• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.219-224
• /
• 2012

In the communication mobile terminal, Vocabulary recognition system has low recognition rates, because this problems are due to phoneme feature extract from inaccurate vocabulary. Therefore they are not recognize the phoneme and similar phoneme misunderstanding error. To solve this problem, this paper propose the system model, which based on the two step process. First, input phoneme is represent by number which measure the distance of phonemes through phoneme likelihood process. next step is recognize the result through the reliability measure. By this process, we minimize the phoneme misunderstanding error caused by inaccurate vocabulary and perform error correction rate for error provrd vocabulary using phoneme likelihood and reliability. System performance comparison as a result of recognition improve represent 2.7% by method using error pattern learning and semantic pattern.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.188-193
• /
• 1997

한국어 문자 인식 후처리는 인식기가 제공하는 후보 음절을 바탕으로 후처리를 하였다. 이 논문은 문자 인식기가 제공하는 후보 음절 대신에 인식기의 인식 결과를 분석하여 인식기의 오인식 통계 정보에 따라 인식 결과 음절의 후보 음절을 생성한다. 여기서 생성된 후보 어절을 각 음절의 확률 값을 이용하여 확률이 가장 놓은 어절을 선택한다. 이때 한국어 대용량 말뭉치에서 추출한 어절의 통계정보를 이용하여 그 어절의 확률 값을 구한다. 이 기법의 장점은 후보 음절의 조합으로 생성된 어절의 확률 값과 그 어절의 말뭉치상의 확률 값을 이용한 결과 말뭉치에 포함된 미등록어 정보에 따라 형태소 분석이 되지 않는 미등록어 처리가 가능하다. 또한 후보 어절 중 형태소 분석이 성공하는 어절이 두개 이상 있을 경우 실제 거의 쓰이지는 않지만 단지 음절의 확률 값이 높아 우선으로 선택되는 경우를 방지하였다. 실험은 약 1,000page 분량의 실험을 통해 오인식 결과를 수집하고, 4000만 원시 말뭉치에서 구한 어절의 통계정보를 이용하였다. 그 결과 문자 인식기의 98.05%의 어절 인식률을 후처리 결과 99.52%로 향상시켰다.

• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.137-142
• /
• 2013

Speech recognition system is input of inaccurate vocabulary by feature extraction case of recognition by appear result of unrecognized or similar phoneme recognized. Therefore, in this paper, we propose a speech recognition error correction method using phoneme similarity rate and reliability measures based on the characteristics of the phonemes. Phonemes similarity rate was phoneme of learning model obtained used MFCC and LPC feature extraction method, measured with reliability rate. Minimize the error to be unrecognized by measuring the rate of similar phonemes and reliability. Turned out to error speech in the process of speech recognition was error compensation performed. In this paper, the result of applying the proposed system showed a recognition rate of 98.3%, error compensation rate 95.5% in the speech recognition.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.9-12
• /
• 2014

본 논문에서는 오인식된 고유명사의 후처리 방법을 제안한다. 최근 음성 인식 후처리를 위해 통계적 방법을 이용하는 연구가 활발히 진행되어 왔다. 하지만 고유명사의 음성 인식 후처리는 대용량의 데이터 수집에 많은 비용이 필요하므로 통계적 방법을 효과적으로 적용하기 어렵다. 따라서 본 논문에서는 발음 변이 현상을 고려하여 편집 거리 알고리즘을 개선한 기법을 제안한다. 본 논문에서는 고유명사의 음성 오인식 교정 성능을 검증하였고, 그 결과 P@3의 결과가 비교 모델보다 55%의 성능 향상률을 보였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.2
• /
• pp.1-9
• /
• 2018

In this paper, we propose a face recognition method which is not sensitive to illumination change and prevents false recognition of photographs. The proposed method uses infrared and depth images at the same time, solves sensitivity of illumination change by infrared image, and prevents false recognition of two - dimensional image such as photograph by depth image. Face detection method using infrared and depth images simultaneously and feature extraction and matching method for face recognition are realized. Simulation results show that accuracy of face recognition is increased compared to conventional methods.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.384-388
• /
• 2005

Currently most of the online handwriting recongition system are using free style input method. However, it has disadvantages of ill-recongition. In this paper, we present a new online Korean HAndwriting recongition system(KOHA) which give a slice restriction and remove the ill-recongition. KOHA uses boundary lines of input window and the stenography is possible with KOHA. Also, KOHA has the advantage of Unistroke.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.9
• /
• pp.83-90
• /
• 2009

In this paper, a method for reduction of error ratio by external light noise is proposed, which separates error moving component caused by external light noise from moving component of an object, using depth information of stereo image. If measured depth information change of extracted moving component is insignificant, the moving component is considered as external light noise, which concludes that there is no moving object. Experimental results assert the usefulness of the proposed method which makes error ratios by external light noise and by false image as shadow diminish.

• Convergence Security Journal
• /
• v.21 no.2
• /
• pp.57-66
• /
• 2021

Deep neural networks (DNNs) provide excellent performance for image, speech, and pattern recognition. However, DNNs sometimes misrecognize certain adversarial examples. An adversarial example is a sample that adds optimized noise to the original data, which makes the DNN erroneously misclassified, although there is nothing wrong with the human eye. Therefore studies on defense against adversarial example attacks are required. In this paper, we have experimentally analyzed the success rate of detection for adversarial examples by adjusting various parameters. The performance of the ensemble defense method was analyzed using fast gradient sign method, DeepFool method, Carlini & Wanger method, which are adversarial example attack methods. Moreover, we used MNIST as experimental data and Tensorflow as a machine learning library. As an experimental method, we carried out performance analysis based on three adversarial example attack methods, threshold, number of models, and random noise. As a result, when there were 7 models and a threshold of 1, the detection rate for adversarial example is 98.3%, and the accuracy of 99.2% of the original sample is maintained.

• 대한두경부종양학회:학술대회논문집
• /
• 1999.12a
• /
• pp.271.4-272
• /
• 1999

• Proceedings of the KSLP Conference
• /
• 2013.03a
• /
• pp.15-15
• /
• 2013