• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.432-435
• /
• 2007

본 논문은 신원확인 수단으로 부각되어 관심이 높은 홍채인식에 대한 연구이다 홍채인식 시스템의 경우 홍채영역에 따라 각 영상들의 특징 값이 차지하는 비중이 서로 다르게 분포되어 있고 눈썹이나 조명에 의한 잡음으로 인하여 인식성능에 영향을 미친다. 이 경우 기존에 등록되어 인증된 사용자의 홍채영상일지라도 제대로 인식하지 못하거나 인증에 실패할 수 있으며, 실세계에서의 홍채영역 사용이 원활하지 못하게 된다. 그러므로 단일 생체인식 시스템에서 홍채인식을 할 경우, 중요한 특징을 그대로 유지하고 인식성능을 향상시키기 위해서 획득된 홍채 영상의 정규화와 전처리 과정을 거친 다음 홍채영역을 분할한 후 각 영역에서의 보정치 적용을 통한 특징추출 방법을 제안한다. 또한 웨이블릿 변환과 주성분 분석을 이용하여 인식 성능이 개선된 특징추출 방법임을 보인다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.187-191
• /
• 2006

본 논문에서는 비전 기술에 기반을 둔 손 모양 인식 시스템의 성능 향상을 위해 학습을 통해 손 모양과 손 구조 간 유사도를 결정하는 방법을 제안한다. 비전 센서에 기반을 둔 손 모양 인식은 손의 높은 자유도로 인한 자체 가림 현상과 관찰 방향 변화에 따른 입력 영상의 다양함으로 인해 인식에 어려움이 따른다. 따라서 비전 기반 손 모양 인식의 경우, 카메라와 손 간의 상대적인 각도에 제한을 두거나 여러 대의 카메라를 배치하는 것이 일반적이다. 그러나 카메라와 손 간의 상대적 각도에 제한을 두는 경우에는 사용자의 움직임에 제약이 따르게 되며, 여러 대의 카메라를 사용할 경우에는 각 입력된 영상에 대한 인식 결과를 최종 인식 결과에 반영하는 방식에 대해서 추가적으로 고려해야 한다. 본 논문에서는 비전 기반 손 모양 인식의 이러한 문제점을 개선하기 위하여 인식의 과정에서 사용되는 손 모양 특징을 손 구조적인 각도 정보와 손 영상 특징으로 나누고, 학습을 통해 각 특징 간 연관성을 정의한다.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.8
• /
• pp.63-67
• /
• 2000

This paper deals with text-prompt speaker recognition based on dynamic time warping (DTW). The Genetic Algorithm was applied to the creation of reference patterns for suitable reflection of the speaker characteristics, one of the most important determinants in the fields of speaker recognition. In order to overcome the weakness of text-dependent and text-independent speaker recognition, the text-prompt type was suggested. Performed speaker identification and verification in close and open set respectively, hence the Genetic algorithm-based reference patterns had been proven to have better performance in both recognition rate and speed than that of conventional reference patterns.

• Proceedings of the Korea Contents Association Conference
• /
• 2013.05a
• /
• pp.289-290
• /
• 2013

이 논문은 얼굴의 기하학적 특징을 이용한 표정인식 시스템을 제안한다. 먼저 얼굴 인식 시스템으로 Haar-like feature의 특징 마스크를 이용한 방법을 적용하였다 인식된 얼굴은 눈을 포함하고 있는 얼굴 상위 부분과 입을 포함하고 있는 얼굴 하위 부분으로 분리한다. 그래서 얼굴 요소 추출에 용이하게 된다. 얼굴 요소 추출은 PCA를 통한 고유 얼굴의 고유 눈과 고유 입의 템플릿 매칭으로 추출하였다. 얼굴 요소는 눈과 입이 있으며 두 요소의 기하학적 특징을 통하여 표정을 인식한다. 눈과 입의 특징 값은 실험을 통하여 정한 각 표정별 임계 값과 비교하여 표정이 인식된다. 본 논문은 기존의 논문에서 거의 사용하지 않는 눈동자의 비율을 적용하여 기존의 표정인식 알고리즘보다 인식률을 높이는 방향으로 제안되었다. 실험결과 기존의 논문보다 인식률이 개선됨을 확인 할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.895-898
• /
• 2004

본 논문에서는 기존의 개인 식별 방법의 한계를 해결하는 대안으로 떠오르고 있는 생체인식 기술 중 인식률이 뛰어난 홍채인식 시스템에 대해 연구하고자 한다. 먼저 홍채인식 시스템의 구현을 위해 신호처리 분야에서 많이 사용되고 있는 wavelet 변환 중 Haar wavelet과 고차 국소 자기 상관 특징을 이용하여 홍채의 특징을 추출하여 특징벡터의 크기를 최소화 하였다. 또, 인식률을 높이기 위해 오류 역전파 학습 알고리즘을 이용하여 홍채패턴에 기반한 신원 확인 및 검증을 위한 개선된 방법을 제시하였다. 학습이 완료된 신경망에 대한 학습데이터와 테스트 데이터의 인식률을 실험한 결과 학습된 데이터는 평균 인식률 $97.4\%$, 테스트 데이터는 $95.5\%$의 인식률을 보였다.

• Journal of the HCI Society of Korea
• /
• v.13 no.4
• /
• pp.5-14
• /
• 2018

The Empathy for Dementia using Virtual Reality (EDuVR) system, developed by the Jeju Provincial Dementia Center, is a 3D video system capturing the experience of dementia in a first-person perspective using 360 degree vritual reality (VR) technology. It was developed to create a greater understanding of dementia and to help people empathize with individuals with dementia through an immersive VR experience. The EDuVR shows how a dementia patient has impairments in memory, orientation, language, judgment and problem solving, as well as problems with activities of daily living. The present study reported the effectiveness of the EDuVR experience in changing public awareness of, and attitude toward, dementia. Sixty-six participants were assigned to the EDuVR (n = 34) or the conventional education (n = 32) groups, and two types of questionnaires - attitude and awareness questionnaires - were administered to the subjects before and after the EDuVR experience or education. The simulator sickness and presence questionnaires were administered to the EDuVR group to assess cybersickness and presence of the VR experience. As a results, the attitude and awareness toward dementia patients changed positively in both the EDuVR and the conventional education groups, and these changes did not differ between two groups. Only one person reported a significant level of cybersicness after experiencing the EDuVR system. These results suggest that the EDuVR enhances the level of understanding and empathy for dementia and would be a useful tool for improving awareness in the general public.

• Journal of Korea Port Economic Association
• /
• v.39 no.3
• /
• pp.91-105
• /
• 2023

This paper identified the difference in perception of the consignment system between the freight company and the consigned vehicle owners, derived factors that urgently need to improve the difference in perception, and presented the basis for establishing a management model based on this. A management model based on the difference in perception of consigned borrowers was established, and research hypotheses were established to conduct reliability, validity, and confirmatory factor analysis, path analysis, and mediation effect verification. As a result of the analysis, out of 58 questions, 56 of the total 65 questions showed a difference in perception of the consignment system between trucking companies and consigned vehicle owners, and the questions were input as management model factors. As a result of conducting confirmatory factor analysis, path analysis, and mediating effect verification using only recognition data, 5 hypotheses were adopted, and it was analyzed that the factor had no mediating effect. It can be analyzed that the appropriateness of the compensation system affects the improvement of each other's relationship, and the improvement of each other's relationship leads to the improvement of transportation services. However, since the mediating effect was rejected because it was not significant, this effect should not be exaggerated.

• Journal of Digital Contents Society
• /
• v.16 no.4
• /
• pp.605-613
• /
• 2015

This paper addresses the problem to make sparse the projection matrix in pattern recognition method. Recently, the size of computer program is often restricted in embedded systems. It is very often that developed programs include some constant data. For example, many pattern recognition programs use the projection matrix for dimension reduction. To improve the recognition performance, very high dimensional feature vectors are often extracted. In this case, the projection matrix can be very big. Recently, RSR(roated sparse regression) method[1] was proposed. This method has been proved one of the best algorithm that obtains the sparse matrix. We propose three methods to improve the RSR; outlier removal, sampling and elastic net RSR(E-RSR) in which the penalty term in RSR optimization function is replaced by that of the elastic net regression. The experimental results show that the proposed methods are very effective and improve the sparsity rate dramatically without sacrificing the recognition rate compared to the original RSR method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.11
• /
• pp.469-478
• /
• 2017

This study analyzed faculties' perceptions on the importance and performance of effective teaching behaviors. The effective teaching behaviors scale consisted of 40 items belonging to 8 factors. A survey was conducted with 86 faculties from 2 universities. It was found that the differences between the importance and performance levels of all items except for 'applying emphasis on important contents' were statistically significant. The scores of importance were higher than those of performance. The results of the IPA showed that 'keep up the good work' area included 19 items that those were high the scores of importance and performance. The 'concentrate here' area included 5 items that need to be improved for effective teaching. The first priority items needing to be improved were 1) Establishing instructional methods and strategies suitable for the objectives, 2) establishing clear objectives, appropriate examples and systematic classes, 3) providing questions, opportunities and appropriate feedback. We suggested that a faculty development program needs to be developed for effective teaching.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.6
• /
• pp.2263-2268
• /
• 2010

In this paper, the hybrid compensation algorithm($A_{HB}$) for localization using the Compensation Algorithm distance($CA_d$) and the Algorithm of Equivalent Distance Rate(AEDR) in SDS-TWR(Symmetric Double-Sided Two-Way Ranging) is suggested and the performance of the proposed algorithm is analyzed by practical experimentations. From experimentations, it is confirmed that the errors are reduced in 28 coordinates of total 32 coordinates in the experimental region and the errors are reduced about above 70% in the assigned 3 type error level ranges by $A_{HB}$. Also, it is analyzed that the average localization error is reduced from 2.67m to 1.19m as 55.4% in total 32 coordinates by $A_{HB}$ and the error compensation capability of $A_{HB}$ is very excellent as above 90%. From above results, we have seen that the error reduction ratio and error compensation capability of $A_{HB}$ is more excellent than each $CA_d$ or AEDR.