• Journal of Korea Multimedia Society
• /
• v.16 no.8
• /
• pp.927-933
• /
• 2013

Face detection algorithm of OpenCV recognizes the faces by Haar matching between input image and Haar features which are learned through a set of training images consisting of many front faces. Therefore the face detection method by Haar matching yields a high face detection rate for the front faces but not in the case of the pan and deformed faces. On the assumption that distributional characteristics of color histogram is similar even if deformed or side faces, a face detection method using the histogram pattern matching is proposed in this paper. In the case of the missed detection and false detection caused by Haar matching, the proposed face detection algorithm applies the histogram pattern matching with the correct detected face area of the previous frame so that the face region with the most similar histogram distribution is determined. The experiment for evaluating the face detection performance reveals that the face detection rate was enhanced about 8% than the conventional method.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.1
• /
• pp.1-7
• /
• 2011

Terrain, building location and area, and building shape information is in need of implementing 3D map. This paper proposes a method of extracting a building area by an improved semi-automatic snake algorithm. The method consists of 3-stage: pre-processing, initializing control points, and applying an improved snake algorithm. In the first stage, after transforming a satellite image to a gray image and detecting the approximate edge of the gray image, the method combines the gray image and the edge. In the second stage, the user looks for the center point of a building and the system sets the circular or rectangular initial control points by an procedural method. In the third stage, the enhanced snake algorithm extracts the building area. In particular, this paper sets the one tenn of the snake in a new way in order to use the proposed method for specializing building area extraction. Finally, this paper evaluated the performance of the proposed method using sky view satellite image and it showed that the matching percentage to the exact building area is 75%.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.5
• /
• pp.470-475
• /
• 2009

This paper is the study which is head tracker using pattern matching. Proposal algorithm obtains initial attitude of head tracker using pattern matching. Optical head tracker consists of infrared LEDs(features) which are attached helmet as pattern, stereo infrared cameras. Proposal algorithm analyzes patterns by error rate of feature distance and estimates feature characteristic number. Initial attitude of head tracker is obtained to compare map data and feature characteristic number.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.117-120
• /
• 2017

본 논문은 스테레오 영상을 이용하여 3 차원 영상을 제공하기 위한 과정에서 중요한 변위 지도 생성 과정의 개선을 목적으로 한다. 변위 지도란, 서로 다른 시점의 두 영상 내에 매칭되는 대응점을 찾고 이와 같은 대응점들 간의 차를 통해 상대적 거리정보를 얻은 후, 이를 정규화하여 픽셀 값으로 나타낸 지도이다. 이에 본 논문에서는 변위 지도 생성 시, 물체들 간 대응점 매칭율을 높이기 위해 물체들의 외곽을 보존하여 형태를 뚜렷하게 하는 전처리 과정을 제안한다. 제안하는 방안은 제한 적응 히스토그램 평활화를 통해 물체들의 세부적인 특징들을 부각시키고, 양방향 필터를 통해 외각을 뚜렷하게 하는 전처리 과정을 포함한다. 본 논문에서는 제한 적응 히스토그램 평활화와 양방향 필터의 처리 과정을 분석하고, 실험결과를 통해 제안하는 전처리 과정을 검증하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.990-991
• /
• 2013

본 연구에서는 모바일 환경에서 장시간 심전도 계측 시 발생하는 무선 및 배터리의 제한적인 자원의 문제점을 해결하기 위하여 낮은 연산량과 높은 압축률을 가지는 템플릿 매칭 기반의 압축 알고리즘을 구현하였다. 템플릿 매칭 기법을 이용한 심전도 데이터 압축은 심전도의 특징점인 R-peak를 검출하여 템플릿을 생성하고 이후 입력되는 심전도 신호와 유사성을 판단하여 해당되는 템플릿의 정보만 저장하고 전송하는 방법이다. 구현된 알고리즘의 성능평가를 위하여 MIT-BIH Normal Sinus Rhythm Database의 10개 레코드에서 각각 10분간 데이터를 추출하여 성능평가를 수행하였으며, 이때, 압축률과 복원율 오차의 평균이 각각 7.94% 와 5.33%의 성능을 나타내었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06c
• /
• pp.4-6
• /
• 2006

최근들어 웹 서비스의 수가 증가하면서 필요한 서비스를 정확하게 탐색하는 것이 중요한 이슈가 되고 있다. 이를 위해 온톨로지에 기반한 시맨틱 웹 서비스 탐색에 관한 연구들이 진행되었다. 그러나 기존 연구는 제한된 개념 해석 방식을 사용하고, 명확한 개념 기술 방법을 제공하지 않기 때문에 매칭 오류가 발생 할 수 있다. 본 논문에서는 이러한 문제를 해결하기 위해 통합 개념 모델과 이를 적용한 웹 서비스 탐색 방법을 제안한다. 제안된 통합 개념 모델은 개념 타입, 클래스, 프로퍼티를 이용한 유연하고 명확한 개념 기술 방벌을 제공한다. 제안된 탐색 방법은 통합 개념 모델에 기반하여 서비스와 사용자 요구사항을 기술하고 매칭을 수행한다. 또한 복합 매칭을 지원하여 보다 정교한 서비스 탐색이 가능하다. 다양한 형태의 사용자 요구사항에 대해 실험한 결과, 제안된 방법은 기존 연구보다 더 높은 정확률과 재현율을 보였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2619-2625
• /
• 2011

The GPS technique widely used recently in car navigation system has two problems that are unavailability in urban canyons and inherent positional error rate. The one has been studied and solved in many literatures. However, the other still leads to incorrect locational information in some area, especially parallel roads. This paper proposes and implements a system to recognize lane of moving vehicle based on images obtained from in-vehicle networks or other devices. The proposed system utilizes a real-time image matching algorithm which determines the direction of moving vehicle in parallel section of road. It also employs a method for accuracy improvement. The results obtained from experimental test on real-time navigation show that the proposed systems works well and the accuracy increases.

• Science of Emotion and Sensibility
• /
• v.18 no.1
• /
• pp.39-48
• /
• 2015

It is known that P300-based concealed information test (P300 CIT) was not greatly affected by the traditional countermeasures. This study was to test whether P300 CIT is affected by the new countermeasures. We used three types of countermeasures. First type was a sequential countermeasure in which participants had to respond in alternating ways to irrelevants by pressing the left index finger covertly when the encountered irrelevant firstly, by wiggling the right big toe inside the shoe when encountered irrelevant secondly, by imaging his or her mother's name when encountered irrelevant thirdly, and by imaging his or her father's name when encountered irrelevant fourthly until all stimuli were presented. Second type was a partial matching and physical countermeasure. Participants in this type were asked to press the left index finger imperceptibly after one of the irrelevants and wiggle the right big toe after another of the irrelevants. Third type was a partial matching and mental countermeasure. Participants were required to imagine mother's name for one irrelevant and father's name for another irrelevant. The results showed that contrary to our expectation, the use of sequential countermeasure increased the detection rate from 77% to 92%. The partial matching countermeasure had a negative effect on P300 CIT. The physical countermeasure decreased the detection rate from 77% to 46%, and the mental countermeasure decreased the detection rate from 100% to 69%. The necessity for the development of methods to prevent or detect countermeasure is discussed.

• Journal of Korea Multimedia Society
• /
• v.10 no.2
• /
• pp.147-169
• /
• 2007

Semantic Web Services Discovery matches between users' requirements and the ontological description of Web Services. However, concepts of an ontology can be interpreted differently according to a point of view. Previous works are limited in interpreting concepts. Since they lack a precise scheme of describing the advertisements and requirements of services and users, respectively, and even do not support a sophisticated matching, semantic mismatches may occur. This paper presents a sophisticated method of discovering Web services. The proposed method facilitates specifying semantics precisely and flexibly based on a proposed integrated concept model. Additionally, more sophisticated discovery is supported by computing complex matchings with many-to-many relationships. Experimental results show that the proposed method performs more efficiently for various kinds of user requests, compared with previous works.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.524-526
• /
• 2003

지문은 사람에 있어서 유일한 특징과 변하지 않는 특성으로 인하여 개인의 인증이나 식별에 많이 사용되고 있다. 이러한 특성을 가진 지문을 스마트카드의 인증과정에 이용함으로써 보안성을 높이고 사용에 편리함을 추가할 수 있다. 본 논문에서는 스마트카드와 서비스시스템 간에 지문을 이용한 인증시스템을 제안하였다. 제안된 시스템은 카드와 서비스시스템이 각각 특징점 정보와 방향성정보를 매칭 함으로서 스마트카드의 계산부하를 줄일 수 있고, 본인 거부율과 타인 수락율의 오류를 줄일 수 있다.