• Journal of the Korean Institute of Telematics and Electronics
• /
• v.18 no.2
• /
• pp.36-43
• /
• 1981

This paper describes a met hod of the extraction of phonemes in Hangout recognition. We provide the direction of strokes aid positional information for analyzing the structure of characters based on the regular combinational rules of Hangout according to Top -Down processing, and show the process of Phoneme extraction seq uencially. In this paper, some processing algorithms are described and simulated. The experiment of the phoneme extraction is carried out for 677 characters actully used daily, and extraction rate of 96% is obtained. The experimental results demonstrate the effectiveness of the proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.9
• /
• pp.19-25
• /
• 2016

This paper is to recognize and play tab chords from guitar musical sheets. The musical chord area of an input image is segmented by changing the image in saturation and applying the Grabcut algorithm. Based on a template matching, our approach detects tab starting sections on a segmented musical area. The virtual block method is introduced to search blanks over chord lines and extract tab fret segments, which doesn't cause the computation loss to remove tab lines. In the experimental tests, the prototype based classification outperforms Bayesian method and the nearest neighbor rule with the whole set of training data and its performance is similar to that of the support vector machine. The experimental result shows that the prediction rate is about 99.0% and the number of selected prototypes is below 3.0%.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.595-597
• /
• 2003

오프라인 필기체 숫자 인식에서 다양한 변형을 잘 흡수 할 수 있는 효율적인 특징을 찾는 것은 중요한 일이며, 본 논문에서는 이를 위해 다양한 단일특징들을 구현 하였으며, 단일 특징만으로는 만족 할 만한 성능을 기대하기 어렵기 때문에 다양한 단일 특징을 복합특징으로 구성하였다. 또한 오프라인 필기체 숫자인식에서 좋은 성능을 발휘하는 것으로 알려진 신경회로망으로 학습을 하였으며, 인식의 성능을 개선시키기 위해 효과적인 특징을 조합하여 하나의 단일 신경회로망들을 구성하고 그것을 다시 복합신경회로망으로 구성하여 성능을 실험 함으로서 성능의 향상을 볼 수 있었고, 신경회로망에 더하여 성능을 개선시키기 위해 신경회로망을 보완 할 수 있는 다수결 투표 방법을 사용하였다. 본 논문에서는 신경회로망의 인식 결과를 비교 분석하여 최적의 특징을 찾아 낸 결과를 2차 다수결 투표를 사용하여 인식하는 방법을 제안한다. 제안된 방식의 성능을 검증하기 위해서 Concorida 대학교의 CENPARIMI 숫자 데이터 베이스를 가지고 인식을 수행 하였으며. 그 결과 97.40%의 정인식률과 0.75%의 오인식률 그리고 1.85%의 거부률을 보였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.3
• /
• pp.481-492
• /
• 1997

This paper presents an algorithm for recognizing surface mount device(SMD) IC pattern based on the error back propoagation(EBP) neural network and discrete cosine transform(DCT). In this approach, we chose such parameters as frequency, angle, translation and amplitude for the shape informantion of SMD IC, which are calculated from the coefficient matrix of DCT. These feature parameters are normalized and then used for the input vector of neural network which is capable of adapting the surroundings such as variation of illumination, arrangement of objects and translation. Learning of EBP neural network is carried out until maximum error of the output layer is less then 0.020 and consequently, after the learning of forty thousand times, the maximum error have got to this value. Experimental results show that the rate of recognition is 100% in case of the random pattern taken at a similar circumstance as well as normalized training pattern. It also show that proposed method is not only relatively relatively simple compare with the traditional space domain method in extracting the feature parameter but also able to re recognize the pattern's class, position, and existence.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9B
• /
• pp.1775-1784
• /
• 1999

This paper proposes a method of removing unnecessary hidden nodes by a new cost function that evaluates the variance and the mean of hidden node outputs during training. The proposed cost function makes necessary hidden nodes be activated and unnecessary hidden nodes be constants. We can remove the constant hidden nodes without performance degradation. Using the CEDAR handwritten digit recognition, we have shown that the proposed method can remove the number of hidden nodes up to 37.2%, with higher recognition rate and shorter learning time.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.1 no.2
• /
• pp.49-59
• /
• 1993

A new signal processing technique is applied to four-cylinder spark and compression ignition engines for the diagnosis of power faults inside the cylinders. This technique utilizes two-sided directional power spectra(예S) of complex vibration signals measured from engine blocks as the patterns for engine cylinder power faults. The dPSs feature that they give not only the frequency contents but also the directivity of the engine block motion. For the automatic detection/diagnosis of cylinder power faults, pattern recognition method using multi-layer neural networks is employed. Experimental results show that the sucess rate for diagnosis of cylinder power faults using dPSs is higher than that using the conventional one-sided power spectra. The proposed technique is also tested to check the robustness to the sensor position and the engine rotational speed.

• Journal of the Korean Society of Safety
• /
• v.23 no.6
• /
• pp.164-170
• /
• 2008

This research was verified detection way of intercept vehicles and performance evaluation after system installation using image detector as detection way of ground installation. By image recognition algorithm was on the trace of moving orbit of violation vehicles for detection way of intercept vehicles. When moving orbit is located special site, utilized geometric image calibration and DC-notch filter. These are cognitive system of license plate by making signal. Then, Bright Evidence Detection and Dark Evidence Detection were applied to after mixing. It is applied to way of Backward tracking for detection way of intercept vehicles. After the field evaluation of developed system, it should be analyzed the more high than recognition rate of minimum standards 80%. It should rise in the estimation of the site applicability is highly from now.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2005.07a
• /
• pp.221-222
• /
• 2005

In this paper, application of NN (Neural Network) as a method of pattern discrimination of PD(partial discharge) which occurs at the stator coil of traction motor was studied. For PD data acquisition, three defective models are manufactured such as internal discharge model, slot discharge model and surface discharge model. PD data for recognition were acquired from PD detector and DAQ board which is able to analysis the PD signal and perform the pattern discrimination. Statistical distributions and parameters are calculated to discriminate PD sources. And also these statistical distribution parameters are applied to classify PD sources by BP and has good recognition rate on the discharge sources.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.83-86
• /
• 2003

This paper presents our style-based language model adaptation for Korean conversational speech recognition. Korean conversational speech is observed various characteristics of content and style such as filled pauses, word omission, and contraction as compared with the written text corpora. For style-based language model adaptation, we report two approaches. Our approaches focus on improving the estimation of domain-dependent n-gram models by relevance weighting out-of-domain text data, where style is represented by n-gram based tf*idf similarity. In addition to relevance weighting, we use disfluencies as predictor to the neighboring words. The best result reduces 6.5％ word error rate absolutely and shows that n-gram based relevance weighting reflects style difference greatly and disfluencies are good predictor.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.123-126
• /
• 2003

We discuss how to reduce the number of inverse matrix and its dimensions requested in MLLR framework for speaker adaptation. To find a smaller set of variables with less redundancy, we employ PCA(principal component analysis) and ICA(independent component analysis) that would give as good a representation as possible. The amount of additional computation when PCA or ICA is applied is as small as it can be disregarded. The dimension of HMM parameters is reduced to about 1/3 ~ 2/7 dimensions of SI(speaker independent) model parameter with which speech recognition system represents word recognition rate as much as ordinary MLLR framework. If dimension of SI model parameter is n, the amount of computation of inverse matrix in MLLR is proportioned to O($n^4$). So, compared with ordinary MLLR, the amount of total computation requested in speaker adaptation is reduced to about 1/80~1/150.