• Journal of the Korean Professional Engineers Association
• /
• v.29 no.2
• /
• pp.71-79
• /
• 1996

This paper evaluates the clustering performance of a neural network and a statistical method. Algorithms which are used in this paper are the GLVQ(Generalized Loaming vector Quantization) for a neural method and the k -means algorithm for a statistical clustering method. For comparison of two methods, we calculate the Rand's c statistics. As a result, the mean of c value obtained with the GLVQ is higher than that obtained with the k -means algorithm, while standard deviation of c value is lower. Experimental data sets were the Fisher's IRIS data and patterns extracted from handwritten numerals.

• Journal of the Korean Data and Information Science Society
• /
• v.16 no.2
• /
• pp.313-325
• /
• 2005

In Korea, there exists a large corpus of handwritten historical documents that serve as a valuable resource. Most of them are hand-written by the King's chroniclers and secretaries. Recently, the historical archives of Lee dynasty have been digitalized. Since it is extremely difficult to utilize conventional OCR system, most of the processes have been performed manually. In this paper, we propose OCR-based digitalization system using Mahalanobis distance-based rejection and interface for eye inspection about historical Hanja documents. Compared with our previous work, experimental results show that the proposed system can help enhancing the overall efficiency of the process.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.4
• /
• pp.355-360
• /
• 2015

In this paper, we propose the design of Radial Basis Function Neural Network based on PCA in order to recognize handwritten digits. The proposed pattern classifier consists of the preprocessing step of PCA and the pattern classification step of pRBFNNs. In the preprocessing step, Feature data is obtained through preprocessing step of PCA for minimizing the information loss of given data and then this data is used as input data to pRBFNNs. The hidden layer of the proposed classifier is built up by Fuzzy C-Means(FCM) clustering algorithm and the connection weights are defined as linear polynomial function. In the output layer, polynomial parameters are obtained by using Least Square Estimation (LSE). MNIST database known as one of the benchmark handwritten dataset is applied for the performance evaluation of the proposed classifier. The experimental results of the proposed system are compared with other existing classifiers.

• Journal of KIISE:Software and Applications
• /
• v.29 no.8
• /
• pp.521-528
• /
• 2002

We propose a new approach to the feature selection for the classification of handwritten characters using two-dimensional(2D) wavelet packet bases. To extract key features of an image data, for the dimension reduction Principal Component Analysis(PCA) has been most frequently used. However PCA relies on the eigenvalue system, it is not only sensitive to outliers and perturbations, but has a tendency to select only global features. Since the important features for the image data are often characterized by local information such as edges and spikes, PCA does not provide good solutions to such problems. Also solving an eigenvalue system usually requires high cost in its computation. In this paper, the original data is transformed with 2D wavelet packet bases and the best discriminant basis is searched, from which relevant features are selected. In contrast to PCA solutions, the fast selection of detailed features as well as global features is possible by virtue of the good properties of wavelets. Experiment results on the recognition rates of PCA and our approach are compared to show the performance of the proposed method.

• Journal of KIISE:Software and Applications
• /
• v.29 no.10
• /
• pp.684-693
• /
• 2002

Electronic Ink is a stored data in the form of the handwritten text or the script without converting it into ASCII by handwritten recognition on the pen-based computers and Personal Digital Assistants(PDAs) for supporting natural and convenient data input. One of the most Important issue is to search the electronic ink in order to use it. We proposed and implemented a script matching algorithm for the electronic ink. Proposed matching algorithm separated the input stroke into a set of primitive stroke using the curvature of the stroke curve. After determining the type of separated strokes, it produced a stroke feature vector. And then it calculated the distance between the stroke feature vector of input strokes and one of strokes in the database using the dynamic programming technique. We did various experiments and our algorithm showed high matching rate over 97.7% for only the Korean script and 94% for the data mixed Korean with the Chinese character.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.2
• /
• pp.157-168
• /
• 1993

In this paper, it is shown that neural networks trained with back propagation algorithm and dictionary can be applied to recognize handwritten English characters. To eliminate the useless data part and to minimize the variety of characters from the scanned image file, various preprocessings : that is, segmentation, centering, noise filtering, sealing and thinning are performed. After these, characteristic features are derived from thinned character pattern. The neural network is trained by using the extracted features for sample data, and all test data are classified into English alphabets according to their features through the neural network. Finally, the ways of reducing learning time and improving recognition rate, and the relationship between learning time and hidden layer nodes are considered. As a result of this study, after successful training, a high recognition rate has been obtained with this system for the trained patterns and about 93% for test patterns. Using dictionary, the recognition rate was about 97% for test pattern.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.215-218
• /
• 2000

This paper describes a new algorithm for segmenting continuous handwritten signatures sampled by a digitizer. Signatures are segmented by three procedures. The first step is to calculate the pen tip speed. Then the Gabor wavelet is carried out on the acquired data from the first step. Finally, the local minima of the filtered output are selected as segmentation points of the signature. The proposed method is experimented with numerous signatures with various length and complexity.

• Journal of Computing Science and Engineering
• /
• v.12 no.1
• /
• pp.24-35
• /
• 2018

Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.

• Journal of Platform Technology
• /
• v.6 no.1
• /
• pp.3-8
• /
• 2018

This paper proposes a technique for recognizing online handwritten cursive data obtained by tracing a motion trajectory while a user is in the 3D space based on a convolution neural network (CNN) algorithm. There is a difficulty in recognizing the virtual character input by the user in the 3D space because it includes both the character stroke and the movement stroke. In this paper, we divide syllable into consonant and vowel units by using labeling technique in addition to the result of localizing letter stroke and movement stroke in the previous study. The coordinate information of the separated consonants and vowels are converted into image data, and Korean handwriting recognition was performed using a convolutional neural network. After learning the neural network using 1,680 syllables written by five hand writers, the accuracy is calculated by using the new hand writers who did not participate in the writing of training data. The accuracy of phoneme-based recognition is 98.9% based on convolutional neural network. The proposed method has the advantage of drastically reducing learning data compared to syllable-based learning.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.3
• /
• pp.50-59
• /
• 1993

There is basic problem with the current evaluation method for character recognition systems. The current method evaluates the average recognition rate by applying the test data to the target system. The average recognition rate tells no more than and no less than the overall performance and it depends on the data. In this paper we propose a testing method which will analyze the target system and point out its strong points and weak points. This can be made possible through using the data which are generated cy distorting the standard character images according to a carefully controlled manner. This paper will describe how to automatically generate such distorted images. Also we will show the method is actually effective and useful by applying it to evaluating existing recognition algorithms.