• 한국컴퓨터그래픽스학회논문지
• /
• 제16권1호
• /
• pp.1-7
• /
• 2010

비전 기반의 감시 시스템에서 동일인의 식별은 매우 중요하다. 감시 시스템에서 주로 사용되는 CCTV 카메라의 영상은 상대적으로 낮은 해상도를 가지므로 얼굴 인식 기법을 이용하여 동일인을 식별하기는 어렵다. 본 논문에서는 CCTV 카메라 영상에서 의상 특징을 이용하여 동일인을 식별하는 알고리즘을 제안한다. 건물의 주출입구에서 출입자가 인증을 받을 때, 의상 특징이 데이터베이스에 저장된다. 그 후, 건물 내에서 촬영한 영상에 대해 배경 차감 및 피부색 발견 기법을 이용하여 의상 영역을 발견한다. 의상의 특징 벡터는 텍스처와 색상 특징을 이용하여 구성한다. 텍스처 특징은 지역적 에지 히스토그램을 이용하여 추출된다. 색상 특징은 색상 지도의 옥트리 기반 양자화(octree-based quantization)를 이용하여 추출된다. 건물 내의 촬영 영상이 주어질 때, 데이터베이스에서 의상 특징이 가장 유사한 사람을 발견함으로써 동일인을 식별하며, 의상 특징 벡터 간의 유사도 측정을 위해서는 유클리디안 거리(Euclidean distance)를 사용한다. 실험 결과, 얼굴인식 기법이 최대 43%의 성공률을 보인 데 비해, 의상 특징을 이용하여 80%의 성공률로 동일인을 식별하였다.

• 대한간호학회지
• /
• 제44권2호
• /
• pp.198-208
• /
• 2014

Purpose: This research was an empirical study designed to identify precursors and interaction effects related to nurses' patient identification behavior. A multilevel analysis methodology was used. Methods: A self-report survey was administered to registered nurses (RNs) of a university hospital in South Korea. Of the questionnaires, 1114 were analyzed. Results: The individual-level factors that had a significantly positive association with patient identification behavior were person-organization value congruence, organizational commitment, occupational commitment, tenure at the hospital, and tenure at the unit. Significantly negative group-level precursors of patient identification behavior were burnout climate and the number of RNs. Two interaction effects of the person-organization value congruence climate were identified. The first was a group-level moderating effect in which the negative relationship between the number of RNs and patient identification behavior was weaker when the nursing unit's value congruence climate was high. The second was a cross-level moderating effect in which the positive relationship between tenure at the unit and patient identification behavior was weaker when value congruence climate was high. Conclusion: This study simultaneously tested both individual-level and group-level factors that potentially influence patient identification behavior and identified the moderating role of person-organization value congruence climate. Implications of these results are discussed.

• 한국한의학연구원논문집
• /
• 제13권1호통권19호
• /
• pp.109-114
• /
• 2007

The high position condition 10 escape which the obesity person appeals. Obesity Pattern-Identification question it will yell and 243 subjects which to the obesity in the patient of 517 subjects which draw up correspond. (longitude obesity 153 person, altitude obesity 90 person) against it analyzes. In order to analyze the reliability of the items which diagnose each Pattern-Identification it used Cronbach alpha coefficient and escape it did the alpha of each item. Alpha value of each Pattern-Identification than appears more highly the item which it will be able to consider an elimination in the item which decreases a reliability. In that phlegm-retention syndrome is bigger alpha coefficient 0.784 than 'meal quantity is few'(0.787) a possibility of seeing in the item which decreases a reliability to the place where it diagnoses it puts in phlegm-retention syndrome.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1202-1205
• /
• 2005

This paper describes a method for vision-based person identification that can detect, track, and recognize person from video using multiple cues: height and dressing colors. The method does not require constrained target's pose or fully frontal face image to identify the person. First, the system, which is connected to a pan-tilt-zoom camera, detects target using motion detection and human cardboard model. The system keeps tracking the moving target while it is trying to identify whether it is a human and identify who it is among the registered persons in the database. To segment the moving target from the background scene, we employ a version of background subtraction technique and some spatial filtering. Once the target is segmented, we then align the target with the generic human cardboard model to verify whether the detected target is a human. If the target is identified as a human, the card board model is also used to segment the body parts to obtain some salient features such as head, torso, and legs. The whole body silhouette is also analyzed to obtain the target's shape information such as height and slimness. We then use these multiple cues (at present, we uses shirt color, trousers color, and body height) to recognize the target using a supervised self-organization process. We preliminary tested the system on a set of 5 subjects with multiple clothes. The recognition rate is 100% if the person is wearing the clothes that were learned before. In case a person wears new dresses the system fail to identify. This means height is not enough to classify persons. We plan to extend the work by adding more cues such as skin color, and face recognition by utilizing the zoom capability of the camera to obtain high resolution view of face; then, evaluate the system with more subjects.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권4호
• /
• pp.262-268
• /
• 2017

Intelligent video surveillance systems have been developed to monitor global areas and find specific target objects using a large-scale database. However, person re-identification presents some challenges, such as pose change and occlusions. To solve the problems, this paper presents an improved person re-identification method using sparse representation and saliency-based dictionary construction. The proposed method consists of three parts: i) feature description based on salient colors and textures for dictionary elements, ii) orthogonal atom selection using cosine similarity to deal with pose and viewpoint change, and iii) measurement of reconstruction error to rank the gallery corresponding a probe object. The proposed method provides good performance, since robust descriptors used as a dictionary atom are generated by weighting some salient features, and dictionary atoms are selected by reducing excessive redundancy causing low accuracy. Therefore, the proposed method can be applied in a large scale-database surveillance system to search for a specific object.

• 디지털산업정보학회논문지
• /
• 제13권3호
• /
• pp.53-64
• /
• 2017

Korean Identification card or driver license is usually used to verify one's identity in Korea. These are also used as an adult certification. Since the form of these ID card is an analog and it needs to be checked with naked eyes, it might be used maliciously. Someone who's got someone else's ID card can do other things. Therefore, it must be reported rapidly when ID card is lost or stolen. The most serious problem might be occurred when they do not recognize and report the loss. They might suffer from pecuniary or mental damage such as opening a mobile phone service, providing loan or credit card, opening a personal checking account, etc. Thus, this study suggests and compares the ways of avoiding these problems. First, the most effective way is to send the authorization code via mobile phones in consideration of build-up period and cost. The person in charge of business processing department using ID card sends the authorization code via registered mobile phone. The owners submits it to the person and their identifications are confirmed. Next effective way is that the person in charge of business processing department using ID card sends text messages via registered mobile phone. Lastly, the most ineffective way is to introduce and implement the electronic ID card ultimately even though it is expensive and takes a long time to build up the system.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.251-254
• /
• 2000

This paper proposes an enhanced algorithm for person identification system utilizing hand vein pattern. The conventional algorithm does not cope with distortion caused by image rotation caused by misplaced hands on the imaging device. A straightforward approach to consider the rotaional compensation required too much computational load, thus, we devised an approach to expect the rotation direction along with image translation, reducing the compuational requirement dramatically In this paper, we present the details of the algorithm with experimental results with the new algorithm.

• 한국인터넷방송통신학회논문지
• /
• 제17권2호
• /
• pp.15-23
• /
• 2017

사람의 빈번한 자세 변화, 그리고 background clutter과 occlusion으로 인해 Person Re-identificatio는 컴퓨터 비전 분야에서 가장 어려운 부분이다. 비겹침 카메라의 이미지는 어떤 사람을 다른 사람과 구별하기 어렵게 한다. 더욱 나은 성능 일치를 달성하기 위해 대부분의 방법은 특징 선택과 거리 메트릭을 개별적으로 사용한다. 그렇게 차별화된 표현과 적절한 거리를 얻을 수 있고, 사람과 중요한 특징의 무시 사이의 유사성을 설명할 수 있다. 이러한 상황은 우리가 이 문제를 다루는 새로운 방법을 고려하도록 한다. 본 논문에서는 Person Re-identification를 위한 3단 계층네트워크를 갖는 향상되고 반복적인 신경 회로망을 제안하였다. 특히 RNN(Revurrent Neural Network) 모델은 반복적인 EM(Expectation Maximum) 알고리즘과 3단 계층 네트워크를 포함하고, 차별적 특징과 지표 거리를 공동으로 학습한다. 반복적인 EM 알고리즘은 RNN 이전에 연속해 있는 CNN(Convoutional Neural Network)의 특징 추출 능력을 충분히 사용할 수 있다. 자율 학습을 통해 EM 프레임 워크는 패치의 레이블을 변경하고 더 큰 데이터 세트를 훈련할 수 있다. 네트워크를 더 잘 훈련시키기 위해 3단 계층 네트워크를 통해 CNN, RNN 및 풀링 계층이 공동으로 특징 추출을 할 수 있다. 실험 결과에 따르면 비전처리 분야에서 다른 연구자의 접근 방식과 비교할 때 이 방법은 경쟁력 있는 정확도를 얻을 수 있다. 이 방법에 대한 다른 요소의 영향은 향후 연구에서 분석되고 평가될 것이다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.247-250
• /
• 2000

This paper proposes a finger crease pattern identification algorithm utilizing a clustering method. The algorithms has been developed for the use of biometric person identification system. Since the finger crease pattern may be well-imaged utilizing low cost imaging devices such as low-end CCD camera with LED lighting, the feasibility of commercialization of the algorithm and the system utilizing the algorithm may be well justified if the finger crease pattern is a reasonable choice for the biometric feature. In this paper, we exploit this possibility and show the potential of using the finger crease pattern as a feature for biometric person identification.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.893-913
• /
• 2017

The handwriting based person identification systems use their designer's perceived structural properties of handwriting as features. In this paper, we present a system that uses those structural properties as features that graphologists and expert handwriting analyzers use for determining the writer's personality traits and for making other assessments. The advantage of these features is that their definition is based on sound historical knowledge (i.e., the knowledge discovered by graphologists, psychiatrists, forensic experts, and experts of other domains in analyzing the relationships between handwritten stroke characteristics and the phenomena that imbeds individuality in stroke). Hence, each stroke characteristic reflects a personality trait. We have measured the effectiveness of these features on a subset of handwritten Devnagari and Latin script datasets from the Center for Pattern Analysis and Recognition (CPAR-2012), which were written by 100 people where each person wrote three samples of the Devnagari and Latin text that we have designed for our experiments. The experiment yielded 100% correct identification on the training set. However, we observed an 88% and 89% correct identification rate when we experimented with 200 training samples and 100 test samples on handwritten Devnagari and Latin text. By introducing the majority voting based rejection criteria, the identification accuracy increased to 97% on both script sets.