• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2831-2838
• /
• 2014

This paper proposes the off-line handwritten flowchart symbol recognition algorithm by type and strength of a cross region of the straight line strokes that is extracted based the normalized dominant slope vectors. In the proposed algorithm, first of all, a connector symbol which consisted only curves is recognized by the special features, and the other symbols with straight line strokes are recognized by type and strength of a cross region, and that is extracted by extension of minimum bounding rectangle of the clusters of the normalized dominant slope vectors, and the straight line strokes of the symbols is extracted by the normalized dominant slope vectors. To confirm the validity of the proposed algorithm, the experiments are conducted for 10 different kinds of flowchart symbols that mainly used for computer program, and the number of symbols is 198. Experiment results were obtained the recognition rate of 99.5%, and the flowchart symbols is recognized correctly robust to variations, and then the proposed algorithm were found very effective for off-line handwritten flowchart symbol recognition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2489-2496
• /
• 2014

The existing ship repair tool management system based on hand writing has many problems such as frequent loss of tool and overdue. To solve this problem, same systems have adopted the bar-code system. However, the systems can't cope with a problem to substitute spurious tool for genuine one on bar-code damage. Therefore, additional validation steps are necessary in order to manage expensive ship repair tool. In this paper, we propose an image comparison method for ship repair tool management. To be more concrete, we propose a normalization method and determination conditions for image comparison to use characteristics of mobile device. The normalization method makes use of the characteristics of mobile device that provides functions of real time recording, overlapping and cropping images. The proposed method applies three conditions(sum of inner angles, size of angle, position of corner coordinates) into the comparison module. The implemented system shows good performance on change direction, lighting, size and etc. The accuracy is more than 95%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.8C
• /
• pp.711-720
• /
• 2012

In this paper, we introduce the implementation of driver fatigue monitering system and its result. Input video device is selected commercially available web-cam camera. Haar transform is used to face detection and adopted illumination normalization is used for arbitrary illumination conditions. Facial image through illumination normalization is extracted using Haar face features easily. Eye candidate area through illumination normalization can be reduced by anthropometric measurement and eye detection is performed by PCA and Circle Mask mixture model. This methods achieve robust eye detection on arbitrary illumination changing conditions. Drowsiness state is determined by the level on illumination normalize eye images by a simple calculation. Our system alarms and operates seatbelt on vibration through controller area network(CAN) when the driver's doze level is detected. Our algorithm is implemented with low computation complexity and high recognition rate. We achieve 97% of correct detection rate through in-car environment experiments.

• Journal of Korean Society of Transportation
• /
• v.17 no.4
• /
• pp.111-124
• /
• 1999

The Purpose of this thesis is to develop a vehicle classification algorithm using single Magnetometer detector during presence time of vehicle detection and is to examine a held application from field test. We collected data using Magnetometer detector on freeway and used digital data to change voltage values according to magnetic flux density in analysis. We collected these datum during the presence time and then obtained characteristics from wave form in these datum. Based on these characteristics, We used the following three methods for this a1gorithm :1. Template Matching Method,2. Neural Network Method using Back-propagation Algorithm 3. Complex Method using changed slope points and mixing method 1, 2. Of course, Before processing of over three methods, These data were processed normalizing by 20, 40 of size in only X axis and moving average by 0, 3, 4, 5 of size. Vehicle classification were Processed in three steps ; 2, 3, 5 types classification. In 2 types vehicle classification, recognition rate is 83% by template matching method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.5
• /
• pp.634-642
• /
• 1993

In this paper a new trajectory control method is proposed for a robot manipulator using a time delay neural network(TDNN) as a feedforward controller with an algorithm to learn inverse dynamics of the manipulator. The TDNN structure has so favorable characteristics that neurons can extract more dynamic information from both present and past input signals and perform more efficient learning. The TDNN neural network receives two normalized inputs, one of which is the reference trajectory signal and the other of which is the error signals from the PD controller. It is proved that the normalized inputs to the TDNN neural network can enhance the learning efficiency of the neural network. The proposed scheme was investigated for the planar robot manipulator with two joints by computer simulation.

• The Journal of the Korea Contents Association
• /
• v.13 no.4
• /
• pp.64-72
• /
• 2013

This paper proposes a dynamic gesture recognition algorithm using SVM(Support Vector Machine) which is suitable for multi-dimension classification. First of all, the proposed algorithm locates the beginning and end of the gestures on the video frames at the Kinect camera, spots meaningful gesture frames, and normalizes the number of frames. Then, for gesture recognition, the algorithm extracts gesture features using body parts' positions and relations among the parts based on the human model from the normalized frames. C-SVM for each dynamic gesture is trained using training data which consists of positive data and negative data. The final gesture is chosen with the largest value of C-SVM values. The proposed gesture recognition algorithm can be applied to the interactive storybook as gesture interface.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.9
• /
• pp.2558-2562
• /
• 1999

This paper proposes on the methods of noise removal and edge extraction which is done by eliminating the ambiguities of the image using normalization and minimizing the entropy. Pre-existing methods have their own peculiarities and limitations, such as gray level distributions change very slowly or two regions which having similar gray level distribution are touched. This affects on the post processing such as feature extraction, as a result, this leads to false-recognition or no-recognition. Therefore, this paper proposes on the methods which overcome these problems. Finally, the effectiveness of this paper is demonstrated by several experiments.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.601-604
• /
• 2021

본 논문에서는 모바일 디바이스의 카메라로부터 얻은 RGB이미지를 분석하여 장애물을 안정적으로 탐지할 수 있는 프레임워크를 제안한다. 본 논문에서는 장애물을 안정적으로 찾기 위해 RANSAC(Random Sample Consensus)기반의 다중 평면 방식을 이용한 위험감지 시스템을 제안한다. 우리의 접근 방식은 RGB영상으로부터 특징점(Feature point)을 추출하고, 특징점을 분석(Feature point analysis)하여 영상내의 평면을 감지한다. 복잡한 지형으로 인해 생성되는 다수의 평면을 RANSAC을 통해 단일 평면으로 정규화하고, 이로부터 특징점을 분류하기 위한 기준점을 계산한다. 모바일 디바이스의 위치와 회전 제약 없이 효과적으로 기준평면(Reference plane)을 탐색할 수 있고, 영상 내 특징점을 실시간으로 계산한다. 다양한 실험을 통해 기준평면과 장애물과의 거리를 파악하여 장애물을 효과적으로 분류하는 결과를 얻었다. 우리의 기법은 실세계에서의 위험요소를 감지하고 모바일 디바이스 사용자의 안전성 확보에 활용할 수 있을 거라 기대한다.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.5
• /
• pp.239-243
• /
• 2008

This paper proposes a new audio identification method based on a combination of the instantaneous and dynamic spectral features of the audio spectrum. Especially we propose the spectro-temporal subband centroids that are easy to compute and effective to summarize the instantaneous and dynamic spectral variations. Experimental results demonstrate that the identification performance can be greatly improved by combining both the spectral and the temporal subband centroids.