• ETRI Journal
• /
• 제36권5호
• /
• pp.696-703
• /
• 2014

In this paper, we present a walking guidance system for the visually impaired for use at subway stations. This system, which is based on environmental knowledge, automatically detects and recognizes both exit numbers and arrow signs from natural outdoor scenes. The visually impaired can, therefore, utilize the system to find their own way (for example, using exit numbers and the directions provided) through a subway station. The proposed walking guidance system consists mainly of three stages: (a) sign detection using the MCT-based AdaBoost technique, (b) sign recognition using support vector machines and hidden Markov models, and (c) three verification techniques to discriminate between signs and non-signs. The experimental results indicate that our sign recognition system has a high performance with a detection rate of 98%, a recognition rate of 99.5%, and a false-positive error rate of 0.152.

• KIEAE Journal
• /
• 제3권2호
• /
• pp.25-32
• /
• 2003

This study deals with the investigation of recognition structure on architectural environment and reconstruction of it by artificial intelligence. To test the possibility of the reconstruction, recognition structure on architectural environment is analysed and each steps of the structure are matched with computational methods. Edge Detection and Neural Network were selected as matching methods to each steps of recognition process. Visual perception system established by selected methods is trained and tested, and the result of the system is compared with that of experiment of human. Assuming that the artificial system resembles the process of human recognition on architectural environment, does the system give similar response of human? The result shows that it is possible to establish artificial visual perception system giving similar response with that of human when it models after the recognition structure and process of human.

• 한국ITS학회 논문지
• /
• 제7권2호
• /
• pp.37-42
• /
• 2008

본 논문에서는 지능형 홈네트워크의 음성제어를 위한 가변어휘 연속음성인식시스템을 개발하였다. 또한 자연스런 음성명령에 대한 인식을 위해 핵심어 기반의 자연스런 연속어휘에 대한 대화형 시나리오를 작성하였고, 핵심어기반의 인식 엔진 및 데이터베이스를 구축하여 인식엔진의 성능을 최적화하였다.

• 반도체디스플레이기술학회지
• /
• 제19권3호
• /
• pp.106-111
• /
• 2020

In this paper, we propose the non-contact gesture recognition system and algorithm using proximity-based sensors. The system uses four IR receiving photodiode embedded on a single chip and an IR LED for small area. The goal of this paper is to use the proposed algorithm to solve the problem associated with bringing the four IR receivers close to each other and to implement a gesture sensor capable of recognizing eight directional gestures from a distance of 10cm and above. The proposed system was implemented on a FPGA board using Verilog HDL with Android host board. As a result of the implementation, a 2-D swipe gesture of fingers and palms of 3cm and 15cm width was recognized, and a recognition rate of more than 97% was achieved under various conditions. The proposed system is a low-power and non-contact HMI system that recognizes a simple but accurate motion. It can be used as an auxiliary interface to use simple functions such as calls, music, and games for portable devices using batteries.

• 전자공학회논문지B
• /
• 제32B권1호
• /
• pp.171-179
• /
• 1995

In many continuous speech recognition systems, phoneme is used as a basic recognition unit However, the coarticulation generated among neighboring phonemes makes difficult to recognize phonemes consistently. This paper proposes allophone as an alternative recognition unit. We have classified each phoneme into three different allophone groups by the location of phoneme within a syllable. For a recognition algorithm, time-delay neural network(TDNN) has been designed. To recognize all Korean allophones, TDNNs are constructed in modular fashion according to acoustic-phonetic features (e.g. voiced/unvoiced, the location of phoneme within a word). Each TDNN is trained independently, and then they are integrated hierarchically into a whole speech recognition system. In this study, we have experimented Korean plosives with phoneme-based recognition system and allophone-based recognition system. Experimental results show that allophone-based recognition is much less affected by the coarticulation.

• Journal of the Optical Society of Korea
• /
• 제14권4호
• /
• pp.388-394
• /
• 2010

In this paper the object recognition performance of a photon counting integral imaging system is quantitatively compared with that of a conventional gray scale imaging system. For 3D imaging of objects with a small number of photons, the elemental image set of a 3D scene is obtained using the integral imaging set up. We assume that the elemental image detection follows a Poisson distribution. Computational geometrical ray back propagation algorithm and parametric maximum likelihood estimator are applied to the photon counting elemental image set in order to reconstruct the original 3D scene. To evaluate the photon counting object recognition performance, the normalized correlation peaks between the reconstructed 3D scenes are calculated for the varied and fixed total number of photons in the reconstructed sectional image changing the total number of image channels in the integral imaging system. It is quantitatively illustrated that the recognition performance of the photon counting integral imaging system can be similar to that of a conventional gray scale imaging system as the number of image viewing channels in the photon counting integral imaging (PCII) system is increased up to the threshold point. Also, we present experiments to find the threshold point on the total number of image channels in the PCII system which can guarantee a comparable recognition performance with a gray scale imaging system. To the best of our knowledge, this is the first report on comparisons of object recognition performance with 3D photon counting & gray scale images.

• 한국멀티미디어학회논문지
• /
• 제13권4호
• /
• pp.496-503
• /
• 2010

어휘인식 시스템은 스탠드 얼론(Standalone)으로 개발되어 지고 있으며 휴대용 단말기에서 사용하였을 경우 메모리 공간의 제약과 오디오 압축으로 인해 인식률이 낮게 나타난다. 본 연구에서는 휴대용 단말기의 성능과 인식률 향상을 위하여 음향학적 탐색과 언어적 탐색을 분리하여 어휘 인식 속도를 개선한 시스템을 제안하였다. 음향학적 탐색은 휴대용 단말기에서 수행하고 보다 복잡한 언어적 탐색은 서버에서 처리하는 시스템으로 음성신호로부터 특징벡터를 추출하여 GMM을 이용한 음소인식을 수행하고, 인식된 음소 열을 서버로 전송하여 렉시컬 트리 탐색 알고리즘을 사용하여 언어적 탐색 단계에서 어휘 인식을 수행하였다. 시스템 성능 평가 결과 어휘 종속 인식률은 98.01%, 어휘 독립 인식률은 97.71%의 인식률을 나타냈으며 인식속도는 1.58초로 나타내었다.

• 한국컴퓨터정보학회논문지
• /
• 제5권2호
• /
• pp.90-97
• /
• 2000

본 논문에서는 불특정 화자의 음성에 대해서도 신뢰성 있는 인식이 이루어지도록 하는 음성인식 시스템을 구현하기 위한 화자적응 음성인식 기법을 제안한다. 제안한 화자적응 기법에 의한 음성인식 시스템은 표준화자의 음성특징을 1차선형 변환 망에 의해 새로운 화자의 음성특징에 선형적으로 적응하여 인식하며. 그 구성은 다층퍼셉트론을 퍼지 벡터양자화기로 사용하는 반연속 HMM을 기반으로 한다 구현한 인식시스템은 그 성능을 확인하기 위해 고립단어 인식실험을 수행하였다. 그 결과, 화자적응 인식인 경우가 화자적응 수행하지 않은 시스템에 비해 인식률이 개선됨을 보였다.

• 한국인터넷방송통신학회논문지
• /
• 제17권5호
• /
• pp.1-8
• /
• 2017

최근 클라우드, 모바일 등 ICT 기술의 발전으로 소셜 네트워크를 통한 이미지 활용이 급증하고 있다. 이러한 이미지는 개인정보가 포함되어 있어, 개인정보 유출 사고가 발생될 수 있다. 이에 이미지에서 개인정보를 인식하고 마스킹하는 연구가 진행되고 있다. 그러나 기존 이미지에서 개인정보를 인식 하는 방법인 광학 문자 인식은 이미지의 밝기, 명암, 왜곡에 따라 인식률의 변화가 심하여 한글 인식이 미흡한 문제가 있다. 따라서 본 논문에서는 광학 문자 인식 방법을 기반으로 CNN 알고리즘에 딥러닝을 적용하여 이미지 인식 기반 향상된 개인정보 식별 및 마스킹 시스템을 설계 및 구현하였다. 또한 구현된 제안 시스템을 동일한 이미지를 가지고 광학 문자 인식과 개인정보 인식률을 비교평가를 진행하고, 제안 시스템의 얼굴 인식률을 측정하였다. 테스트 결과 제안 시스템의 개인정보 인식률은 광학 문자인식에 비해 32.7% 향상되었으며 얼굴 인식률은 86.6%로 확인되었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.629-632
• /
• 2000

In this paper, we studied on the phoneme classification for Korean speech recognition. In the case of making large vocabulary speech recognition system, it is better to use phoneme than syllable or word as recognition unit. And, In order to study the difference of speech recognition according to the number of phoneme as recognition unit, we used the speech toolkit of OGI in U.S.A as recognition system. The result showed that the performance of diphthong being unified was better than that of seperated diphthongs, and we required the better result when we used the biphone than when using mono-phone as recognition unit.