을 적용시켜 일치되는 블록에 대하여 1차와 2차 중심점으로 추출하였다. 이렇게 추출된 1차와 2차 중심점을 이용하여 직교좌표를 생성하였다. 직교좌표는 지문영상을 처리하여 인식 및 인증시스템에서 유용하게 쓰일 수 있을 것이다.