• Journal of the Korea Computer Graphics Society
• /
• v.8 no.3
• /
• pp.17-23
• /
• 2002

Motion capture system is widely used nowadays in the entertainment industry like movies, computer games and broadcasting. This system consist of several high resolution and high speed CCD cameras and expensive frame grabbing hardware for image acquisition. KAIST VR laboratory focused on low cost system for a few years and have been developed a LAN based optical motion capture system. But, by using low cost system some problems like occlusion, noise and swapping of markers' trajectory can be occurred. And more labor intensive work is needed for post-processing process. In this thesis, we propose a trajectory rectification algorithm by confidence model of markers attached on actor. Confidence model is based on graph structure and consist of linkage, marker and frame confidence. To reduce the manual work in post-processing, we have to reconstruct the marker graph by maximizing the frame confidence.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.552-559
• /
• 2011

In this paper, a new image watermarking algorithm is proposed which can hide specific information of an ID card's owner in photo image for preventing ID's photo forgery. Proposed algorithm uses the image segmentation and the correlation peak position modulation of spread spectrum. The watermark embedded in photo ensures not only robustness against printing and scanning but also sufficient information capacity hiding unique number such as social security numbers in small-sized photo. Another advantage of proposed method is extracting accurate information with error tolerance within some rotation range by using $2^h{\times}2^w$ unit sample space not instead $1{\times}1$ pixels for insertion and extraction of information. 40 bits information can be embedded and extracted at $256{\times}256$ sized ID photo with BER value of 0 % when the test condition is 300dpi scanner and photo printer with 22 photos. In conclusion, proposed algorithm shows the robustness for noise and rotational errors occured during printing and scanning.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.4
• /
• pp.113-123
• /
• 2004

This paper presents a new collusion-secure fingerprinting scheme to embed fingerprints into three-dimensional(3-D) mesh models efficiently. In the proposed scheme, we make the same number of fingerprints as the number of customers based on the finite projective geometry, partition a 3-D mesh model related to the number of bits assigned to each fingerprint and then embed a watermark representing copyright information into each submesh to be marked. Considering imperceptibility and robustness of the watermarking algorithm we embed the watermark signal into mid-frequency DCT coefficients obtained by transforming vertex coordinates in the triangle strips which are generated from the submeshes to be marked. Experimental results show that our scheme is robust to additive random noises, MPEG-4 SNHC 3-D mesh coding, geometrical transformations, and fingerprint attacks by two traitors' collusion. In addition, we can reduce the number of bits assigned to each fingerprint significantly.

• 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.

• Journal of KIISE:Software and Applications
• /
• v.29 no.4
• /
• pp.248-257
• /
• 2002

Clustering is a method for grouping objects with similar properties into a same cluster. SVD(Singular Value Decomposition) is known as an efficient preprocessing method for clustering because of dimension reduction and noise elimination for a high dimensional and sparse data set like E-Commerce data set. However, it is hard to evaluate the worth of original attributes because of information loss of a converted data set by SVD. This research proposes a cluster feature selection method, called ENTROPY-SVD, to find important attributes for each cluster based on entropy weighting and SVD. Using SVD, one can take advantage of the latent structures in the association of attributes with similar objects and, using entropy weighting one can find highly dense attributes for each cluster. This paper also proposes a model-based collaborative filtering recommendation system with ENTROPY-SVD, called CFS-CF and evaluates its efficiency and utilization.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2C
• /
• pp.262-271
• /
• 2004

There are channel errors when video data are transmitted between encoder and decoder. These channel errors would make decoded image incorrect, so it is very important to detect and recover channel errors. This paper proposes a method of error detection and recovery by hiding specific information into video bitstream using fragile watermark and checking it later. The proposed method requires no additional bits into compressed bitstream since it embeds a user-specific data pattern in the least significant bits of LEVELs in VLC codewords. The decoder can extract the information to check whether the received bitstream has an error or not. We also propose to use this method to embed essential data such as motion vectors that can be used for error recovery. The proposed method can detect corrupted MBs that usually escape the conventional syntax-based error detection scheme. This proposed method is quite simple and of low complexity. So the method can be applied to multimedia communication system in low bitrate wireless channel.

• Journal of Digital Convergence
• /
• v.13 no.5
• /
• pp.237-244
• /
• 2015

Export-led policies, FTA signed and economics of scale through a variety of market-oriented policies, such as regulations to improve market grew constantly. Accordingly, the correct decision making accurately analyze the economics market for decision, a problem has been an important issue in predicting. For accurate analysis and decision-making of the most common indicators of the stock market by proposing a number of indicators of economic transformation techniques were applied to the convergence model combining estimation and forecasts problem confirmed its effectiveness. Experimental result, gave the model estimation method to apply a transform to show the valid combinations proposed model state estimation result was confirmed in a very similar exercise aspect of the physical problem and the KOSPI index prediction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1542-1550
• /
• 2019

Legacy studies for classifying arrhythmia have been studied to improve the accuracy of classification, Neural Network, Fuzzy, etc. Deep learning is most frequently used for arrhythmia classification using error backpropagation algorithm by solving the limit of hidden layer number, which is a problem of neural network. In order to apply a deep learning model to an ECG signal, it is necessary to select an optimal model and parameters. In this paper, we propose optimal parameter extraction method based on a deep learning. For this purpose, R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval segment is modelled. And then, the weights were learned by supervised learning method through deep learning and the model was evaluated by the verification data. The detection and classification rate of R wave and PVC is evaluated through MIT-BIH arrhythmia database. The performance results indicate the average of 99.77% in R wave detection and 97.84% in PVC classification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1341-1347
• /
• 2020

Legacy studies for classifying arrhythmia have been studied in order to improve the accuracy of classification, Neural Network, Fuzzy, Machine Learning, etc. In particular, deep learning is most frequently used for arrhythmia classification using error backpropagation algorithm by solving the limit of hidden layer number, which is a problem of neural network. In order to apply a deep learning model to an ECG signal, it is necessary to select an optimal model and parameters. In this paper, we propose parameter extraction based on AR and arrhythmia classification through a deep learning. For this purpose, the R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval is modelled. And then, the weights were learned by supervised learning method through deep learning and the model was evaluated by the verification data. The classification rate of PVC is evaluated through MIT-BIH arrhythmia database. The achieved scores indicate arrhythmia classification rate of over 97%.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.1
• /
• pp.32-43
• /
• 2009

In this paper, we improve the performance of cardiac disorder classification by continuous heart sound signals using automatic segmentation and extreme learning machine (ELM). The accuracy of the conventional cardiac disorder classification systems degrades because murmurs and click sounds contained in the abnormal heart sound signals cause incorrect or missing starting points of the first (S1) and the second heart pulses (S2) in the automatic segmentation stage, In order to reduce the performance degradation due to segmentation errors, we find the positions of the S1 and S2 pulses, modify them using the time difference of S1 or S2, and extract a single period of heart sound signals. We then obtain a feature vector consisting of the mel-scaled filter bank energy coefficients and the envelope of uniform-sized sub-segments from the single-period heart sound signals. To classify the heart disorders, we use ELM with a single hidden layer. In cardiac disorder classification experiments with 9 cardiac disorder categories, the proposed method shows the classification accuracy of 81.6% and achieves the highest classification accuracy among ELM, multi-layer perceptron (MLP), support vector machine (SVM), and hidden Markov model (HMM).