• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.148-153
• /
• 1989

본 논문에서는 광 상관기 (optical correlator) 에 의한 한글문자 분리 인식의 한 방법을 제안하였다. 효율적인 분리 인식을 위해서 병렬 나무 (tree) 구조로부터 입력 신호를 두 방향으로 병렬 처리하여 각 방향으로 자음과 모음을 따로 분리시켜 2단계 만에 인식한 뒤 이들을 위치에 따라 조합하여 문자 분리 인식하도록 하며, 아울러 이러한 병렬 나무구조의 각 단계에서 필터 합성시 MACE (minimum average correlation energy) 개념을 이용하여 광 상 관평면상에서 부엽의 문제를 줄이고, 실제 광 시스템에서 생길 수 있는 왜곡을 학습표본에 포함하여 광 상관기 시스템에 의한 실질적인 한글 문자의 왜곡에 무관한 분리인식을 하도록 하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.75-78
• /
• 1998

이 논문에서는 대용량 연속음성 인식에서 인식 속도를 향상시키기 위한 방법들에 대해서 연구하였다. 음성인식에 있어서 많은 양의 계산을 요하는 부분은 관측 확률의 계산과 탐색에 필요한 계산이다. 탐색에 필요한 계산을 줄이기 위하여 빔 탐색법과 phoneme look-ahead기법을 통해 탐색 공간을 줄였으며, 관측 확률을 계산하는데 소요되는 시간을 줄이기 위하여 입력 특징 벡터와 이웃 관계에 있는 가우시안 성분들만 정확한 계산을 하는 VQ에 의한 계산량 감축 방법과 tree-structured pdf 방법을 구현하였다. 3천개의 어휘와 2천여개의 트라이폰 모델로 구성된 연속 음성인식 시스템에서 보통의 Viterbi 빔 탐색법을 적용한 경우에 실시간의 2.73배의 인식 속도로 93.39%의 단어 인식률을 얻을 수 있는데 phoneme look-ahead 기법과 tree-structured pdf 방법을 추가 적용함으로써 비슷한 인식 성능에서 1.55배의 인식 속도를 얻을 수 있었다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.74-77
• /
• 1998

우리는 C++를 이용하여 음성인식기를 구현하여 기존의 C를 이용한 경우에 비하여 30% 수준의 소스로 표현하였고 인식기의 공동개발, 확장 및 개선, 기술 전수 등이 용이하게 되었으며 이를 음성인식 엔진 및 음성인식 연구를 위한 툴로 사용할 수 있게 되었다. 이 인식기의 특징으로는 연속 음성 및 대화체 음성을 인식할 수 있으며 trigram 언어 모델을 사용하였고 문맥 종속 음소 모델링에서는 기존의 triphone 보다 넓은 문맥을 고려한 n-phone context modeling을 사용하였으며 모델의 선정에는 음성학적 지식을 기반으로 한 질문을 사용한 decision tree를 사용하여 훈련에 나타나지 않은 단어나 문맥인 경우라도 가장 가까운 모델을 선정할 수 있게 하였다. 또, tree lexicon을 사용하여 속도를 개선하였으며 state 단위의 모델 공유를 통해 제한된 데이터를 이용하여 더 많은 모델을 훈련할 수 있어 성능을 개선하였다. 상용화를 염두에 두고 pc에서 구현하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.293-297
• /
• 1998

전화망에서의 연결 숫자 인식 시스템의 개발에 대한 내용을 다루며, 이 시스템에서 다양한 숫자 모델링 방법들을 구현하고 비겨하였다. Word 모델의 경우 문맥독립 whole-word 모델을 구현하였으며, sub-word 모델로는 triphone 모델과 불파음화 자음을 모음에 포함시킨 modified triphone 모델을 구현하였다. 그리고 tree-based clustering 방법을 sub-word 모델과 문맥종속 whole-word 모델에 적용하였다. 이와 같은 숫자모델들에 대해 연속 HMM을 이용하여 화자독립 연결숫자 인식 실험을 수행한 결과, 문맥종속 단어 모델이 문맥독립 단어 모델보다 우수한 성능을 나타냈으며, triphone 모델과 modified triphone 모델은 유사한 성능을 나타냈다. 특히 tree-based clustering 방법을 적용한 문맥종속 단어 모델이 4연 숫자열에 대해 99.8%의 단어 dsltlr률 및 99.1%의 숫자열 인식률로서 가장 우수한 성능을 나타내었다.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1994.11a
• /
• pp.202-205
• /
• 1994

There is a close relation between electrical treeing and internal partial discharges in solid dielectrics. In this paper, the characteristics of electrical treeing and partial discharge in solid dielectrics are investigated. We carried out the measurements of electrical treeing and PD(partial discharge) characteristics. From the experimental results, we found out that maximum PD magnitude increased linearly with time at first stage, thereafter increased remarkably. These tendencies are very similar to the characteristics of tree growth with time.

• The Journal of the Korea Contents Association
• /
• v.7 no.11
• /
• pp.94-101
• /
• 2007

We introduce the way to detect the mutation worm. We implemented the program that can generate signature using LCSeq(Longest Common Subsequence) technique in Suffix Tree studied as pattern recognition algorithm. We also showed the process to detect the mutation of CodeRed worm and Nimda worm and evaluated signatures generated by snort and LCSeq.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1997.11a
• /
• pp.451-455
• /
• 1997

The partial discharge has been blown as the chief breakdown of power equipments. The analysis and the recognition is much difficult because the partial discharge signal is very small and has complex aging pattern. Recently, insulation aging diagnosis based on pattern of phase(Ф), partial discharge magnitude(q), number(n) has been very important. Owing to depreciate the reappearance of aging progress at the electrical tree pattern and to be difficult to analyze visually, the study on partial discharge pattern is suggested to normalizing analysis method of partial discharge signals. This parer is purposed on prediction of life-time measurement of cv-cable, on decision of risk degree with normalization and real-time measurement of partial discharge signals for aging diagnosis of cv-cable. As normalizing the aging signals of electrical tree in cv-cable, it is able to confirm risk degree of insulation material with the distribution of Ф-q-n and recognize the process of aging pattern using neural network.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1100-1108
• /
• 2015

A camera-based real-time hand posture and gesture recognition system is proposed for controlling various devices inside automobiles. It uses an imaging system composed of a camera with a proper filter and an infrared lighting device to acquire images of hand-motion sequences. Several steps of pre-processing algorithms are applied, followed by a background normalization process before segmenting the hand from the background. The hand posture is determined by first separating the fingers from the main body of the hand and then by finding the relative position of the fingers from the center of the hand. The beginning and ending of the hand motion from the sequence of the acquired images are detected using pre-defined motion rules to start the hand gesture recognition. A set of carefully designed features is computed and extracted from the raw sequence and is fed into a decision tree-like decision rule for determining the hand gesture. Many experiments are performed to verify the system. In this paper, we show the performance results from tests on the 550 sequences of hand motion images collected from five different individuals to cover the variations among many users of the system in a real-time environment. Among them, 539 sequences are correctly recognized, showing a recognition rate of 98%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.12
• /
• pp.2364-2375
• /
• 1994

For the efficient recognition of printed Korean characters, a multiplexed minimum average correlation energy(MMACE) filter is proposed. Proposed method solved the disadvantages of the tree structure algorithm which recognition system is very huge and recognition method is sophisticated. Using only one consonant MMACE filter and one vowel one, we recognized the full Korean character. Each MMACE filter is multiplexed by 4 K-tuple MACE filters which are synthesized by 24 consonants and vowels. Hence the proposed MMACE filter and the correlation distribution plane are divided by 4 subregion. We obtained the binary codes for the Korean character recognition from each correlation distribution subplane. And the obtained codes are compared with the truth table for consonants and vowels in computer. We can recognize the full Korean characters when substitute the corresponded consonant or vowel font of the consistent code to the correlation peak place in the output correlation plane. The computer simulation and optical experiment results show that the proposed compact Korean character recognition system using the MMACE filters has high discrimination capability.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.38 no.1
• /
• pp.36-44
• /
• 2020

This study analyzed the Planting Prototype of Haengdan(杏壇)is the One of the traditional planting techniques and the value of natural monument plant and derived the value of the ginkgo tree in Sejong-ri as a natural monument. The results are as follows; First, ginkgo trees have high environmental adaptability, practicality and visual value. There were also many ginkgo trees that were deeply related to Confucian and Buddhist ideas. Ginkgo trees accounted for the largest portion of the number of old tree designated as natural monuments in recognition of their value. Second, after analyzing the historical and cultural values of ginkgo trees, ginkgo trees became the place of gardens and buildings by symbolizing Confucius(孔子)' Confucian ideas. In Buddhism, it was related to the creation of temples or the achievements of ancient monks. The people had a symbol of the prosperity of their offspring and the succession of the family. Third, in 1024 gongdobo, the grandson of Confucius, rebuilt the shrine, installed the platform in the central position and planted ginkgo trees. It originated from what he called "the "haengdan(杏壇)." The tree was then recorded as "heungheang(紅杏)" which was written by Wang Jae-jin's poetry during the Ming Dynasty. Thus it was misused as apricot tree. The cause of this is due to the same kanji reading. or it can be seen as influence on the taoism. But Korea has been sticking to the use of the first ginkgo trees. Forth, biologically, the Sejong-ri ginkgo tree is characterized by the composition of a pair of male trees. The landscape is contrasted with the twisted male tree and vertical female trees. In addition, in terms of authenticity and integrity, the relationship between Admiral Im, Nan-Su(林蘭秀) of the Goryeo Dynasty and the ginkgo tree is found in various literature.