• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.215-218
• /
• 2004

본 논문은 실내외에서 얻어진 자연 영상으로부터 기울어진 영상을 바로 보정하고 텍스트를 추출하는 방법을 제안한다. 본 연구는 명도 이미지를 대상으로 모든 과정이 4단계로 이루어진다. 첫째 자연 영상에서 에지 검출 처리를 위한 전처리 및 Canny 에지 추출을 수행하며, 둘째 영상의 기울기를 추출하기 위해 허프변환에 대한 전처리와 후처리를 한 후, 셋째로 잡음영상과 선을 제거하고 텍스트 특징을 이용한 후보영역 검출을 한다. 마지막으로 텍스트 후보영역 안에서 지역적 이진화를 수행하여 불필요한 비텍스트 연결 요소를 추려내기 위해 두 가지 텍스트 추출 방법을 수행한다. 본 연구는 게시판, 교통표지판, 책 표지 등 100장의 자연영상을 대상으로 실험한 결과 텍스트 추출에서 90.3% 추출 정확도를 가졌으며, 기울어진 각도 추출에서도 94.3%의 높은 추출률을 보였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.379-381
• /
• 2013

In this paper, we propose a method to detect the gradient of the spaces between sentences and to deskew in the document image. First, gradient is measured by pixels for spaces between sentences that has been done an edge extraction in document image and then skewed image is corrected by using the value of the gradient which has been measured. Since document image is divided into several areas, it shows a robust processing result by handling the margin, images, and multistage form in the document. Because the proposed method does not use pixel of the character region but use the blank area, degraded document image as well as vivid document image is effectively corrected than conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.227-232
• /
• 2018

In a Hough transform that is a representative algorithm for the straight line detection, a great number of edge pixels generated from noisy or complex images cause enormous amount of computation and pseudo straight lines. This paper proposes a two step straight line detection algorithm to improve the conventional Hough transform. In the first step, the proposed algorithm divides an image into non-overlapping blocks and detects the information related to the straight line of the edge pixels in the block using a principal component analysis (PCA). In the second step, it detects the straight lines by performing the Hough transform limited slope area to the pixels associated with the straight line. Simulation results show that the proposed algorithm reduces average of ${\rho}$ computation by 94.6% and prevents the pseudo straight lines although some additional computation is needed.

• Geophysics and Geophysical Exploration
• /
• v.15 no.4
• /
• pp.190-198
• /
• 2012

A series of density log data were obtained from the standoff experiments made in the four physical model boreholes of different densities, and the properties of spine and rib curves have been derived by the analysis of the gamma-gamma data. Particularly, the shape of gamma ray propagation path between source and detector, the geometrical property of spine and rib curves, the influence of borehole density and the detector combination on the properties of the curves, and the adequate detector combination for standoff compensation could be discussed. It was also confirmed that spine and rib slopes can be expressed as proportional to source-to-detector distance ratio between far and near detectors. The result of this experiment was also effectively applied for understanding the basic concept of spine and rib slopes.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.10a
• /
• pp.107-107
• /
• 2003

• Journal of Biomedical Engineering Research
• /
• v.24 no.3
• /
• pp.175-181
• /
• 2003

Studies of muscle fatigue have mostly been checked under isometric exercise. However EMG signals from isotonic exercise generate uncontrollable noise, so there were difficulties in gathering reliable median frequency and muscle fatigue index if frequency analysis was equally applied in isometric exercise. This study tried to compare the differences of muscle fatigue determinant variables in terms of median frequency searching methods of EMG signal, which was estimated in isotonic exercise. To accomplish this, we determined median frequency by using different FFT intervals and overlapping ration of consecutive FFT sections under the same EMG signal, and then searched for a linear regression line, and compared initial median frequency, slope, and muscle fatigue index which were variables under the linear regression line. In result of comparison, initial median frequency was more elevated as FFT exercise interval became larger. The slope of the linear regression line showed distinguishable decreasing tendency as FFT intervals were larger and overlapping sections were smaller. Significant tendency of muscle fatigue index in FFT interval was shown by high muscle fatigue index in specific FFT intervals.

• Journal of Korean Society of Environmental Engineers
• /
• v.28 no.11
• /
• pp.1148-1153
• /
• 2006

Signal measuring system to analyze ion concentrations in biofilm was constructed with ion selective microeleclrode and electrometer. In order to evaluate the performance and applicability of signal measuring system, the following characteristics, such as slope of calibration curve, detection limit, variation of response according to the time, and potentiometric selectivity coefficient, were investigated. The slope of calibration curve showed high degree of association for primary ion concentration. The response of the system was log-linear in standard solution down to $10{\mu}M$ and signal measuring system was not sensitive for interfering ions. In comparison with commercial electrometer, the fabricated electrometer system had similar tendencies for the slope of calibration curve, detection limit, and response time. Therefore the signal measuring system could be used to investigate ion profiles in biofilm as a cost effective and reliable measuring system.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.777-785
• /
• 2017

In the modern real world, we can extract and recognize some texts to get a lot of information from the scene containing them, so the techniques for extracting and recognizing text areas from a scene are constantly evolving. They can be largely divided into texture-based method, connected component method, and mixture of both. Texture-based method finds and extracts text based on the fact that text and others have different values such as image color and brightness. Connected component method is determined by using the geometrical properties after making similar pixels adjacent to each pixel to the connection element. In this paper, we propose a method to adaptively change to improve the accuracy of text region extraction, detect and correct the slope of the image using edge and image segmentation. The method only extracts the exact area containing the text by correcting the slope of the image, so that the extracting rate is 15% more accurate than MSER and 10% more accurate than EEMSER.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.4
• /
• pp.259-266
• /
• 2016

Recently, CCTV cameras are emplaced actively to reinforce security and intelligent surveillance systems have been under development for detecting and monitoring of the objects in the video. In this study, we propose a method for detection of upper body in intelligent surveillance system using FCM-based RBFNN classifier realized with the aid of HOG features. Firstly, HOG features that have been originally proposed to detect the pedestrian are adopted to train the unique gradient features about upper body. However, HOG features typically exhibit a very high dimension of which is proportional to the size of the input image, it is necessary to reduce the dimension of inputs of the RBFNN classifier. Thus the well-known PCA algorithm is applied prior to the RBFNN classification step. In the computer simulation experiments, the RBFNN classifier was trained using pre-classified upper body images and non-person images and then the performance of the proposed classifier for upper body detection is evaluated by using test images and video sequences.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.5
• /
• pp.21-27
• /
• 2008

Despite recent studies on development of pulse diagnosis systems and needs for commercializing them, the reproducibility is one of the most controversial issues as ever. Because the pulse pressure value, which is one of the important parameters to evaluate reproducibility, is very vulnerable to moving artifacts, the reproducibility can not be obtained easily. In this paper, we suggested a moving artefacts detection system for a pulse diagnosis system so that a pulse diagnosis system can be robust to theses kinds of artefacts by excluding the contaminated parts from the pulse wave signal to be analyzed. This moving artifacts detection system was designed to consist of a three-axis accelerometer, an electromyography amplifier and a two-axis tilt sensor. To assess the suitability of the system, we examined the characteristics of each sensor's output signals with regard to the three specific motions such as extension, flexion and rotation. And, we also examined the each sensor's response to the high-frequency and low-frequency moving artifacts while the pulse wave signal was acquired from a pressure sensor for the pulse diagnosis. From these results, we could find that the response to subject's motions would be reflected in electromyography signal first, in accelerometer signals and in tilt sensor sequently. And, the facts that a stable pulse wave can be acquired in two seconds after high frequency or low frequency motions ended, were also found. Consequently, based on these findings, we set up some rules on the moving artifacts detection and designed an algorithm which is fit for our moving artifacts detection system.