• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.1
• /
• pp.112-119
• /
• 2000

A die-casting junction method is usually used to manufacture the tub of an IH(induction heating) jar. If there is a very small air bubble in the junction area, the thermal conductivity is deteriorated and local overheat occurs. Such problem brings serious inferiority of the IH jar. In this paper, we propose a new method to detect such defect with simply measured thermal data. Thermal distribution of preheated tubs is obtained by scanning with infrared thermal sensors and analyzed with the statistic pattern recognition method. By defining the characteristic feature as the temperature difference between sensors and using ellipsoid function as decision boundary, a supervised learning method of genetic algorithm is proposed to obtain the required parpameters. After applying the proposed method to experiment, we have proved that the rate of recognition is high even for a small number of data set.

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.103-110
• /
• 2017

The pole filtering concept has been successfully applied to cepstral feature normalization techniques for noise-robust speech recognition. In this paper, it is proposed to apply the pole filtering selectively only to the speech intervals, in order to further improve the recognition performance for short utterances in noisy environments. Experimental results on AURORA 2 task with clean-condition training show that the proposed selectively pole-filtered cepstral mean normalization (SPFCMN) and selectively pole-filtered cepstral mean and variance normalization (SPFCMVN) yield error rate reduction of 38.6% and 45.8%, respectively, compared to the baseline system.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.48-53
• /
• 2002

In this paper, we presented a new approach to the recognition of unconstrained handwritten numerals using an improved RBF(Radial Basis Function) Neural Networks. The RBF Neural Networks used Raised Cosine as a basis function to improve discrimination and reduce processing time. The performance of Raised Cosine RBF Neural Networks classifier was evaluated using totally unconstrained handwritten numeral database of Concordia University, Montreal, Canada, and the experimental results showed the recognition rate of 98.05%.

• Journal of Korean Port Research
• /
• v.12 no.2
• /
• pp.225-232
• /
• 1998

Todays, the efficient management of container has not been realized in container terminal, because of the excessive quantity of container transported and manual system. For the efficient and automated management of container in terminal, the automated container identifier recognition system in terminal is a significant problem. However, the identifier recognition rate is decreased owing to the difficulty of image preprocessing caused the refraction of container surface, the change of weather and the damaged identifier characters. Therefore, this paper proposes more accurate system for container identifier recognition as suggestion of LSPRD(Line-Scan Proper Region Detection) for stronger preprocessing against external noisy element and MBP(Momentum Back-Propagation) neural network to recognize the identifier.

• The Journal of Information Technology
• /
• v.9 no.1
• /
• pp.55-63
• /
• 2006

In this paper, a Hangul recognition system using of Kohonen Network in the phoneme separation and learning is proposed. A Hangul consists of phoneme that are consists of strokes. The phoneme recognition and separation are very important in the recognition of character. So, the phonemes which mismatching has been happened are correctly separated through the learning of neural networks. also, learning rate($\alpha$) adjusted according to error, in order to solved that its decreased the number of iteration and the problem of local minimum, adaptively.

• MALSORI
• /
• no.54
• /
• pp.63-72
• /
• 2005

The performance of speech recognition system is degraded by the mismatch between training and test environments. Many studies have been presented to compensate for noise components in the cepstral domain. Recently, higher order cepstral moment normalization method has been introduced to improve recognition accuracy. In this paper, we present real-time high order moment normalization method with post-processing smoothing filter to reduce the parameter estimation error in higher order moment computation. In experiments using Aurora2 database, we obtained error rate reduction of 44.7% with proposed algorithm in comparison with baseline system.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• pp.103-106
• /
• 2005

In this paper, we propose a language modeling approach to improve the performance of a large vocabulary continuous speech recognition system. The proposed approach is based on the active learning framework that helps to select a text corpus from a plenty amount of text data required for language modeling. The perplexity is used as a measure for the corpus selection in the active learning. From the recognition experiments on the task of continuous Korean speech, the speech recognition system employing the language model by the proposed language modeling approach reduces the word error rate by about 6.6 % with less computational complexity than that using a language model constructed with randomly selected texts.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.5
• /
• pp.601-606
• /
• 2019

This paper is a study on speech recognition in the Korean using grapheme unit (Cho-sumg [onset], Jung-sung [nucleus], Jong-sung [coda]). Here we make ASR (Automatic speech recognition) system without G2P (Grapheme to Phoneme) process and show that Deep learning based ASR systems can learn Korean pronunciation rules without G2P process. The proposed model is shown to reduce the word error rate in the presence of sufficient training data.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.40-49
• /
• 2018

We propose a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. We propose detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). The feature vector is applied to LDA and using Euclidean distance of intra-class variance and inter class variance in the 2nd dimension, the final analysis and matching is performed. Experimental results show that the proposed method has a wider distribution when the input image is rotated $45^{\circ}$ left / right. We can improve the recognition rate by applying this feature value to a single algorithm and complex algorithm, and it is possible to recognize in real time because it does not require much calculation amount due to dimensional reduction.

• Journal of Information Processing Systems
• /
• v.15 no.1
• /
• pp.91-99
• /
• 2019

An innovative tone modeling framework based on deep neural networks in tone recognition was proposed in this paper. In the framework, both the prosodic features and the articulatory features were firstly extracted as the raw input data. Then, a 5-layer-deep deep belief network was presented to obtain high-level tone features. Finally, support vector machine was trained to recognize tones. The 863-data corpus had been applied in experiments, and the results show that the proposed method helped improve the recognition accuracy significantly for all tone patterns. Meanwhile, the average tone recognition rate reached 83.03%, which is 8.61% higher than that of the original method.