• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권10호
• /
• pp.446-452
• /
• 2002

For most of pattern recognition applications, it is required to correctly recognize patterns even if they have translation variations. In this paper, to achieve the goal of translation invariant pattern recognition, we propose a new generalized translation invariant second-order neural network using a constraint on the weights. The weight constraint is implemented using generalized translation invariant features which are accumulated sums of pixel combinations. Simulation results will be given to demonstrate that the proposed second-order neural network has the generalized translation invariant property.

• 말소리와 음성과학
• /
• 제8권2호
• /
• pp.23-30
• /
• 2016

This paper describes some implementation schemes of CNN in view of mini-batch DNN training for efficient second order optimization. This uses same procedure updating parameters of DNN to train parameters of CNN by simply arranging an input image as a sequence of local patches, which is actually equivalent with mini-batch DNN training. Through this conversion, second order optimization providing higher performance can be simply conducted to train the parameters of CNN. In both results of image recognition on MNIST DB and syllable automatic speech recognition, our proposed scheme for CNN implementation shows better performance than one based on DNN.

• 음성과학
• /
• 제7권3호
• /
• pp.69-85
• /
• 2000

Recently, Computer Assisted Language Learning (CALL) received widely held attention from diverse audiences. However, to the author's knowledge, relatively little attention was paid to the educational implications of voice recognition (VR) softwares in language teaching in general, and teaching and learning pronunciation in particular. This study explores, and extends the applicability of VR softwares toward second language research areas addressing how VR softwares might facilitate interview data entering processes. To aid the readers' understanding in this field, the background of classroom interaction research, and the rationale of why interview data, therefore the role of VR softwares, becomes critical in this realm of inquiry will be discussed. VR softwares' development and a brief report on the features of up-to-date VR softwares will be sketched. Finally, suggestions for future studies investigating the impact of VR softwares on second language learning, teaching, and research will be offered.

• 한국생활과학회지
• /
• 제17권2호
• /
• pp.223-233
• /
• 2008

The purpose of this study was to find out conflict of preservice teachers affected by the role recognition and performance of cooperating teachers in the early childhood education practicum. The following research questions were established in order to achieve this purpose. First, Is there any differences in conflict of preservice teachers according to their personal variables? Second, Is there any differences in the role recognition and performance of cooperating teachers according to their personal variables? Third, Is there any differences in conflict of preservice teachers according to the role recognition and performance of cooperating teachers? The subjects of this study were 214 pairs of cooperating teachers who taught preservice teachers. The data were collected with the role recognition and performance of cooperating teachers and conflict of preservice teacher instrument and analyzed by t-test and ANOVA using SPSS 14.0 software. The results show that there was significantly difference conflict of preservice teachers according to their personal variables. Second, there was significantly differences the role recognition and performance of cooperating teachers according to their personal variables. Third, there was significantly differences conflict of preservice teachers affected by the role recognition and performance of cooperating teachers in the early childhood education practicum.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 제11회 음성통신 및 신호처리 워크샵 논문집 (SCAS 11권 1호)
• /
• pp.395-398
• /
• 1994

In this paper the word recognition using sub-model based Hidden Markov Model was studied. Phoneme models were composed of 61 phonemes in therms of Korean language pronunciation characteristic. Using this, word model was maded by serial concatenation. But, in case of this phoneme concatenation, the second and the third phoneme of syllable are overlapped in distribution at the same time. So considering this, the method that combines the second and the third phoneme to one model was proposed. And to prevent the increase in number of model, similar phonemes were combined to one, and finially, 57 models were created. In experiment proper model structure of sub-model was searched for, and recognition results were compared. So similar recognition results were maded, and overall recognition rates were increased in case of using parameter tying method.

• 한국멀티미디어학회논문지
• /
• 제21권11호
• /
• pp.1244-1253
• /
• 2018

The color of traffic light is sensitive to various illumination conditions. Especially it loses the hue information when oversaturation happens on the lighting area. This paper proposes a traffic light recognition method robust to these illumination variations. The method consists of two steps of traffic light detection and recognition. It just uses the intensity and saturation in the first step of traffic light detection. It delays the use of hue information until it reaches to the second step of recognizing the signal of traffic light. We utilized a deep learning technique in the second step. We designed a deep convolutional neural network(DCNN) which is composed of three convolutional networks and two fully connected networks. 12 video clips were used to evaluate the performance of the proposed method. Experimental results show the performance of traffic light detection reporting the precision of 93.9%, the recall of 91.6%, and the recognition accuracy of 89.4%. Considering that the maximum distance between the camera and traffic lights is 70m, the results shows that the proposed method is effective.

• 음성과학
• /
• 제12권1호
• /
• pp.7-14
• /
• 2005

This study investigated the reading ability of Korean second-graders and the relationship between reading and phonological awareness and RAN (Rapid Automatized Naming) ability. A language-based reading assessment battery was used. Children at the end of the Korean second-grade were still at the developmental stage of decoding skill and seemed to be at Chall's stage 1. Findings indicated significant correlations between reading ability and phonological awareness and between reading ability and RAN ability. Therefore, the importance of phonological processing could be extended to syllable-based alphabetic languages.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권10호
• /
• pp.473-478
• /
• 2001

Image processings using the two-dimensional wavelet transform (2DWT) have been a very active research area in recent years because the 2DWT possess many good properties. However, the discrete 2DWT can not be used for pattern recognition directly because it does not have the translation property. In this paper, we show why conventional discrete two-dimensional wavelet transforms cannot be used for pattern recognitions directly. Then, we propose a new method that makes it possible to use discrete 2DWT to pattern recognition without modification of standard pyramidal algorithms. The main idea of our method is to postprocess the wavelet transformed images using the second-order neural network. To justify the validity of the method, evaluations with test images were performed. The effectiveness of the method can be shown by the evaluation results.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2463-2466
• /
• 2003

This paper studied the pattern recognition algorithm and feature parameters for emotion recognition. In this paper, KNN algorithm was used as the pattern matching technique for comparison, and also VQ and GMM were used lot speaker and context independent recognition. The speech parameters used as the feature are pitch, energy, MFCC and their first and second derivatives. Experimental results showed that emotion recognizer using MFCC and their derivatives as a feature showed better performance than that using the Pitch and energy Parameters. For pattern recognition algorithm, GMM based emotion recognizer was superior to KNN and VQ based recognizer

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2006년도 추계 종합학술대회 논문집
• /
• pp.533-535
• /
• 2006

본 논문은 얼굴 인식에서 널리 사용되고 있는 PCA 기법에서 1, 2, 3차의 저차원의 특징 벡터를 배제하여 조명있는 얼굴의 인식률 변화를 실험하였다. 보편적으로 저차원 3개를 배제할 경우 조명에 강건한 얼굴 인식을 보인다고 하나, 저차원의 어느 부분이 조명에 크게 관여가되는지는 알려지지 않고 있다. 이에 본 연구에서는 1차, 2차, 3차 및 이를 조합하여 저차원의 조명에 대한 영향을 분석하였다.