• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.653-662
• /
• 2006

In ubiquitous computing that is to build computing environments to provide proper services according to user's context, human being's emotion recognition based on facial expression is used as essential means of HCI in order to make man-machine interaction more efficient and to do user's context-awareness. This paper addresses a problem of rigidly basic emotion recognition in context-sensitive facial expressions through a new Bayesian classifier. The task for emotion recognition of facial expressions consists of two steps, where the extraction step of facial feature is based on a color-histogram method and the classification step employs a new Bayesian teaming algorithm in performing efficient training and test. New context-sensitive Bayesian learning algorithm of EADF(Extended Assumed-Density Filtering) is proposed to recognize more exact emotions as it utilizes different classifier complexities for different contexts. Experimental results show an expression classification accuracy of over 91% on the test database and achieve the error rate of 10.6% by modeling facial expression as hidden context.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1952-1953
• /
• 2011

본 논문에서는 다항식 기반 Radial Basis Function(RBF)신경회로망(Polynomial based Radial Basis function Neural Network)을 설계하고 이를 n-클래스 패턴 분류 문제에 적용한다. 제안된 다항식기반 RBF 신경회로망은 입력층, 은닉층, 출력층으로 이루어진다. 입력층은 입력 벡터의 값들을 은닉층으로 전달하는 기능을 수행하고 은닉층과 출력층사이의 연결가중치는 상수, 선형식 또는 이차식으로 이루어지며 경사 하강법에 의해 학습된다. Networks의 최종 출력은 연결가중치와 은닉층 출력의 곱에 의해 퍼지추론의 결과로서 얻어진다. 패턴분류기의 최적화는 PSO(Particle Swarm Optimization)알고리즘을 통해 이루어진다. 그리고 제안된 패턴분류기는 실제 얼굴인식 시스템으로 응용하여 직접 CCD 카메라로부터 입력받은 데이터를 영상 보정, 얼굴 검출, 특징 추출 등과 같은 처리 과정을 포함하여 서로 다른 등록인물의 n-클래스 분류 문제에 적용 및 평가되어 분류기로써의 성능을 분석해본다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.216-221
• /
• 2003

Emotions recognition is a topic on which little research has been done to date. This paper proposes a new method that can recognize the human s emotion from facial image by using eigenspace. To do so, first, we get the face image by using the skin color from the original color image acquired by CCD color camera. Second, we get the vector image which is projected the obtained face image into eigenspace. And then, we propose the method for finding out each person s identification and emotion from the weight of vector image. Finally, we show the practical application possibility of the proposed method through the experiment.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.173-182
• /
• 2009

In this paper, we studied about the extraction of the parameter and implementation of speechreading system to recognize the Korean 8 vowel. Face features are detected by amplifying, reducing the image value and making a comparison between the image value which is represented for various value in various color space. The eyes position, the nose position, the inner boundary of lip, the outer boundary of upper lip and the outer line of the tooth is found to the feature and using the analysis the area of inner lip, the hight and width of inner lip, the outer line length of the tooth rate about a inner mouth area and the distance between the nose and outer boundary of upper lip are used for the parameter. 2400 data are gathered and analyzed. Based on this analysis, the neural net is constructed and the recognition experiments are performed. In the experiment, 5 normal persons were sampled. The observational error between samples was corrected using normalization method. The experiment show very encouraging result about the usefulness of the parameter.

• The KIPS Transactions:PartA
• /
• v.12A no.1 s.91
• /
• pp.13-22
• /
• 2005

Similarly to the edges defined in a 2D image, we can define the geometric features representing the boundary of the distinctive parts appearing on 3D meshes. The geometric features have been used as basic primitives in several applications such as mesh simplification, mesh deformation, and mesh editing. In this paper, we propose geometric livewire and geometric livelane for extracting geometric features in a 3D mesh, which are the extentions of livewire and livelane methods in images. In these methods, approximate curvatures are adopted to represent the geometric features in a 3D mesh and the 3D mesh itself is represented as a weighted directed graph in which cost functions are defined for the weights of edges. Using a well-known shortest path finding algorithm in the weighted directed graph, we extracted geometric features in the 3D mesh among points selected by a user. In this paper, we also visualize the results obtained from applying the techniques to extracting geometric features in the general meshes modeled after human faces, cows, shoes, and single teeth.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.273-279
• /
• 2021

In this paper, we propose an algorithm that shortens the learning time by performing individual learning using partitioning the deep learning structure. The proposed algorithm consists of four processes: network classification origin setting process, feature vector extraction process, feature noise removal process, and class classification process. First, in the process of setting the network classification starting point, the division starting point of the network structure for effective feature vector extraction is set. Second, in the feature vector extraction process, feature vectors are extracted without additional learning using the weights previously learned. Third, in the feature noise removal process, the extracted feature vector is received and the output value of each class is learned to remove noise from the data. Fourth, in the class classification process, the noise-removed feature vector is input to the multi-layer perceptron structure, and the result is output and learned. To evaluate the performance of the proposed algorithm, we experimented with the Extended Yale B face database. As a result of the experiment, in the case of the time required for one-time learning, the proposed algorithm reduced 40.7% based on the existing algorithm. In addition, the number of learning up to the target recognition rate was shortened compared with the existing algorithm. Through the experimental results, it was confirmed that the one-time learning time and the total learning time were reduced and improved over the existing algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.7
• /
• pp.935-943
• /
• 1993

In this paper, robust recognition system for tilted facial image was developed. At first, standard facial image and lilted facial image are captured by CCTV camera and then transformed into binary image. The binary image is processed in order to obtain contour image by Laplacian edge operator. We trace and delete outermost edge line and use inner contour lines. We label four inner contour lines in order among the inner lines, and then we extract left and right eye with known distance relationship and with two eyes coordinates, and calculate slope information. At last, we rotate the tilted image in accordance with slope information and then calculate the ten distance features between element and element. In order to make the system invariant to image scale, we normalize these features with distance between left and righ eye. Experimental results show 88% recognition rate for twenty five face images when tilted degree is considered and 60% recognition rate when tilted degree is not considered.

• Review of KIISC
• /
• v.25 no.4
• /
• pp.43-50
• /
• 2015

바이오인식기술은 사람의 지문 얼굴 홍채 정맥 등 신체적 특징(Physiological characteristics) 또는 음성 서명 자판 걸음걸이 등 행동적 특징(Behavioral characteristics)을 자동화된 IT 기술로 추출 저장하여 다양한 IT 기기로 개인의 신원을 확인하는 사용자 인증기술이다. 2001년 미국의 911 테러사건으로 인하여 전 세계 국제공항 항만 국경에서 지문 얼굴 홍채 등 바이오정보를 이용한 출입국심사가 보편화됨과 동시에 ISO/IEC JTC1 SC37(바이오인식) 국제표준화기구를 중심으로 표준화가 급속도로 진행되어 왔다. 최근 들어 스마트폰 테블릿 PC 등 모바일기기에 지문 얼굴 등 바이오정보를 탑재하여 다양한 모바일 응용서비스를 가능하게 해주는 모바일 바이오인식 응용기술이 전 세계적으로 개발 보급되고, 삼성전자 페이팔 중심으로 바이오인식기술을 이용한 모바일 지급결제솔루션에 대한 사실표준화협의체인 FIDO, ITU-T SG17 Q9(텔레바이오인식) 국제표준화기구를 중심으로 표준화가 진행되고 있다. 특히 이러한 모바일 바이오인식기술은 스마트폰을 통한 비대면 인증기술 수단으로서 핀테크의 중요한 요소기술로 작용될 전망이다. 한편, 위조지문 등 전통적인 바이오인식 기술의 위변조 위협으로 인한 우려도 증폭됨에 따라 스마트워치 등 웨어러블 디바이스에서 살아있는 사람의 심박수(심전도), 뇌파 등의 생체신호를 측정하여 스마트폰을 통하여 개인을 식별하는 차세대 바이오인식기술로 진화중에 있다. 본고에서는 바이오인식기술의 변천사와 함께 국내외 모바일 바이오인식기술 동향과 표준화 추진현황을 살펴보고, 지난 2015년 5월 29일 발족한 KISA "모바일 생체신호 인증기술 표준연구회"를 통하여 뇌파 심전도 등생체신호를 이용한 차세대 바이오인식 기술 및 표준화 계획을 수립하여 향후 바이오인식기반의 비대면 인증기술에 대한 추진전략을 모색하고자 한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11C
• /
• pp.1140-1151
• /
• 2003

This paper proposes a face recognition method based on modified Otsu's binarization and Hu moment. Proposed method is robust to brightness, contrast, scale, rotation, and translation changes. As the proposed modified Otsu's binarization computes other thresholds from conventional Otsu's binarization, namely we create two binary images, we can extract higher dimensional feature vector. Here the feature vector has properties of robustness to brightness and contrast changes because the proposed method is based on Otsu's binarization. And our face recognition system is robust to scale, rotation, and translation changes because of using Hu moment. In the perspective of brightness, contrast, scale, rotation, and translation changes, experimental results with Olivetti Research Laboratory (ORL) database and the AR database showed that average recognition rates of conventional well-known principal component analysis (PCA) are 93.2% and 81.4%, respectively. Meanwhile, the proposed method for the same databases has superior performance of the average recognition rates of 93.2% and 81.4%, respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.397-404
• /
• 2013

This paper propose the hardware architecture of face detection hardware system using the AdaBoost algorithm. The proposed structure of face detection hardware system is possible to work in 30frame per second and in real time. And the AdaBoost algorithm is adopted to learn and generate the characteristics of the face data by Matlab, and finally detected the face using this data. This paper describes the face detection hardware structure composed of image scaler, integral image extraction, face comparing, memory interface, data grouper and detected result display. The proposed circuit is so designed to process one point in one cycle that the prosed design can process full HD($1920{\times}1080$) image at 70MHz, which is approximate $2316087{\times}30$ cycle. Furthermore, This paper use the reducing the word length by Overflow to reduce memory size. and the proposed structure for face detection has been designed using Verilog HDL and modified in Mentor Graphics Modelsim. The proposed structure has been work on 45MHz operating frequency and use 74,757 LUT in FPGA Xilinx Virtex-5 XC5LX330.