• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.3 s.309
• /
• pp.17-24
• /
• 2006

In this paper, an algorithm for anchor frame detection in news video is proposed, which consists of four steps. In the first step, the cumulative histogram method is used to detect shot boundaries in order to segment a news video into video shots. In the second step, skin color information is used to detect face regions in each shot boundary. In the third step, color information of upper body regions is used to extract anchor object, which produces candidate anchor frames. Then, from the candidate anchor frames, a graph-theoretic cluster analysis algorithm is utilized to classify the news video into anchor-person frames and non-anchor frames. Experiment results have shown the effectiveness of the proposed algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.5
• /
• pp.361-367
• /
• 2003

We propose an algorithm to detect the face region using a variable ellipsoidal mask and a neural network. Since outlines of human faces are similar to ellipsoid, the ellipsoidal mask that has the fixed ratio of major and minor axis can be used to detect the candidate area. The positions of eyes and lips are extracted in this candidate area, and then the morphological analysis is applied to make features which are consist of six parameters, such as the geometrical ratio of eyes and lips. A back-propagation neural network is used as a classifier to determine the most possible face region. The experimental result is conducted to verify its efficiency compared with those of previous works.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.59-62
• /
• 2016

본 논문에서는 실종자 데이터베이스에 등록된 실종자에 대한 색인으로 텍스트 기반의 통제 색인만을 사용할 때 발생하는 문제점에 대한 해결책을 다룬다. 기존 실종자를 등록할 때 함께 등록하게 되는 실종자에 대한 이미지는 정형화 할 수 없어 실종자 조회에 사용될 수 없었다. 이러한 문제점을 해결하고자 OpenCV와 TensorFlow 를 이용하여 영상의 유사도를 추출함으로써 실종자의 이미지를 정형화시켜 유의미한 정보로 변경하여 사용하고자 하는 방법을 제안한다.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.60-62
• /
• 2005

In this study, the automatic tracking algorithm tracing a human face is proposed by using YCbCr color coordinated information and its thermal properties expressed in terms of thermal indexes in an infra-red image. The facial candidates are separately estimated in CbCr color and infra-red domain, respectively with applying the morphological image processing operations and the geometrical shape measures for fitting the elliptical features of a human face. The identification of a true face is accomplished by logical 'AND' operation between the refined image in CbCr color and infra-red domain.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.575-578
• /
• 1999

The principal features of a face are as follows : skin-tone, symmetry, and requisites such as shape of ellipse, eyes, nose, mouth. Also, faces have different size, various shape and position. In case of application of face recognition and detection without preprocessing, efficiency of the performance is decreased. In addition, face itself, complex background, image quality, etc. are included. Therefore, previous face recognition methods are implemented on the base of specific constraints of the face image. In this paper, we propose the efficient and automatic face detection algorithm for minimizing influence such as complex background, image quality, etc. This face detection technique consists of skin-tone, candidate face region and face region extractions.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.531-535
• /
• 1999

Automatic human face detection in a complex background is one of the difficult problems. In this paper, we propose an effective and robust automatic face detection approach that can locate the face region in natural scene images when the system is used as a pre-processor of a face recognition system . We use two natural and powerful visual cues, the skin color and the eyes. In the first step of the proposed system, the method based on the human skin color space by selecting flesh tone regions using normalized r-g space in color images. In the next step, we extract eye features by calculating moments and using geometrical face model. Experimental results demonstrate that the approach can efficiently detect human faces and satisfactory deal with the problems caused by bad lighting condition, skew face orientation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.719-722
• /
• 2016

운전자의 주의력 감쇠는 교통사고 요인에 있어서 큰 비중을 차지한다. 주의력 감쇠는 무선 통화, 기기 조작, 졸음으로 나타날 수 있는데 자동차 대형사고의 대부분은 졸음운전으로 인하여 일어나며, 졸음운전 시에는 운전자의 운전조작 및 방어 조작 능력이 현저하게 저하한다. 본 시스템은 카메라로부터 실시간으로 영상 데이터를 입력 받아 처리하여 운전자의 졸음 상태를 인식하는 시스템으로 운전자에게 졸음방지 기능을 제공한다. Haar-Like Feature cascade classifier 방법을 사용하여 얼굴 및 눈 영역 검출을 하였고 Open Eye, Closed Eye가 학습된 MLP(Multi-Layer Perceptron)를 이용해 눈 깜박임을 인식하여 PERCLOS(Percentage of Eye Close)방법으로 졸음을 판단하였다. 본 논문에서 제안한 방법의 인식률의 정확도를 검증하기 위해 인식률 테스트를 하였다.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.9
• /
• pp.577-579
• /
• 2005

In this study, the automatic tracking algorithm tracing a human face is proposed by using YCbCr color coordinated information and its thermal properties expressed in terms of thermal indexes in an infra-red image. The facial candidates are separately estimated in CbCr color and infra-red domain, respectively with applying the morphological image processing operations and the geometrical shape measures for fitting the elliptical features of a human face. The identification of a true face is accomplished by logical 'AND' operation between the refined image in CbCr color and infra-red domain.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06b
• /
• pp.88-91
• /
• 2010

정보통신망 및 멀티미디어 기술의 발전으로 인해 정보의 형태는 단순한 텍스트 데이터에서 멀티미디어 데이터로 전환되고 있다. 멀티미디어 기술은 저장, 재생, 압축 등 관련 기술의 빠른 발전과 미디어의 사회, 문화적 역할이 계속 증가함에 따라 우리 사회 전반에 걸쳐 매우 광범위하게 사용되고 있으며, 이로 인해 동영상 검색등의 많은 검색을 요구 하고 있으나, 동영상 검색의 문제점은 생산되는 컨텐츠에서 동영상이 가지고 있는 비중은 계속해서 높아지지만 쌓아진 데이터를 검색하기엔 몇 가지 문제점이 있다. 첫 번째는 데이터의 중복성이고 두 번째는 제목, 내용 그리고 Keyword가 일치하지 않으며, 세 번째는 저자권 침해 등이 있다. 본 연구에서는 본 논문에서는 빠르게 변화되고 있는 정보화 시대에 맞게 동영상에서 음성과 얼굴영역을 검출하여, 검색 시 효율적이고 정확한 데이터의 검색이 이루어 질 수 있도록 검색 알고리즘을 제안하고 소개하며, 이중 두 번째의 문제점인 제목, 내용 그리고 Keyword의 불일치한 점에 두어 검색 시 영상의 이미지 검색과 음성을 통하여 keyword를 찾아 효율적이고 검색율의 높일 방법을 연구한다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.4
• /
• pp.9-18
• /
• 2011

In this paper, we propose a method which recognizes human activity using model-based gaze direction estimation in an indoor environment. The method consists of two steps. First, we detect a head region and estimate its gaze direction as prior information in the human activity recognition. We use color and shape information for the detection of head region and use Bayesian Network model representing relationships between a head and a face for the estimation of gaze direction. Second, we recognize event and scenario describing the human activity. We use change of human state for the event recognition and use a rule-based method with combination of events and some constraints. We define 4 types of scenarios related to the gaze direction. We show performance of the gaze direction estimation and human activity recognition with results of experiments.