• 전기학회논문지
• /
• 제66권8호
• /
• pp.1265-1271
• /
• 2017

In this paper, the speech parameter fusion method is studied to improve the performance of the conventional emotion recognition system. For this purpose, the combination of the parameters that show the best performance by combining the cepstrum parameters and the various pitch parameters used in the conventional emotion recognition system are selected. Various pitch parameters were generated using numerical and statistical methods using pitch of speech. Performance evaluation was performed on the emotion recognition system using Gaussian mixture model(GMM) to select the pitch parameters that showed the best performance in combination with cepstrum parameters. As a parameter selection method, sequential feature selection method was used. In the experiment to distinguish the four emotions of normal, joy, sadness and angry, fifteen of the total 56 pitch parameters were selected and showed the best recognition performance when fused with cepstrum and delta cepstrum coefficients. This is a 48.9% reduction in the error of emotion recognition system using only pitch parameters.

• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.175-182
• /
• 1994

In this study, we present unvoiced consonant recognition system using characteristic parameters of the phoneme of the each syllable. For the recognition, the characteristic parameters on the time domain such as ZCR, total energy of the consonant region and half region energy of the consonant region, and those on the frequency domain such as the frequency spectrum of the transition region are used. The objective unvoiced consonants in this study are /ㄱ/,/ㄷ/,/ㅂ/,/ㅈ/,/ㅋ/,/ㅌ/,/ㅍ/ and /ㅊ/. Each characteristic parameter of two regions extracted from these segmented unvoiced consonants are used for each recognition system of the region, independently, And complementing two outputs of each other system, the final output is to be produced. The recognition system is implemented using MLP which has learning ability. The recognition simulation results for 112 unvoiced consonant samples are that average recognition rates are 96.4$\%$ under 80$\%$ learning rates and 93.7$\%$ under 60$\%$ learning rates.

• 제어로봇시스템학회논문지
• /
• 제13권8호
• /
• pp.719-725
• /
• 2007

In this paper, we present an audio-visual speech recognition system for noise-robust human-computer interaction. Unlike usual speech recognition systems, our system utilizes the visual signal containing speakers' lip movements along with the acoustic signal to obtain robust speech recognition performance against environmental noise. The procedures of acoustic speech processing, visual speech processing, and audio-visual integration are described in detail. Experimental results demonstrate the constructed system significantly enhances the recognition performance in noisy circumstances compared to acoustic-only recognition by using the complementary nature of the two signals.

• 한국컴퓨터정보학회논문지
• /
• 제24권6호
• /
• pp.67-72
• /
• 2019

This paper proposes a computer vision-based banknote recognition system intended to assist the blind. This system is robust and fast in recognizing banknotes on videos recorded with a smartphone on real-life scenarios. To reduce the computation time and enable a robust recognition in cluttered environments, this study segments the banknote candidate area from the background utilizing a technique called Pixel-Based Adaptive Segmenter (PBAS). The Speeded-Up Robust Features (SURF) interest point detector is used, and SURF feature vectors are computed only when sufficient interest points are found. The proposed algorithm achieves a recognition accuracy of 98%, a 100% true recognition rate and a 0% false recognition rate. Although Korean banknotes are used as a working example, the proposed system can be applied to recognize other countries' banknotes.

• 한국멀티미디어학회논문지
• /
• 제25권4호
• /
• pp.568-574
• /
• 2022

In this paper, direction normalization and CNN deep learning are used to develop a more reliable license plate recognition system. The existing license plate recognition system consists of three main modules: license plate detection module, character segmentation module, and character recognition module. The proposed system minimizes recognition error by adding a direction normalization module when a detected license plate is inclined. Experimental results show the superiority of the proposed method in comparison to the previous system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.573-574
• /
• 1992

We developed a recognition and tracking system of moving objects. The system consists of one CCD video camera, two DC motors in horizontal and vertical axles with encoders, pluse width modulation(PWM) driving unit, 16 bit NEC 9801 microcomputer, and their interfaces. The recognition and tracking system is able to recognize shape and size of a moving object and is able to track the object within a certain range of errors. This paper presents the brief introduction of the recognition and tracking system developed in our laboratory.

• 대한전자공학회논문지SP
• /
• 제41권4호
• /
• pp.45-50
• /
• 2004

본 논문에서는 실시간 얼굴인식 시스템을 위한 새로운 PCA 기반 LDA 혼합 알고리즘을 제안한다. 크게 얼굴추출 부분과 얼굴인식 부분으로 구성되어 있으며, 얼굴추출 부분에는 차영상, color filtering, 눈과 입의 영역 검출 그리고 정규화 방법을 사용하였고, 얼굴인식 부분에는 추출된 얼굴 후보 영역 영상에 PCA와 LDA를 혼합하여 적용하였다. 기존의 PCA만을 사용한 인식시스템은 낮은 인식률을 보였으며, LDA만을 사용한 인식시스템에서는 학습데이터의 수에 비하여 영상의 화소 개수가 많은 경우 LDA를 입력 영상에 그대로 적용하기 곤란하였다. 이러한 단점을 극복하기 위하여, 정규화 된 영상에 PCA를 적용하여 차원을 축소한 후 LDA를 사용하여 실시간 인식을 가능하게 하였으며, 인식률 또한 향상시킬 수 있었다. 제안한 시스템의 성능을 평가하기 위하여 자체 제작한 DAUface의 데이터베이스를 가지고 실험을 하였다. 실험 결과, 제안된 방법이 PCA 방법과 LDA 방법, 그리고 ICA 방법에 비해 인식률이 상당히 우수함을 알 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제15권7호
• /
• pp.83-90
• /
• 2010

어휘 인식 시스템에서 인식률 저하의 요인으로는 유사한 음소 인식과 부정확한 어휘 제공으로 인해 오인식 오류가 존재한다. 부정확한 어휘의 입력으로 특징을 추출하여 인식할 경우 오인식의 결과가 나타나거나 유사한 음소로 인식되며 특징 추출이 제대로 이루어지지 않으면 음소 인식 시 유사한 음소로 인식하게 된다. 따라서 본 논문에서는 음소가 갖는 특징을 기반으로 음소 유사율을 이용한 어휘 인식 후처리에서의 오류 보정 후처리 시스템을 제안하였다. 음소 유사율은 모노폰으로 훈련시킨 훈련 데이터를 각각의 음소에 MFCC와 LPC 특징 추출 방법을 이용하여 구하였다. 유사한 음소는 정확한 음소로 인식할 수 있도록 유도하여 부정확한 어휘 제공으로 인하여 오인식되는 오류를 최소화하였다. 음소 유사율과 신뢰도를 이용하여 오류 보정율을 구하였으며, 어휘 인식 과정에서 오류로 판명된 어휘에 대하여 오류 보정을 수행하였다. 에러패턴 학습을 이용한 시스템과 의미기반을 이용한 시스템에 비해 시스템 성능 평가 결과 MFCC와 LPC는 각각 7.5%와 5.3%의 인식 향상률을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1183-1186
• /
• 2004

In the steel production line, the molten metal of a furnace is transformed into billet and then moves to the heating furnace of the hot rolling mill. This paper describes about the realtime billet characters recognition system in the steel production line. Normally, the billets are mixed at yard so that their identifications are very difficult and very important processing. The character recognition algorithm used in this paper is base on the subspace method by K-L transformation. With this method, we need no special feature extraction steps, which are usually error prone. So the gray character images are directly used as input vectors of the classifier. To train the classifier, we have extracted eigen vectors of each character used in the billet numbers, which consists of 10 arabia numbers and 26 alphabet aharacters, which are gathered from billet images of the production line. We have developed billet characters recognition system using this algorithm and tested this system in the steel production line during the 8-days. The recognition rate of our system in the field test has turned out to be 94.1% (98.6% if the corrupted characters are excluded). In the results, we confirmed that our recognition system has a good performance in the poor environments and ill-conditioned marking system like as steel production plant.

• 디지털산업정보학회논문지
• /
• 제5권2호
• /
• pp.77-85
• /
• 2009

In this paper, we propose data format for smell, taste, touch with speech and vision which can be transmitted and implement a floral scent detection and recognition system. We provide representation method of data of smell, taste, and touch. Also, proposed floral scent recognition system consists of three module such as floral scent acquisition module using Metal Oxide Semiconductor (MOS) sensor array, entropy-based floral scent detection module, and floral scent recognition module using correlation coefficients. The proposed system calculates correlation coefficients of the individual sensor between feature vector(16 sensors) from floral scent input point until the stable region and 12 types of reference models. Then, this system selects the floral scent with the maximum similarity to the calculated average of individual correlation coefficients. To evaluate the floral scent recognition system using correlation coefficients, we implemented an individual floral scent recognition system using K-NN with PCA and LDA that are generally used in conventional electronic noses. In the experimental results, the proposed system performs approximately 95.7% average recognition rate.