• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.89-96
• /
• 2006

In this paper, we propose two approaches for the character segmentation on Korean document images. One is an improved version of a projection profile-based algorithm. It involves estimating the number of characters, obtaining the split points and then searching for each character's boundary, and selecting the best segmentation result. The other is developed for low quality document images where adjacent characters are connected. In this case, parts of the projection profile are cut to resolve the connection between the characters. This is called ${\alpha}$-cut. Afterwards, the revised former segmentation procedure is conducted. The two approaches have been tested with 43,572 low-quality Korean word images punted in various font styles. The segmentation accuracies of the former and the latter are 91.81% and 99.57%, respectively. This result shows that the proposed algorithm using a ${\alpha}$-cut is effective for low-quality Korean document images.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.3
• /
• pp.209-214
• /
• 2010

This paper proposes an algorithm of segmentation and title detection for document image. The automated title detection method that we have developed is composed of two phases, segmentation and title area detection. In the first phase, we extract and segment the document image. To perform this operation, the binary map is segmented by combination of morphological operation and CCA(connected component algorithm). The first phase provides segmented regions that would be detected as title area for the second stage. Candidate title areas are detected using geometric information, then we can extract the title region that is performed by removing non-title regions. After classification step that removes non-text regions, projection is performed to detect a title region. From the fact that usually the largest font is used for the title in the document, horizontal projection is performed within text areas. In this paper, we proposed a method of segmentation and title detection for various forms of document images using geometric features and projection profile analysis. The proposed system is expected to have various applications, such as document title recognition, multimedia data searching, real-time image processing and so on.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.20-26
• /
• 2021

In this paper, we studied the rotation angle estimation methods required for image alignment in an image recognition environment. In particular, a rotation angle estimation method applicable to a low specification embedded-based environment was proposed and compared with the existing method using complex moment. The proposed method estimates the rotation angle through similarity mathcing of the 1D projection profile along the radial axis after converting an image into polar coordinates. In addition, it is also possible to select a method of using vector sum of the projection profile, which more simplifies the calculation. Through experiments conducted on binary pattern images and gray-scale images, it was shown that the estimation error of the proposed method is not significantly different from that of complex moment-based method and requires less computation and system resources. For future expansion, a study on how to match the rotation center in gray-scale images will be needed.

• Journal of KIISE:Software and Applications
• /
• v.31 no.9
• /
• pp.1121-1130
• /
• 2004

This paper proposes a method for line and word segmentation for machine-printed text blocks. To separate a text region into the unit of lines, it analyses the horizontal projection profile and performs a recursive projection profile cut method. In the word segmentation, between-word gaps are identified by a hierarchical clustering method after finding gaps in the text line by using a connected component analysis. In addition, a special symbol detection technique is applied to find two types of special symbols tying between words using their morphologic features. An experiment with 84 text regions from English and Korean documents shows that the proposed method achieves 99.92% accuracy of word segmentation, while a commercial OCR software named Armi 6.0 Pro$^{TM}$ has 97.58% accuracy.y.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.99-106
• /
• 2006

Type classification is a very needed step in recognizing huge character set language such as korean characters. Since most previous researches are based on the composition rule of Korean characters, it has been difficult to correctly classify composite vowel characters and problem space was not divided equally for the lack of classification of last consonant which is relatively bigger than other graphemes. In this paper, I Propose a new type classification method in which horizontal vowel is extracted before vortical vowel and last consonants are further classified into one of five small groups based on horizontal projection profile. The new method uses 19 character types which is more stable than previous 6 types or 15 types. Through experiments on 1.000 frequently used character sets and 30.614 characters scanned from several magazines, I showed that the proposed method is more useful classifying Korean characters of huge set.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.631-638
• /
• 2012

This work proposes a new method to generate velocity profile of a traction motor equipped in a rehabilitation system for knee joint patients through humanoid robot simulation. To this end, a three-dimensional full-body humanoid robot model is newly constructed, and natural human gait is simulated by applying to it reference joint angle trajectories already published. Linear velocity is derived from distance data calculated between the positions of a thigh band and its traction motor at every sampling instance, which is a novel idea of this paper. The projection rule is employed to kinematically describe the humanoid robot because of its high efficiency and accuracy, and measured joint trajectories are used in simulating human natural gait referring to Winter's book. The attained motor velocity profile for a certain position in human body will be applied to our walking-assistance system which is implemented with a treadmill system.

• Progress in Medical Physics
• /
• v.23 no.4
• /
• pp.252-260
• /
• 2012

The reduction of radiation dose from x-ray is a main concern in computed tomography (CT) imaging due to the side-effect of the dose on human body. Recently, the various methods for dose reduction have been studied in CT and one of the method is a iterative reconstruction based on total variation (TV) minimization at few-views data. In this paper, we evaluated the image quality between total variation (TV) minimization algorithm and Feldkam-Davis-kress (FDK) algorithm in micro computed tomography (CT). To evaluate the effect of TV minimization algorithm, we produced a cylindrical phantom including contrast media, water, air inserts. We can acquire maximum 400 projection views per rotation of the x-ray tube and detector. 20, 50, 90, 180 projection data were chosen for evaluating the level of image restoration by TV minimization. The phantom and mouse image reconstructed with FDK algorithm at 400 projection data used as a reference image for comparing with TV minimization and FDK algorithm at few-views. Contrast-to-noise ratio (CNR), Universal quality index (UQI) were used as a image evaluation metric. When projection data are not insufficient, our results show that the image quality of reconstructed with TV minimization is similar to reconstructed image with FDK at 400 view. In the cylindrical phantom study, the CNR of TV image was 5.86, FDK image was 5.65 and FDK-reference was 5.98 at 90-views. The CNR of TV image 0.21 higher than FDK image CNR at 90-views. UQI of TV image was 0.99 and FDK image was 0.81 at 90-views. where, the number of projection is 90, the UQI of TV image 0.18 higher than FDK image at 90-views. In the mouse study UQI of TV image was 0.91, FDK was 0.83 at 90-views. the UQI of TV image 0.08 higher than FDK image at 90-views. In cylindrical phantom image and mouse image study, TV minimization algorithm shows the best performance in artifact reduction and preserving edges at few view data. Therefore, TV minimization can potentially be expected to reduce patient dose in clinics.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1804_1805
• /
• 2009

최근 여러 산업 분야에서는 품질의 향상과 생산성을 높이기 위해 자동화 검사 장치 개발이 활발하게 연구 되고 있다. 본 연구에서는 비전을 이용한 신뢰도 높은 슬라브(Slab) 표면 검사 자동화 알고리즘의 전처리 단계인 오실레이션 마크(Oscillation mark) 검출을 목표로 한다. 슬라브 영상의 경우 조업시에 발생하는 산화 물질인 스케일(Scale)이 영상 전체에 분포하고 있으며, 이러한 스케일은 형태적 특징 및 밝기 특징이 일정치 않기 때문에 오실레이션 마크 검출 성능을 저하 시킨다. 따라서 스케일의 영향을 최소화 하고 효과적으로 오실레이션 마크를 검출하기 위해 가버 필터(Gabor filter)와 수직 투영 프로파일(Vertical projection profile)을 이용한 노이즈 제거 방법을 사용한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10a
• /
• pp.293-296
• /
• 2000

본 논문에서는 주제어 인식에 기반한 문서영상의 검색 및 색인 시스템에 적용하기 위한 단어 단위 분한 시스템을 제안한다. 제안 시스템은 영상 전처리, 문서 구조 분석을 통해 추출된 텍스트 영역을 입력으로 단어 단위 분할을 수행하는데, 텍스트 영역에 대해 텍스트 라인을 분할하고 분할된 텍스트 라인을 단어 단위로 분할하는 계층적 접근 방법을 사용한다. 텍스트라인 분할은 수평 방향 투영 프로파일을 적용하여 분할 지점을 구한다. 그리고 단어 분할은 연결요소들을 추출한 후 연결요소간의 gap 정보를 구하고, gap 군집화 기법을 사용하여 단어 단위 분한 지점을 구한다. 이때 단어 단위 분할의 성능을 저하시키는 특수기호에 대해서는 휴리스틱 정보를 이용하여 검출한다. 제안 시스템의 성능 평가는 50개의 텍스트 영역에 적용하여 99.83%의 정확도를 얻을 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.11a
• /
• pp.207-210
• /
• 2012

본 논문에서는 스테레오스코픽 3D 동영상에서 왼쪽과 오른쪽 영상 사이의 프레임 동기가 맞지 않아 시청에 어려움을 주는 문제를 해결하기 위해서, 두 영상에서 물체의 움직임에 따른 차이를 이용한 프레임 동기화 방법을 제안한다. 제안 방식은 교정화 과정을 통해 수직 시차를 보정한 왼쪽과 오른쪽 입력 영상에서 각각 전 영상과의 차분 값에 대한 수평 방향 투영 프로파일을 구하고, 이들의 절대 오차에 대한 평균 (mean of absolute difference(MAD))를 계산해 최소값이 되는 프레임 조합을 찾아 프레임 동기를 맞추는 방법이다. 실험결과, 프레임 동기가 맞는 프레임 조합에서 최소 MAD 값을 기록하여 스테레오스코픽 3D 동영상에서의 프레임 동기화가 가능하다는 것을 볼 수 있으며, 특정 잡음이나 영상 압축 조건에 대해서도 동작함을 알 수 있다.