• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.337-339
• /
• 2003

얼굴인식은 얼굴 요소간의 지형적 특징보다 얼굴 영역 영상을 그대로 사용하여 인식하는 외관기반(appearance-based) 방법이 선호된다. 이때, 배경의 영향을 배제하기 위해 얼굴요소정보를 포함하는 최소 사각 영역을 사용하거나, 타원 마스크를 적용한다. 그러나, 이러한 전처리 방법은 개인별 외관특징으로써의 얼굴 윤곽 정보를 활용하지 못하게 한다. 본 논문에는 얼굴의 윤곽정보를 추출하기 위한 전처리 절차를 제안하고, ORL 얼굴 데이터에 대한 인식률 실험을 통해 제안하는 방법이 얼굴인식 성능을 크게 향상시킬 수 있음을 보인다.

• Journal of Korea Multimedia Society
• /
• v.13 no.4
• /
• pp.487-495
• /
• 2010

It has been required to develop an accurate and reliable evaluation method for the performance of biometric systems as their use is getting popular. Among a number of biometric systems, face recognition is one of the most widely used techniques and this leads to develop a stable evaluation method for face recognition systems in order to standardize the performance of face recognition systems. However, it is considered as a difficult task to evaluation such systems due to a large number of factors that affect their performance. Thus, it may be infeasible to take into account all the environmental factors that are related to the performance of face recognition systems and this naturally suggests an evaluation method for the overall performance based on scenarios. In this paper, we have analyzed environmental factors that are related to the performance of general face recognition systems and proposed their evaluation method taking into account those factors. We have proposed an evaluation method based on scenario that considers the combination of individual environment factors instead of evaluating the performance of face recognition systems regarding each factor. Indeed, we have presented examples on the evaluation of face recognition systems based on scenario that takes into account overall environmental factors.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.373-376
• /
• 2011

얼굴 영상에서 구성요소(눈썹, 눈, 코, 입 등)의 존재에 따라 보는 사람의 얼굴 인식 정확도는 큰 영향을 받는다. 이는 인간의 뇌에서 얼굴 정보를 처리하는 과정은 얼굴 전체 영역 뿐만 아니라, 부분적인 얼굴 구성요소의 특징들도 고려함을 말한다. 비음수 행렬 분해(NMF: Non-negative Matrix Factorization)는 이러한 얼굴 영역에서 부분적인 특징들을 잘 표현하는 기저영상들을 찾아내는데 효과적임을 보여주었으나, 각 기저영상들의 중요도는 알 수 없었다. 본 논문에서는 NMF로 찾아진 기저영상들에 대응되는 인코딩 정보를 SLR(Sparse Logistic Regression)을 이용하여 성별 인식에 중요한 부분 영역들을 찾고자 한다. 실험에서는 주성분분석(PCA)과 비교를 통해 NMF를 이용한 기저영상 및 특징 벡터 추출이 좋은 성능을 보여주고, 대표적 이진 분류 알고리즘인 SVM(Support Vector Machine)과 비교를 통해 SLR을 이용한 특징 벡터 선택이 나은 성능을 보여줌을 확인하였다. 또한 SLR로 확인된 각 기저영상에 대한 가중치를 통하여 인식 과정에서 중요한 얼굴 영역들을 확인할 수 있다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1998.11a
• /
• pp.25-29
• /
• 1998

본 논문은 얼굴 인식 또는 표정 인식 분야에 있어서 중요한 특징을 나타내는 얼굴과 얼굴의 주요소인 눈과 입, 눈썹의 영역 추출 및 그의 윤곽선·추출에 관한 방법을 제시한다. 얼굴요소의 영역 추출은 엣지 정보와 이진화 영상을 병합하여 이용한 프로젝션 분석을 통하여 얼굴 및 각 얼굴요소를 포함하는 최소포함사각형(MER: Minimum Enclosing Rectangle)을 추출하였다. 얼굴 영상에 관련된 윤곽선 연구에는 가변 템플릿(Deformable Template), 스네이크(Snakes: Active Contour Model)를 이용하는 연구들이 이루어지고 있는데 가변 템플릿 방법은 수행시간이 느리고 추출된 윤곽선의 모양이 획일 된 모양을 갖는 특성이 있다. 본 논문에서는 사람마다 얼굴요소의 모양의 개인차가 반영되고 빠른 수렴을 할 수 있는 스네이크 모델을 정의하여 눈, 입, 눈썹, 얼굴의 윤곽선 추출 실험을 하였다. 또한 스네이크는 초기 윤곽선의 설정이 윤곽선의 추출 곁과에 큰 영향을 미치므로, 초기 윤곽선의 설정 과정이 매우 중요하다. 본 논문에서는 얼굴 및 각 얼굴요소를 포함하는 각각의 최소 포함 사각형(MER)을 추출하고, 이 추출된 MER 내에서 얼굴 및 각 얼굴요소의 일반적인 모양을 초기 윤곽선으로 설정하는 방법을 사용하였다. 실험결과 눈, 입, 얼굴의 MER의 추출은 모두 성공하였고, 눈썹이 흐린 사람들의 경우에만 눈썹의 MER추출이 졸지 않았다. 추출된 MER을 기반으로 하여 스네이크 모델을 적용한 결과, 눈, 입, 눈썹, 얼굴의 다양한 모양을 반영한 윤곽선 추출 결과를 보였다. 특히 눈의 경우는 1차 유도 엣지 연산자에 의한 엣지 와 2차 유도 연산자를 이용한 영점 교차점(Zero Crossing)과 병합한 에너지 함수를 설정하여 보다 더 나은 윤곽선 추출 결과를 보였다. 얼굴의 윤곽선의 경우도 엣지 값과 명도 값을 병합한 에너지 함수에 의해 비교적 정확한 결과를 얻을 수 있었다.잘 동작하였다.되는 데이타를 입력한후 마우스로 원하는 작업의 메뉴를 선택하면 된다. 방법을 타액과 혈청내 testosterone 농도 측정에 응용하여 RIA의 결과와 비교하여 본 바 상관관계가 타액에서 r=0.969, 혈청에서 r=0.990으로 두 결과가 잘 일치하였다. 본 실험에서 측정된 한국인 여성의 타액내 testosterone농도는 107.7$\pm$12.0 pmol／l이었고, 남성의 타액내 농도는 274.2$\pm$22.1 pmol／l이었다. 이상의 결과로 보아 본 연구에서 정립된 EIA 방법은 RIA를 대신하여 소규모의 실험실에서도 활용할 수 있을 것으로 사려된다.또한 상실기 이후 배아에서 합성되며, 발생시기에 따라 그 영향이 다르고 팽창과 부화에 관여하는 것으로 사료된다. 더욱이, 조선의 ${\ulcorner}$구성교육${\lrcorner}$이 조선총독부의 관리하에서 실행되었다는 것을, 당시의 사범학교를 중심으로 한 교육조직을 기술한 문헌에 의해 규명시켰다.nd of letter design which represents -natural objects and was popular at the time of Yukjo Dynasty, and there are some documents of that period left both in Japan and Korea. "Hyojedo" in Korea is supposed to have been influenced by the letter design. Asite- is also considered to have been "Japanese Letter Jobcheso." Therefore, the purpose of this study is to look into the origin of the letter designs in the Chinese character culture

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.70-78
• /
• 2007

The performance of face recognition is greatly affected by the illumination effect because intra-person variation under different lighting conditions can be much bigger than the inter-person variation. In this paper, we propose an illumination robust face recognition by separating identity factor and illumination factor using the symmetric bilinear models. The translation procedure in the bilinear model requires a repetitive computation of matrix inverse operation to reach the identity and illumination factors. Sometimes, this computation may result in a nonconvergent case when the observation has an noisy information. To alleviate this situation, we suggest a ridge regressive bilinear model that combines the ridge regression into the bilinear model. This combination provides some advantages: it makes the bilinear model more stable by shrinking the range of identity and illumination factors appropriately, and it improves the recognition performance by reducing the insignificant factors effectively. Experiment results show that the ridge regressive bilinear model outperforms significantly other existing methods such as the eigenface, quotient image, and the bilinear model in terms of the recognition rate under a variety of illuminations.

• The Journal of the Korea Contents Association
• /
• v.9 no.6
• /
• pp.1-8
• /
• 2009

There are a lot of influences, such as location of camera, luminosity, brightness, and direction of light, which affect the performance of 2-dimensional image recognition. This paper suggests an adaptive method for face-image recognition in noisy environments using evolvable filtering and feature extraction which uses one sample image from camera. This suggested method consists of two main parts. One is the environmental-adjustment module which determines optimum sets of filters, filter parameters, and dimensions of features by using "steady state genetic algorithm". The other another part is for face recognition module which performs recognition of face-image using the previous results. In the processing, we used Gabor wavelet for extracting features in the images and k-Nearest Neighbor method for the classification. For testing of the adaptive face recognition method, we tested the adaptive method in the brightness noise, in the impulse noise and in the composite noise and verified that the adaptive method protects face recognition-rate's rapidly decrease which can be occurred generally in the noisy environments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.165-170
• /
• 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%.

• 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%.

• Journal of KIISE:Software and Applications
• /
• v.27 no.7
• /
• pp.731-741
• /
• 2000

This paper proposes a method to detect a facial region and extract facial features which is crucial for visual recognition of human faces. In this paper, we extract the MER(Minimum Enclosing Rectangle) of a face and facial components using projection analysis on both edge image and binary image. We use an active contour model(snakes) for extraction of the contours of eye, mouth, eyebrow, and face in order to reflect the individual differences of facial shapes and converge quickly. The determination of initial contour is very important for the performance of snakes. Particularly, we detect Minimum Enclosing Rectangle(MER) of facial components and then determine initial contours using general shape of facial components within the boundary of the obtained MER. We obtained experimental results to show that MER extraction of the eye, mouth, and face was performed successfully. But in the case of images with bright eyebrow, MER extraction of eyebrow was performed poorly. We obtained good contour extraction with the individual differences of facial shapes. Particularly, in the eye contour extraction, we combined edges by first order derivative operator and zero crossings by second order derivative operator in designing energy function of snakes, and we achieved good eye contours. For the face contour extraction, we used both edges and grey level intensity of pixels in designing of energy function. Good face contours were extracted as well.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.1
• /
• pp.85-92
• /
• 2020

Deep learning shows outstanding performance in image and video analysis, such as object classification, object detection and semantic segmentation. In this paper, it is analyzed that the performances of deep learning models can be affected by characteristics of train dataset. It is proposed as a method for selecting activation function and optimization algorithm of deep learning to classify facial expression. Classification performances are compared and analyzed by applying various algorithms of each component of deep learning model for CK+, MMI, and KDEF datasets. As results of simulation, it is shown that genetic algorithm can be an effective solution for optimizing components of deep learning model.