• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권9호
• /
• pp.2312-2325
• /
• 2013

In this paper, we propose a preprocessing method that it is to correct the distortion of text area in Korean signboard images as a preprocessing step to improve character recognition. Distorted perspective in recognizing of Korean signboard text may cause of the low recognition rate. The proposed method consists of four main steps and eight sub-steps: main step consists of potential vertical components detection, vertical components detection, text-boundary estimation and distortion correction. First, potential vertical line components detection consists of four steps, including edge detection for each connected component, pixel distance normalization in the edge, dominant-point detection in the edge and removal of horizontal components. Second, vertical line components detection is composed of removal of diagonal components and extraction of vertical line components. Third, the outline estimation step is composed of the left and right boundary line detection. Finally, distortion of the text image is corrected by bilinear transformation based on the estimated outline. We compared the changes in recognition rates of OCR before and after applying the proposed algorithm. The recognition rate of the distortion corrected signboard images is 29.63% and 21.9% higher at the character and the text unit than those of the original images.

• 복식
• /
• 제59권6호
• /
• pp.72-81
• /
• 2009

The purpose of this study is to develop geometric patterns which can be reinterpreted in a modern sense and textile designs which can be commercialized in the mural painting of Goguryeo Dynasty's tomb. Of 42 tombs where genres and portraits could be observed, the costume style of Goguryeo dynasty could be mainly observed in the tombs built in the 4th and 5th centuries. Since geometric patterns found in the portrait could be represented in a modern sense, this study was intended to develop the patterns of a necktie which is one of cultural products by applying geometric patterns in the mural painting of Goguryeo Dynasty's tomb in the 5th century with many patterns distributed. The scope of patterns was limited to a square, a triangle, a circle, and a diagonal line which were the basic of geometric patterns found in the mural painting. The methods of study were literature review and empirical study. Adobe Photoshop CS3 was used to edit geometric patterns found in the mural painting of Goguryeo Dynasty's tomb in the 5th century. By extracting a square(${\square}$), a triangle(${\vartriangle}$), a circle(${\bigcirc}$), and a diagonal line(${\diagdown}$) from edited images, predicted images were proposed before products were made. Finally textile designs were made through the simulation of edited design patterns in the necktie and handkerchief. This study will contribute to the positive effects on the development of cultural product designs applying the characteristic of geometric patterns and the construction of Korean image.

• Journal of Welding and Joining
• /
• 제18권2호
• /
• pp.86-94
• /
• 2000

This study was performed to investigate types and formation mechanism of cracks in two Al alloy welds, A5083 and A7N01 spot-welded by pulse Nd : YAG laser, using SEM, EPMA and Micro-XRD. In the weld zone, three types of crack were observed : center line crack({TEX}$C_{C}${/TEX}), diagonal crack({TEX}$C_{D}${/TEX}), and U shape crack({TEX}$C_{U}${/TEX}). Also, HAZ crack({TEX}$C_{H}${/TEX}) was observed in the HAZ region, furthermore, mixing crack({TEX}$C_{M}${/TEX}) consisting of diagonal crack and HAZ crack was observed. White film was formed at th hot crack region in the fractured surface after it was immersed to 10% NaOH water. In the case of A5083 alloy, white films in {TEX}$C_{C}${/TEX} crack and {TEX}$C_{D}${/TEX} crack region were composed of low melting phases, {TEX}$Fe_{2}SiAl_{8}${/TEX} and eutectic phases, $Mg_2$Al$_3$ and $Mg_2$Si. Such films observed $CuAl_2$, {TEX}$Mg_{32}(Al,Zn)_{3}${/TEX}, MgZn$_2$, $Al_2$CuMg and $Mg_2$Si were observed in the whitely etched films near {TEX}$C_{C}${/TEX} crack and {TEX}$C_{D}${/TEX} crack regions. The formation of liquid films was due to the segregation of Mg, Si, Fe in the case of A5083 alloy and Zn, Mg, Cu, Sim in the case of A7N01 alloy, respectively. The {TEX}$C_{C}${/TEX} and {TEX}$C_{D}${/TEX} cracks were regarded as a result of the occurrence of tensile strain during the welding process. The formation of {TEX}$C_{M}${/TEX} crack is likely to be due to the presence of liquid film at the grain boundary near the fusion line in the base metal as well as in the weld fusion zone during solidification. The {TEX}$C_{U}${/TEX} crack is considered a result of the collapsed keyhole through incomplete closure during rapid solidification.

• 융합신호처리학회논문지
• /
• 제10권1호
• /
• pp.7-12
• /
• 2009

본 논문에서는 local min/max 연산을 이용한 필기체 숫자의 방향특징 추출 기법을 제안한다. 숫자의 방향특징은 숫자를 이루는 선에서 수평, 수직 및 두 대각방향인 4개 방향의 선들로 구성된 방향선분 영상으로부터 구해진다. Kirsch 마스크를 사용하는 기존의 방향특징 추출기법은 에지형태인 두 겹으로 된 방향선분 영상을 생성하는데 반해 본 논문에서 제시하는 방법은 방향성 수축연산을 사용하여 한 겹으로 된 방향선분 영상을 생성한다. 본 방향성 수축연산을 숫자영상에 적용하기 위해서는 먼저 세선화, 영상 팽창 등의 전처리가 필요하지만 이 방법은 숫자를 이루는 선 자체와 더욱 유사한 형태를 갖는 방향선분을 제공한다. 우리가 구하고자 하는 [$4{\times}4$] 크기인 4개의 방향특징은 4개의 방향선분 영상으로부터 조닝방법을 통해 구해진다. 보다 높은 필기체 숫자인식을 얻기 위해, 본 연구에서는 우리가 제안한 방향특징에 기존의 Kirsch 방향특징과 오목특징을 결합한 다중특징을 사용하였다. 본 숫자 특징에 의한 인식률을 테스트를 위해 오류역전파 알고리즘으로 학습되는 다층퍼셉트론 신경회로망을 인식기로 사용하였으며, Concordia 대학의 CENPARMI 숫자 데이터베이스를 사용하여 실험한 결과 98.35%의 인식률을 얻을 수 있었다.

• ETRI Journal
• /
• 제34권6호
• /
• pp.978-981
• /
• 2012

We present an analytic solution to the projector pose estimation problem for the pinhole projection model in which the source image is a centered rectangle with an unknown aspect ratio. From a single quadrilateral given as a target image, our solution gives the position and orientation of a projector as well as the aspect ratio of a source image. The proposed method decomposes the problem into two pose estimation problems of coupled line projectors aligned at each diagonal of the given quadrilateral and then computes the common solution that satisfies the relevant geometric constraints. The solution is formulated as simple analytic equations. We also provide a determinant of projectability of an arbitrary quadrilateral.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2001년도 춘계학술대회 논문집
• /
• pp.123-128
• /
• 2001

Numerical simulation is conducted to clarify the heat transfer and fluid flow characteristics of brake shoe for freight car. High order up-wind scheme for governing equations, k-epsilon turbulent model and SIMPLEC algorithm based on finite volume method are used to solve the physical shoe model. The governing equations are solved by TDMA(Tri-Diagonal Matrix Algorithm) with line-by-line method and block correction. From the results of simulation, the characteristics of cooling pattern is strongly affected by the velocity of train and the material of shoe. The face lift of shoe affects on the temperature distribution of rear surface of shoe as well as the front surface of that. Due to the grooves in shoe, it will be expected to cool the frictional heat and result in the reduction of maintenance efforts.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 1999년도 추계학술대회 논문집
• /
• pp.93-98
• /
• 1999

Numerical simulation is conducted to clarify the heat transfer and fluid flow characteristics of brake disk-lining for rolling stock. Multiple rotational reference frame, k-epsilon turbulent model and SIMPLE algorithm based on finite volume method are used to solve the physical disk-lining model. The governing equations are solved by TDMA(TriDiagonal Matrix Algorithm) with line-by-line method and block correction, From the results of simulation, the characteristics of cooling pattern is strongly affected by the grooves in lining. The face lift of lining affects on the temperature distribution of rear surface of lining as well as the front surface of that. Due to the grooves in lining, it will be expected to extend the maintenance life circle of lining.

• 한국지능시스템학회논문지
• /
• 제15권6호
• /
• pp.709-713
• /
• 2005

고해상도의 항공영상으로부터 3차원 와이어프레임(wire-frame) 구성을 위한 새로운 선소 추출 알고리듬을 제안하였다. 본 연구의 목적은 기존의 방식들의 문제점인 라인 불일치 문제, 에지부분의 Blurring 문제 등을 고려하여 보다 정밀하고 효과적인 선소를 추출하는데 있다. 먼저 항공영상으로부터 에지맵을 추출한 후, 에지 점들의 체인 코드 추적을 수행하고 에지강도와 방향성분을 고려한 선소의 추출을 행하였다. 에지맵의 추출은 Smith가 제안한 SUSAN(Smallest Univalue Segment Assimilating Nucleus) 알고리듬을 이용하였다. 제안한 알고리듬은 다음의 4 단계로 구성된다. 에지 맵의 체인코드 추적 결과에 기반하여 비선소 후보점을 감소시키기 위한 수평/수직/대각 성분 제거, 인접점 제거, 각도 일치점 제거, 선소를 이루는 시작점 및 끝점 검출 등의 과정을 통하여 선소추출을 행하였다. 제안한 알고리듬과 기존의 Boldt 알고리듬을 비교한 결과 제안한 알고리듬이 건물을 이루고 있는 주요 선소를 더욱 충실히 찾아냈고 불필요한 선소는 적게 찾아냄을 확인하였다.

• 융복합기술연구소 논문집
• /
• 제6권1호
• /
• pp.23-26
• /
• 2016

DC motor shafts have several defects such as double cut, deep scratch on surface, and defects in diameter and length. The deep scratches are due to collision among the other shafts. So the scratches are long and thin but their orientations are random. If the smallest enclosing box, i.e. oriented bounding box for a detective point group is found, then the size of the corresponding defect can be modeled as its diagonal length. This paper proposes an suface inspection algorithm for the DC motor shaft using the oriented bounding box. To evaluate the proposed algorithm, a test bed is made with a line scan CCD camera (4096 pixels/line) and two rollers mechanism to rotate the shaft. The experimental result on a pre-processed image with contrast streching algorithm, shows that the proposed algorithm sucessfully finds 150 surface defects and its computation time (0.291 msec) is enough fast for the requirement (4 seconds).

• 정보처리학회논문지D
• /
• 제9D권5호
• /
• pp.915-924
• /
• 2002

현재, 컨베이어 벨트 시스템에 소포를 적재하고, 우편번호를 입력하여 구분한다. 구분된 소포 중에서 기록관리 대상의 경우에는 바코드를 판독하여 처리하고 있다. 본 논문에서는 2m/sec 이내로 이송되는 소포를 라인 CCD(Charged Coupled Device) 카메라를 통해 이미지를 획득(4,096$\times$4,096)한 후, 바코드 ROI(Region of Interest)의 추출을 위해 32$\times$32 크기의 미세블록의 검사방법을 적용하였다. ROI 추출 단계는 미세블록(128$\times$128)들의 최대 및 최소값의 차이 분포를 이용하여 컨베이어 벨트 영역과 소포의 바탕면은 제거하였다. 그리고 문자열과 바코드 영역을 검출하기 위해 대각선(diagonal) 검사방법을 사용하였으며, 바코드 ROI 만을 분리하기 위해 미세블록의 중앙에 5개의 수평라인으로 스캔하여 에지 수와 크기에 대한 변화량을 검사하였다. 검출된 영역 중에서 잘못 검출된 영역을 그룹의 라벨링 과정에서 그룹의 크기를 비교하여 제거하였다. 미세블록 검사과정에서 누락된 바코드 영역을 보정하고 바코드의 정보 해석을 위해 추출된 ROI의 외곽좌표들과 기울기 분포를 이용하여 중심 축 라인과 ROI 영역의 기울기에 따라 중심축을 보정하는 방법 등을 적용하였다. 이와 같은 방법에 의해 바코드의 ROI 추출과 중심축 생성은 60～180msec이내에 가능하게 되었으며, ROI 추출의 정확도는 99.44% 이상이 달성되었다.