• 로봇학회논문지
• /
• 제1권1호
• /
• pp.66-72
• /
• 2006

In face recognition, learning speed of face is very important since the system should be trained again whenever the size of dataset increases. In existing methods, training time increases rapidly with the increase of data, which leads to the difficulty of training with a large dataset. To overcome this problem, we propose SVDD (Support Vector Domain Description)-based learning method that can learn a dataset of face rapidly and incrementally. In experimental results, we show that the training speed of the proposed method is much faster than those of other methods. Moreover, it is shown that our face recognition system can improve the accuracy gradually by learning faces incrementally at real environments with illumination changes.

• 한국정보통신학회논문지
• /
• 제24권1호
• /
• pp.50-56
• /
• 2020

현재 심층 신경망 이론 및 응용 연구의 빠른 개발로 얼굴 인식의 효과가 향상되고 있다. 그러나 심층 신경망 계산의 복잡성과 탐지 환경의 복잡성으로 인해 얼굴을 빠르고 정확하게 감지하는 방법이 주요 문제가 된다. 이 논문은 FDDB, LFW 및 FaceScrub 공개 데이터 세트를 훈련 표본을 사용하는 단순한 MTCNN 모델을 기반으로 둔다. MTCNN 모델을 분류하고 소개하면서 학습 훈련 속도를 높이고 성능을 향상하는 방법을 모색합니다. 본 논문에서는 다이내믹 이미지 피라미드 기술을 이용하여 기존 이미지 Pyramid 기술을 대체하여 샘플을 분할하고 MTCNN 모델의 OHEM을 훈련에서 제거하여 훈련 속도를 향상시켰다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• 한국응급구조학회지
• /
• 제24권3호
• /
• pp.55-63
• /
• 2020

Purpose: This study aimed to establish effective training strategies and methods by comparing the effects of 360° virtual reality video and first-person video in non-face-to-face practical lectures. Methods: This crossover study, implemented May 18-31, 2020, included 27 participants. We compared 360° virtual reality video and first-person video. SPSS version 25.0 was used for statistical analysis. Results: The 360° virtual reality video had a higher score of experience recognition (p=.039), vividness (p=.045), presence (p=.000), fantasy factor (p=.000) than the first-person video, but no significant difference was indicated for satisfaction (p=.348) or interest (p=.441). Conclusion: 360° virtual reality video and first-person video can be used as training alternatives to achieve the standard educational objectives in non-face-to-face practical lectures.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 SMICS 2004 International Symposium on Maritime and Communication Sciences
• /
• pp.106-109
• /
• 2004

Many reported methods assume that the faces in an image or an image sequence have been identified and localization. Face detection from image is a challenging task because of variability in scale, location, orientation and pose. In this paper, we present an efficient linear discriminant for multi-view face detection. Our approaches are based on linear discriminant. We define training data with fisher linear discriminant to efficient learning method. Face detection is considerably difficult because it will be influenced by poses of human face and changes in illumination. This idea can solve the multi-view and scale face detection problem poses. Quickly and efficiently, which fits for detecting face automatically. In this paper, we extract face using fisher linear discriminant that is hierarchical models invariant pose and background. We estimation the pose in detected face and eye detect. The purpose of this paper is to classify face and non-face and efficient fisher linear discriminant..

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3172-3193
• /
• 2018

Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.

• 한국방사선학회논문지
• /
• 제14권7호
• /
• pp.923-930
• /
• 2020

2020년도는 COVID-19 위기 상황으로 인하여 불가피하게 전면 비대면 교육을 시행하게 되었다. 연구자는 방사선사면허대비 전국 보건 계열 방사선과 3학년, 방사선학과 4학년 학생들이 면허시험을 앞두고 실시한 대면 교육과 비대면 모의시험(2019년 1.2회, 2020년 1.2회)의 성적을 알아보기 위하여 전국 방사선학과 및 방사선과 48개 대학 중 5개의 대학을 선정하여 대면 교육과 비대면 교육(2019년 1,2회, 2020년 1,2회)의 성적을 1회 모의고사 시험에 대면 교육과 비대면 교육(2019년 1회, 2020년 1회)의 성적을 비교하여, 비모수 검정으로 통계를 분석한 결과, 이론(Z=-2.023, p<0.05), 응용(Z=-2.023, p<0.05), 실기(Z=-2.023, p<0.05) 모두 성적에 차이가 있는 것으로 나타났다. 2회 모의고사 시험에 대면 교육과 비대면 교육 (2019년 2회, 2020년 2회)의 성적을 비교하여, 비모수 검정으로 통계를 분석한 결과, 이론(Z=-2.023, p<0.05), 응용(Z=-2.023, p<0.05), 실기(Z=-1.753, p<0.05) 성적에 차이가 있는 것으로 나타났다. 모의고사 시험의 결과 비대면 교육이 대면교육에 비교해 성적이 저조함에 따라 강의 방법을 달리하거나, 학생들과 소통할 수 있는 다양한 교육 방법을 병행해야 할 것으로 사료된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2720-2736
• /
• 2013

Multi-view face detection has become an active area for research in the last few years. In this paper, a novel multi-view human face detection algorithm based on improved real Adaboost is presented. Real Adaboost algorithm is improved by weighted combination of weak classifiers and the approximately best combination coefficients are obtained. After that, we proved that the function of sample weight adjusting method and weak classifier training method is to guarantee the independence of weak classifiers. A coarse-to-fine hierarchical face detector combining the high efficiency of Haar feature with pose estimation phase based on our real Adaboost algorithm is proposed. This algorithm reduces training time cost greatly compared with classical real Adaboost algorithm. In addition, it speeds up strong classifier converging and reduces the number of weak classifiers. For frontal face detection, the experiments on MIT+CMU frontal face test set result a 96.4% correct rate with 528 false alarms; for multi-view face in real time test set result a 94.7 % correct rate. The experimental results verified the effectiveness of the proposed approach.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1464-1479
• /
• 2018

In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn't need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFacel, which uses pairs of face images as inputs and maps them to target space so that the $L_2$ norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.

• 한국멀티미디어학회논문지
• /
• 제9권10호
• /
• pp.1266-1275
• /
• 2006

본 논문은 AdaBoost(Adaptive Boosting)알고리즘을 이용한 실시간 얼굴 검출 및 추적에 패한 기법을 제안한다. 얼굴 검출은 8종류의 간단한 웨이블릿 특징 모형을 이용한다. 각각의 특징들은 $20{\times}20$의 훈련 영상에서 다양한 크기와 위치로 배치되어 초기의 특징 집합을 구성한다. 초기의 특징 집합과 훈련 영상은 AdaBoost알고리즘의 입력으로 사용된다. AdaBoost알고리즘의 기본원리는 약한 분류기를 선형적으로 결합하여 최종적으로는 계층적 구조를 갖는 강한 분류기론 생성하는 것이다. 본 논문에서는 AdaBoost알고리즘에서 훈련 영상과 초기의 특징 집합 간에 이루어지는 반복적 계산량을 줄이기 위해 SAT(Summed-Area Table) 기법을 이용하였다. 얼굴 추적은 Pan-Tilt카메라를 통해 동적으로 가시 영역을 확장해 가면서 검출된 영역의 위치와 크기정보를 이용하여 실시간으로 이루어진다. 검출된 얼굴 영역의 중심을 전체 영상의 중심으로 이동하는 방법을 사용하였다. 실험결과 92.5%의 얼굴 검출율과 평균 12프레임의 얼굴 추적속도를 얻었다.