• ETRI Journal
• /
• 제37권2호
• /
• pp.395-405
• /
• 2015

We address the problem of uncooperative person recognition through continuous monitoring. Multiple modalities, such as face, height, clothes color, and voice, can be used when attempting to recognize a person. In general, not all modalities are available for a given frame; furthermore, only some modalities will be useful as some frames in a video sequence are of a quality that is too low to be able to recognize a person. We propose a method that makes use of stochastic information updates of temporal modalities and environment estimators to improve person recognition performance. The environment estimators provide information on whether a given modality is reliable enough to be used in a particular instance; such indicators mean that we can easily identify and eliminate meaningless data, thus increasing the overall efficiency of the method. Our proposed method was tested using movie clips acquired under an unconstrained environment that included a wide variation of scale and rotation; illumination changes; uncontrolled distances from a camera to users (varying from 0.5 m to 5 m); and natural views of the human body with various types of noise. In this real and challenging scenario, our proposed method resulted in an outstanding performance.

• 한국멀티미디어학회논문지
• /
• 제19권5호
• /
• pp.881-889
• /
• 2016

Ocular region recently emerged as a new biometric trait for overcoming the limitations of iris recognition performance at the situation that cannot expect high user cooperation, because the acquisition of an ocular image does not require high user cooperation and close capture unlike an iris image. This study proposes a new method for ocular image recognition based on BRISK (binary robust invariant scalable keypoints). It uses the distance ratio of the two nearest neighbors to improve the accuracy of the detection of corresponding keypoint pairs, and it also uses geometric constraint for eliminating incorrect keypoint pairs. Experiments for evaluating the validity the proposed method were performed on MMU public database. The person recognition rate on left and right ocular image datasets showed 91.1% and 90.6% respectively. The performance represents about 5% higher accuracy than the SIFT-based method which has been widely used in a biometric field.

• 한국정보통신학회논문지
• /
• 제25권9호
• /
• pp.1152-1157
• /
• 2021

본 논문에서는 아파트 공동현관의 출입통제에 적합한 얼굴인식 방법을 제안한다. 제안 방법은 기존의 얼굴인식 방식과는 다르게 별도의 수동 얼굴 등록 과정을 거치지 않는다. 건물에 있는 인물(예 : 거주자)이 공동현관문을 통해 외출하면 외출 시점에 촬영된 영상에서 자동 추출된 얼굴데이터(얼굴영상 및 특징)를 거주자 데이터베이스에 등록한다. 외출한 인물이 귀가하여 다시 공동현관문을 통해 출입하고자 하면 출입 시점에 촬영된 영상에서 추출된 얼굴데이터를 거주자 데이터베이스에 등록된 얼굴데이터와 대조하여 동일 인물이 식별되는 경우에만 공동현관문을 개방하여 출입을 허용한다. 동일 인물로 매칭된 얼굴데이터는 거주자 데이터베이스에서 바로 삭제되며, 외출할 때마다 새롭게 추출된 최신 얼굴데이터로 등록 갱신된다. 따라서 항상 최신 얼굴 데이터에 기반하여 얼굴 대조가 이루어져 동일인물을 식별하기에 유리하다. 제안 방법에 대해 구현의 용이함을 검증하기 위해 PC 2대와 포털에서 제공하는 클라우드를 활용하여 파이썬 기반의 얼굴인식 기능을 구현하였다. 또한 제안방법의 보안을 강화하기 위한 아이디어를 제시하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.106-109
• /
• 2003

Many diverse methods have been developing in the field of biometric identification as human-friendliness has been emphasized in the intelligent system's area. One of emerging method is to use human footprint. Automated footprint-based person recognition was started by Nakajima et al.'s research but they showed relatively low recognition result by low spatial resolution of pressure sensor and standing posture. In this paper, we proposed a modified Nakajima's method to use walking footprint which could give more stable toe information than standing posture. Finally, we prove the usefulness of proposed method as 91.4tt recognition rate in 11 volunteers' test.

• 한국지능시스템학회논문지
• /
• 제18권1호
• /
• pp.53-59
• /
• 2008

최근 하지가 불편한 노약자나 장애인이 집안의 다양한 가전기기를 손쉽게 제어하기 위한 비전 기반의 손동작 인식 기술이 발전해 왔다. 다수의 사용자가 하나의 손동작 인식 시스템을 사용할 경우 사용자마다 손동작 특성이 모두 다르기 때문에 특정 사용자의 인식률이 저하되는 문제가 발생한다. 또한 동일한 사용자라 하더라도 시간에 따라 손동작 특성이 변화할 수 있다. 사용자마다 다른 손동작 특성은 모델 학습 및 선택 기법을 사용해 효과적으로 다루어질 수 있다. 시간에 따라 변하는 사용자의 특성은 퍼지 개념을 이용해 효과적으로 다루어질 수 있다. 본 논문에서는 다변량 퍼지 의사 결정트리를 이용해 사용자 별 인식모델을 만드는 방법을 제시한다. 또한 새로운 사용자가 시스템을 사용할 경우 가장 적합한 모델을 선택해 인식에 사용하고 인식률을 측정한다.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.280-286
• /
• 2022

Facial recognition system is a biometric manipulation. Its applicability is simpler, and its work range is broader than fingerprints, iris scans, signatures, etc. The system utilizes two technologies, such as face detection and recognition. This study aims to develop a facial recognition system to recognize person's faces. Facial recognition system can map facial characteristics from photos or videos and compare the information with a given facial database to find a match, which helps identify a face. The proposed system can assist in face recognition. The developed system records several images, processes recorded images, checks for any match in the database, and returns the result. The developed technology can recognize multiple faces in live recordings.

• 대한간호
• /
• 제35권4호
• /
• pp.64-74
• /
• 1996

In general. social cognition for a disabled person seemed that he was limited aspects of emotion and psychology. Thus he was rejected. avoided. worthless and not accepted. People who have been raised in an ethnic collectivity often acquire from that experience not only basic conceps and attitudes toward health and illness but also fundamental styles of interpersonal behavior and concerns about the world. The effects of this enculuration carryover into health- care situation and also become an important influence on personal activities devoted to health maintenance and disease prevention. Our Korean culture is a state of tradition Confucianism. respects his honor and external feature. Therefore recognition of a disabled person is more specipic. This study uses Walker and Avant's process of concept analysis. The concep of recognition of disabilty can be defined as follows : Recognition of disability is a person's conscious process of sensation. perception. memory and thought and is constructed from value. attitude. emotion and expierince which is dynamics. and in everyday life is feeling that basic activity is not free and occurs interaction of envionment. Attributes of disability recognition are defined as 1) It is feeling that basic activity of his daily life is not free in everyday life. 2) It is a person's conscious process of sensation. perception. memory and thought. 3) It occurs interaction of enviornment. 4) It is constructed from value. attitude. emotion and experience. 5) it is dynamics ( changing but not stasis). Nurse is always suppoted and pushed him. She plans institutional and situational surroundings.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권1호
• /
• pp.70-78
• /
• 2007

얼굴 인식 시스템의 성능은 조명 변화로 인하여 발생하는 개인내 (intra-person) 차이가 개인간 (inter-person)의 차이보다 클 수 있기 때문에 조명 변화에 많은 영향을 받는다. 본 연구에서는 이러한 문제를 해결하기 위해서 대칭형 bilinear 모델을 이용하여 조명 요소와 신원 요소를 분리하는 방법을 제안한다. Bilinear 모델로 조명 요소와 신원 요소를 얻기 위한 translation 과정은 반복적 역행렬을 구하는 것이 요구되는데 입력 데이타에 따라 수렴하지 않는 경우가 발생할 수 있다. 이러한 문제를 완화하기 위해서 ridge regression 모델과 bilinear 모델을 결합한 ridge regressive bilinear 모델을 제안하였다. 제안된 모델은 조명 요소와 신원 요소의 분산을 적절히 줄여줌으로서 bilinear 모델에 안정성을 제공하며, 인식에 더 많은 고차원 요소 정보를 이용하게 함으로써 인식 성능을 높여 준다. 실험 결과에서 제안한 ridge regressive bilinear 모델이 bilinear 모델, 고유얼굴(eigenface) 방법, Quotient image 보다 좋은 인식 성능을 보여줌을 확인 할 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제26권2호
• /
• pp.19-25
• /
• 2021

본 논문에서는 비전 기술과 딥러닝 기반의 얼굴인식을 통해 실종자를 식별하는 방법을 제안하였다. 모바일 디바이스에서 전송된 원본 이미지에 대해 얼굴인식에 적합하도록 이미지를 전처리한 후, 얼굴인식의 정확도 향상을 위한 이미지 데이터 증식과 CNN 기반 얼굴학습 및 검증을 통해 실종자를 인식하였다. 본 논문의 구현 결과를 이용하여 가상의 실종자 이미지를 식별한 결과, 원본 데이터와 블러 처리한 데이터를 함께 학습한 모델의 성능이 가장 우수하게 나왔다. 또한 사전학습된 가중치를 사용한 학습 모델은 사용하지 않은 모델보다 높은 성능을 보였지만, 편향과 분산이 높게 나오는 한계를 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.