• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.469-471
• /
• 2002

본 논문에서는 얼굴 영상의 변화를 보상할 수 있는 전처리 과정으로서 기하학적 특징에 기반한 순수 얼굴 영역 검출 기법을 도입하고 후처리 과정으로 간단한 정합 기법을 사용한 얼굴 인식 기법을 제안한다. 실험결과를 보면 제안한 기법은 PCA와 LDA 기법에 비해 영상의 변화에 민감하지 않고 높은 인식률을 가진다.

• 한국벤처창업학회:학술대회논문집
• /
• 2021.11a
• /
• pp.135-142
• /
• 2021

20년 3월부터 본격화된 코로나 팬데믹은 전세계경제에 큰 충격으로 불확실성은 더욱 커져 경제생태계 대변혁의 시대를 맞이하고 있는 가운데 고령 인구의 증가, 생산인구의 감소와 더불어 20년 12월 기준 직장의 폐업과 정리해고, 경영부진 등 비자발적인 일자리를 떠난 사람이 19년 대비 48.9%(2020 통계청) 증가, 직장인의 퇴직 평균연령도 51.7세로 직장인 의지와 관계없이 조기 은퇴가 불가피한 상황이다. 한편 직장 근로자 10명중 8명은 창업할 의지가 있는 것으로 나타나 이제는 직장인의 창업은 선택이 아닌 필수로 인식하고 있다. 본 연구의 목적은 직장인의 기업가정신과 지속학습, 보상만족, 고용가능성이 창업의지와 어떠한 상관관계를 가지고 있는가를 조사하고 혁신행동이 매개역할을 하는지에 대해 분석하는데 있다. 본 연구에서는 직장 재직자의 기업가정신과 직장생활 과정에서 지속학습, 보상만족, 고용가능성이 창업의지에 미치는 영향에 관한 연구를 혁신행동의 매개효과를 중심으로 진행하였다. 따라서 본 연구에서는 재직자의 기업가정신과 지속학습, 보상만족, 고용가능성이 혁신활동을 증가시키고, 증가된 혁신활동이 창업의지에 영향을 미칠 것이라는 인과적 경로를 검증하고자 한다. With Corona의 불확실한 경제여건에서 조직은 생존을 위한 끊임없는 변화를 추구함에 따른 재직자의 고용불안은 가중될 것이며, 100세 시대를 준비해야 하기에 창업은 필수적 상황으로 창업의지를 종속변수로 설정하여 본 연구를 진행하였다.

• Proceedings of the Korean Institute of Landscape Architecture Conference
• /
• 2019.03a
• /
• pp.30-31
• /
• 2019

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.936-941
• /
• 2006

To apply object recognition techniques to real environment, illumination compensation method should be developed. As effective illumination compensation model, we focused our attention on Retinex model and illumination-Reflectance model, implemented them, and experimented on their performance. We implemented Retinex model with Single Scale Retinex, Multi-Scale Retinex, and Retinex Neural Network and Multi-Scale Retinex Neural Network, neural network model of Retinex model. Also, we implemented illumination-Reflectance model with reflectance image calculation by calculating an illumination image by low frequency filtering in frequency domain of Discrete Cosine Transform and Wavelet Transform, and Gaussian blurring. We compare their illumination compensation performance to facial images under nine illumination directions. We also compare their performance after post processing using Principal Component Analysis(PCA). As a result, illumination Reflectance model showed better performance and their overall performance was improved when illumination compensated images were post processed by PCA.

• Review of KIISC
• /
• v.12 no.2
• /
• pp.41-49
• /
• 2002

음성 인식 기술과 뿌리를 공유하는 화자 인식 기술은 지난 수십 년간의 연구결과로 괄목할 만한 진보가 이루어졌으며 최근에는 일반화될 수 있으리라는 기대를 가지도록 하기에 충분했다. 하지만 이러한 기술이 실제 환경에 적용되었을 때, 발성 환경을 제어할 수 없으며 그 결과 훈련 환경과는 다른 환경에서 발성된 음성을 인식 해야하는 이른바 '불일치 조건(mismatch condition)' 현상이 발생하게된다. 초기에는 이 현상을 극복하기 위해 잡음 자체를 모델링하고 제거함으로써 훈련과 인식 환경의 차이를 일정하게 정규화(normalization)해주는 연구가 진행되었다. 하지만 최근에는 잡음에 의한 왜곡의 모델이 복잡하고 실제 인식 성능에 직접적으로 나타나지 않는 문제점을 추가로 극복하기 위해, 훈련과 인식 환경의 차이를 보상해주는(compensation) 연구가 활발히 진행되고 있다. 본 논문에서는 기본적인 화자인식기술과 함께 성능저하를 일으키는 불일치 요인들 및 그것들을 극복하기 위한 기술들을 소개하고자 한다.

• Journal of Broadcast Engineering
• /
• v.21 no.1
• /
• pp.51-59
• /
• 2016

This paper presents a method of DCT-based illuminant compensation to enhance the accuracy of face recognition under an illuminant change. The basis of the proposed method is that the illuminant is generally located in low-frequency components in the DCT domain. Therefore, the effect of the illuminant can be compensated by controlling the low-frequency components. Moreover, a directional high-order local pattern descriptor is used to detect robust features in the case of face motion. Experiments confirm the performance of the proposed algorithm got up to 95% when tested using a real database.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.22 no.1
• /
• pp.301-331
• /
• 2011

This study aims at investigating ways to enhance the efficiency of knowledge management systems in research institutes. This study analyzes the current state of knowledge management systems, changes in users' perception, and the use of knowledge management systems in Daedeok Science Park, and suggests improvement measures. This study reviews previous studies and employs a survey for case studies. This study also conducts log data analysis of knowledge management systems to investigate the current state of system use. The questionnaire asks about the interest in knowledge management, evaluation and rewards of knowledge contribution, quality of knowledge, and the level of utility. This study tests hypothesis and analyzes the frequencies. This study finds that the interest and use of knowledge management system have been remarkably dropped, and also reveals that maintaining reward systems and diverse rewarding systems are required.

• Korean Journal of Culture and Social Issue
• /
• v.27 no.2
• /
• pp.191-216
• /
• 2021

How an individual construes one's future influences everyday decisions. For example, savings and impulsive purchasing, which is highly familiar with our life, are related to future time perception. Drawing on the idea of future self-continuity, the perceived connectedness between the current and future self, this study demonstrated whether media images with various age ranges influence a sense of connectedness with one's future self as well as impatience. Furthermore, the study measured whether these relationships were moderated by the positivity of older adults and an individual's dispositional optimism in general. Results showed that watching various images of people with a wide range of age (from the 20s to 90s) in social media increased young adults' (the 20s) self-continuity and decreased their intention of impatient consumption. This effect was also moderated by the degree to which the participants perceive aging positively.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.6
• /
• pp.462-472
• /
• 2004

In this paper a method for compensating for thp performance degradation or automatic speech recognition (ASR) is proposed. which is mainly caused by speaking rate variation. Before the new method is proposed. quantitative analysis of the performance of an HMM-based ASR system according to speaking rate is first performed. From this analysis, significant performance degradation was often observed in the rapidly speaking speech signals. A quantitative measure is then introduced, which is able to represent speaking rate. Time scale modification (TSM) is employed to compensate the speaking rate difference between input speech signals and training speech signals. Finally, a method for compensating the performance degradation caused by speaking rate variation is proposed, in which TSM is selectively employed according to speaking rate. By the results from the ASR experiments devised for the 10-digits mobile phone number, it is confirmed that the error rate was reduced by 15.5% when the proposed method is applied to the high speaking rate speech signals.

• The Journal of the Korea Contents Association
• /
• v.19 no.6
• /
• pp.58-71
• /
• 2019

The purpose of this study is to explore the multi-dimensionality and the differences of the career success that is revealed by the employee's perception. In order to fulfill the research purpose, LDA topic modeling has applied to extract latent topics of career success from 126 Korean employees' open-end survey questionnaires. The extracted latent topics are social recognition, continuing service within an organization, expertise, financial rewards, and pursuing personal meaning. The occurrence probability of each topic was different by individual characteristics such as gender, education, position. Study findings showed there is multi-dimensionality in career success, and there are differences of topic occurrence probability by demographic characteristics. Additionally, this study showed how to apply the recently developed machine learning approach in order to reduce the researcher's bias by adapting the LDA topic modeling to the qualitative open-ended survey data.