• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1278-1290
• /
• 2008

This paper proposes a preprocessing method and a neural network based character recognizer to enhance the overall performance of the license plate recognition system. First, plate outlines are extracted by virtual line matching, and then the 4 vertexes are obtained by calculating intersecting points of extracted lines. By these vertexes, plate image is reconstructed as rectangle-shaped image by bilinear transform. Finally, the license plate is recognized by the neural network based classifier which had been trained using delta-bar-delta algorithm. Various license plate images were used in the experiments, and the proposed plate normalization enhanced the recognition performance up to 16 percent.

• The Journal of the Korea Contents Association
• /
• v.5 no.4
• /
• pp.94-102
• /
• 2005

In this paper, three axial accelerometer was used to develop a small sensor module, which was attached to human body to calculate the acceleration in gravity direction by human motion, when it was positioned in any direction. To measure its wearer's walking or running motion using the sensor module, the acquired sensor data was pre-processed to enable its quantitative analysis. The acquired digital data was transformed to orthogonal coordinate value in three dimension and calculated to be single scalar acceleration data in gravity direction and normalized to be physical unit value. The normalized sensor data was used to detect walking pattern and calculate their step counts. Developed algorithm was implemented in the form of PDA application. The accuracy of the developed sensor to detect step count was about 97% in laboratory experiment.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.33-36
• /
• 1999

본 논문에서는 기존의 text-to-speech(TTS) 합성방식이 미리 정해진 화자에 의한 단조로운 합성음을 가지는 문제를 극복하기 위하여, 임의의 화자의 음색을 표현할 수 있는 화자 변환(Voice Conversion) 기능을 구현하였다. 구현된 방식은 화자의 음향공간을 Gaussian Mixture Model(GMM)로 모델링하여 연속 확률 분포에 따른 화자 변환을 가능케 했다. 원시화자(source)와 목적화자(target)간의 특징 벡터의 joint density function을 이용하여 목적화자의 음향공간 특징벡터와 변환된 벡터간의 제곱오류를 최소화하는 변환 함수를 구하였으며, 구해진 변환 함수로 벡터 mapping에 의한 스펙트럼 포락선을 변환했다. 운율 변환은 음성 신호를 정현파 모델에 의해서 모델링하고, 분석된 운율 정보(피치, 지속 시간)는 평균값을 고려해서 변환했다. 성능 평가를 위해서 VQ mapping 방법을 함께 구현하여 각각의 정규화된 켑스트럼 거리를 구해서 성능을 비교 평가하였다. 합성시에는 ABS-OLA 기반의 정현파 모델링 방식을 채택함으로써 자연스러운 합성음을 생성할 수 있었다.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.213-223
• /
• 2004

In this paper, we propose a new face detection method for real-time applications. It is based on the template-matching and appearance-based method. At first, we apply Min-max normalization with histogram equalization to the input image according to the variation of intensity. By applying the PCA transform to both the input image and template, PC components are obtained and they are applied to the LDA transform. Then, we estimate the distances between the input image and template, and we select one region which has the smallest distance. SVM is used for final decision whether the candidate face region is a real face or not. Since we detect a face region not the full region but within the $\pm$12 search window, our method shows a good speed and detection rate. Through the experiments with 6 category input videos, our algorithm shows the better performance than the existing methods that use only the PCA transform. and the PCA and LDA transform.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.11 no.5
• /
• pp.332-339
• /
• 1986

This paper proposes a new method for the normalization of shape pattern based on Gaussian probability density function to increase automatic recognition rate of hand-written Hangul pattern. The sizes of hand-written Hangul pattern are detected from the input images, and pattern sizes are normalized by two variables interpolation. The pattrn shapes are noralized by letting correlation coefficients equal to zero. It is analyzed theoretically and verified through computer simulation for the relation between input image and normaized shape pattern. It is confirmed that this method is effective and reasonable for deformed hand-written Hangul pattern. Experimental resu results show that the declination. size and stroke width of hand-written Hangul patterns are mych improved.

• Journal of KIISE:Software and Applications
• /
• v.34 no.2
• /
• pp.169-177
• /
• 2007

Hangul text normalization in current Unicode makes wrong Hangul syllable problems when using with precomposed modern Hangul syllables and composing old Hangul by using conjoining-Hangul Jamo and compatibility Hangul Jamo. This problem comes from allowing incorrect normalization form of compatibility Hangul Jamo and Hangul Symbol and also permitting to use conjoining-Hangul Jamo mixture with precomposed Hangul syllable in Unicode Hangul composing rule. It is caused by lack of consideration of old Hangul and/or insufficient understanding of Hangul code processing when writing specification for normalization forms in Unicode. Therefore on this paper, we study Hangul code in Unicode environment, specifically problems of normalization used for Web and XML, IDN in nowadays. Also we propose modification of Hangul normalization methods and Hangul composing rules for correct processing of Hangul normalization in Unicode.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.4
• /
• pp.210-216
• /
• 2005

We Propose a new feature normalization scheme based on eigenspace for achieving robust speech recognition. In general, mean and variance normalization (MVN) is Performed in cepstral domain. However, another MVN approach using eigenspace was recently introduced. in that the eigenspace normalization Procedure Performs normalization in a single eigenspace. This Procedure consists of linear PCA matrix feature transformation followed by mean and variance normalization of the transformed cepstral feature. In this method. 39 dimensional feature distribution is represented using only a single eigenspace. However it is observed to be insufficient to represent all data distribution using only a sin91e eigenvector. For more specific representation. we apply unique na independent eigenspaces to cepstra, delta and delta-delta cepstra respectively in this Paper. We also normalize training data in eigenspace and get the model from the normalized training data. Finally. a feature space rotation procedure is introduced to reduce the mismatch of training and test data distribution in noisy condition. As a result, we obtained a substantial recognition improvement over the basic eigenspace normalization.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.451-455
• /
• 2008

In this paper we embody a system that recognizes the printed alphabet of two font types (Batang, Dodum) inputted by a black-and-white CCD camera and converts it into an editable text form. The image of the inputted printed sentences is binarized, then the rows of each sentence are separated through the vertical projection using the Histogram method, and the height of the characters are normalized to 48 pixels. With the reverse application of the basic principle of the Nonogram puzzle to the individual normalized character, the character is covered with the pixel-based squares, representing the characteristics of the character as the numerical information of the Nonogram puzzle in order to recognize the character through the comparison with the standard pattern information. The test of 2609 characters of font type Batang and 1475 characters of font type Dodum yielded a 100% recognition rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.7
• /
• pp.1604-1609
• /
• 2004

We have to convert XML DTD into relational database schema for storing XML Document at relational database. Hybrid inlining algorithm are used for converting XML DTD to relational database schema. But this method have some problem. That is the relational database schema have N:N relationship are created according this method are not satisfied with third normal from. Therefore, We proposed Extended Hybrid inlining algorithm for solving this problem in this paper.