• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.374-379
• /
• 2003

본 논문에서는 pattern recognition을 위하여 support vector fuzzy inference system을 제안하였다 Fuzzy inference system의 structure와 parameter를 identification 하기 위하여 Support vector machine을 이용하였으며 에러 최소화 기법으로는 gradient descent 방법을 사용하였다. 제안된 SVFIS 방법의 성능을 파악하고자 COIL 이미지를 이용한 3차원 물체 인식 실험을 수행하였다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.3
• /
• pp.221-225
• /
• 2010

This paper presents the preliminary study of an interactive rehabilitation support system for both dementia patients and their caregivers, the goal of which is to improve the quality of life(QOL) of the patients suffering from dementia through virtual interaction. To achieve the virtual interaction, three kinds of recognition modules for speech, facial image and pen-mouse gesture are studied. The results of both practical tests and questionnaire surveys show that the proposed system had to be further improved, especially in both speech recognition and user interface for real-world applications. The surveys also revealed that the pen-mouse gesture recognition, as one of possible interactive aids, show us a probability to support weakness of speech recognition.

• ETRI Journal
• /
• v.36 no.5
• /
• 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.

• The Journal of Korean Association of Computer Education
• /
• v.17 no.5
• /
• pp.69-77
• /
• 2014

The purpose of this study was to investigate the recognition on the administrative and financial support system to execute integrated early education program by kindergarten and educational offices. The results were as follows. First, there has been a difference of recognition by three variables: 1) teachers' position in the area of all, law and institution, curriculum, administrative and financial support, and assessment, 2) educational career in the area of all, law and institution, curriculum, and supervision, 3) integrated education career in the area of all, law and institution, administrative and financial support and assessment. Second, there has been a difference of recognition by two variables: 1) kindergarten institutional establishment in the area of all, law and institutions, curriculum, teaching-learning, financial support, and assessment. 2) size in the area of all, law and institutions, curriculum, supervision, administrative and financial support, and assessment.

• Journal of Digital Convergence
• /
• v.10 no.9
• /
• pp.339-344
• /
• 2012

Established continuous vocabulary recognition system improved recognition rate by using decision tree based tying modeling method. However, since system model cannot support the retrieve of phoneme data, it is hard to secure the accuracy. In order to improve this problem, we remodeled a system that could retrieve probabilistic model from continuous vocabulary clustering model to phoneme unit. Therefore in this paper showed 95.88%of recognition rate in system performance.

• Journal of Digital Convergence
• /
• v.10 no.11
• /
• pp.359-363
• /
• 2012

In the vocabulary recognition model, system has some problems that vocabulary is nor recognize and similar vocabulary recognition is created., because it is caused by system extract vocabulary feature from inaccurate vocabulary. To solve this problems, this paper propose the system modeling and implementation for efficient configuration thread support system, it process the configuration thread information and it apply the facet method in database retrieve for optimization of vocabulary likelihood rate. Proposed system showed 95.31% of vocabulary dependency recognition rate and 97.38% vocabulary independency recognition rate in system performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.431-436
• /
• 1989

A rule-based recognition system for Korean spoken place names using anti-formants which is analyzed by ARMA model is presented. The recognition system is composed of three parts; the extraction, the recognition and the recognition support. As a result of experiment, the recognition rates of city place names was 90.9%.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.5
• /
• pp.259-266
• /
• 2014

In this paper, we propose a novel technique for noise robust automatic speech recognition (ASR). The development of ASR techniques has made it possible to recognize isolated words with a near perfect word recognition rate. However, in a highly noisy environment, a distinct mismatch between the trained speech and the test data results in a significantly degraded word recognition rate (WRA). Unlike conventional ASR systems employing Mel-frequency cepstral coefficients (MFCCs) and a hidden Markov model (HMM), this study employ histogram of oriented gradient (HOG) features and a Support Vector Machine (SVM) to ASR tasks to overcome this problem. Our proposed ASR system is less vulnerable to external interference noise, and achieves a higher WRA compared to a conventional ASR system equipped with MFCCs and an HMM. The performance of our proposed ASR system was evaluated using a phonetically balanced word (PBW) set mixed with artificially added noise.

• International Journal of Internet, Broadcasting and Communication
• /
• v.9 no.1
• /
• pp.9-17
• /
• 2017

This paper describes a process of developing commercial real time image recognition system with company. In this paper we will make a system that is combining an empirical kernel map method and conjugate least squares support vector machine in order to represent images in a low-dimensional subspace for real time image recognition. In the traditional approach calculating these eigenspace models, known as traditional PCA method, model must capture all the images needed to build the internal representation. Updating of the existing eigenspace is only possible when all the images must be kept in order to update the eigenspace, requiring a lot of storage capability. Proposed method allows discarding the acquired images immediately after the update. By experimental results we can show that empirical kernel map has similar accuracy compare to traditional batch way eigenspace method and more efficient in memory requirement than traditional one. This experimental result shows that proposed model is suitable for commercial real time image recognition system.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.327-330
• /
• 2000

In this paper, we describe an intelligent method to detect types of vehicles using Support Vector Machines focused to the Intelligent Transportation System (ITS) applications such as in the CCD based Electronic Toll Collection System (ETCS). This algorithm can be used the various fields of ITS applications. Support Vector Machines employed in this paper has been recently proposed as a very effective method for 3D image recognition. And our proposed feature extraction method using the singluar values that directly come from pixels at input images. Consequently, The low calculation load and the high recognition rate in spite of image rotation and various noises are one of merits of proposed method.