• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.55-64
• /
• 2013

Due to the popularization of digital high-performance capturing equipments and the emergence of powerful image-editing softwares, it is easy for anyone to make a high-quality counterfeit money. However, the probability of detecting a counterfeit money to the general public is extremely low. In this paper, we propose a counterfeit money detection algorithm using a general purpose scanner. This algorithm determines counterfeit money based on the different features in the printing process. After the non-local mean value is used to analyze the noises from each money, we extract statistical features from these noises by calculating a gray level co-occurrence matrix. Then, these features are applied to train and test the support vector machine classifier for identifying either original or counterfeit money. In the experiment, we use total 324 images of original money and counterfeit money. Also, we compare with noise features from previous researches using wiener filter and discrete wavelet transform. The accuracy of the algorithm for identifying counterfeit money was over 94%. Also, the accuracy for identifying the printing source was over 93%. The presented algorithm performs better than previous researches.

• Journal of the Korea Society for Simulation
• /
• v.32 no.1
• /
• pp.35-44
• /
• 2023

In recent, there are many research cases that analyze trends or research trends with text analysis. When collecting documents by searching for keywords in abbreviations for data analysis, it is necessary to disambiguate abbreviations. In many studies, documents are classified by hand-work reading the data one by one to find the data necessary for the study. Most of the studies to disambiguate abbreviations are studies that clarify the meaning of words and use supervised learning. The previous method to disambiguate abbreviation is not suitable for classification studies of documents looking for research data from abbreviation search documents, and related studies are also insufficient. This paper proposes a method of semi-automatically classifying documents collected by abbreviations by going topic modeling with Non-Negative Matrix Factorization, an unsupervised learning method, in the data pre-processing step. To verify the proposed method, papers were collected from academic DB with the abbreviation 'MSA'. The proposed method found 316 papers related to Micro Services Architecture in 1,401 papers. The document classification accuracy of the proposed method was measured at 92.36%. It is expected that the proposed method can reduce the researcher's time and cost due to hand work.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.6
• /
• pp.937-946
• /
• 1995

We proposed and efficient block segmentation and classification method for the document analysis using SGLDM(spatial gray level dependence matrix) and BP (back Propagation) neural network. Seven texture features are extracted directly from the SGLDM of each gray-level block image, and by using the nonlinear classifier of neural network BP, we can classify document blocks into 9 categories. The proposed method classifies the equation block, the table block and the flow chart block, which are mostly composed of the characters, out of the blocks that are conventionally classified as non-character blocks. By applying Sobel operator on the gray-level document image beforebinarization, we can reduce the effect of the background noises, and by using the additional horizontal-vertical smoothing as well as the vertical-horizontal smoothing of images, we can obtain an effective block segmentation that does not lead to the segmentation into small pieces. The result of experiment shows that a document can be segmented and classified into the character blocks of large fonts, small fonts, the character recognigible candidates of tables, flow charts, equations, and the non-character blocks of photos, figures, and graphs.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.326-334
• /
• 2022

In this paper, we propose speech enhancement algorithm as a pre-processing for robust speech recognition in noisy environments. Auxiliary-function-based Independent Vector Analysis (AuxIVA) is performed with weighted covariance matrix using time-varying variances with scaling factor from target masks representing time-frequency contributions of target speech. The mask estimates can be obtained using Neural Network (NN) pre-trained for speech extraction or diffuseness using Coherence-to-Diffuse power Ratio (CDR) to find the direct sounds component of a target speech. In addition, outputs for omni-directional noise are closely chained by sharing the time-varying variances similarly to independent subspace analysis or IVA. The speech extraction method based on AuxIVA is also performed in Independent Low-Rank Matrix Analysis (ILRMA) framework by extending the Non-negative Matrix Factorization (NMF) for noise outputs to Non-negative Tensor Factorization (NTF) to maintain the inter-channel dependency in noise output channels. Experimental results on the CHiME-4 datasets demonstrate the effectiveness of the presented algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.200-208
• /
• 2003

This paper proposes a separation and feature extraction of image signals using the independent component analysis(ICA) based on neural networks of efficient learning rule. The proposed learning rule is a hybrid fixed-point(FP) algorithm based on secant method and momentum. Secant method is applied to improve the performance by simplifying the 1st-order derivative computation for optimizing the objective function, which is to minimize the mutual informations of the independent components. The momentum is applied for high-speed convergence by restraining the oscillation in the process of converging to the optimal solution. The proposed algorithm has been applied to the composite images generated by random mixing matrix from the 10 images of $512\times512$-pixel. The simulation results show that the proposed algorithm has better performances of the separation speed and rate than those using the FP algorithm based on Newton and secant method. The proposed algorithm has been also applied to extract the features using a 3 set of 10,000 image patches from the 10 fingerprints of $256\times256$-pixel and the front and the rear paper money of $480\times225$-pixel, respectively, The simulation results show that the proposed algorithm has also better extraction speed than those using the another methods. Especially, the 160 basis vectors(features) of $16\times16$-pixel show the local features which have the characteristics of spatial frequency and oriented edges in the images.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.3
• /
• pp.98-107
• /
• 2007

For high-dimensional pattern recognition, such as face classification, the small number of training samples leads to the Small Sample Size problem when the number of pattern samples is smaller than the number of dimensionality. Recently, various LDA-extensions have been developed, including LDA, PCA+LDA, and Direct-LDA, to address the problem. This paper proposes a method of improving the classification efficiency by increasing the number of (sub)-classes through pre-clustering a training set prior to the execution of Direct-LDA. In LDA (or Direct-LDA), since the number of classes of the training set puts a limit to the dimensionality to be reduced, it is increased to the number of sub-classes that is obtained through clustering so that the classification performance of LDA-extensions can be improved. In other words, the eigen space of the training set consists of the range space and the null space, and the dimensionality of the range space increases as the number of classes increases. Therefore, when constructing the transformation matrix, through minimizing the null space, the loss of discriminatve information resulted from this space can be minimized. Experimental results for the artificial data of X-OR samples as well as the bench mark face databases of AT&T and Yale demonstrate that the classification efficiency of the proposed method could be improved.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.485-490
• /
• 2004

In data representation, the clustering performs a grouping process which combines given data into some similar clusters. The various similarity measures have been used in many researches. But, the validity of clustering results is subjective and ambiguous, because of difficulty and shortage about objective criterion of clustering. The fuzzy clustering provides a good method for subjective clustering problems. It performs clustering through the similarity matrix which has fuzzy membership value for assigning each object. In this paper, for objective fuzzy clustering, the clustering algorithm which joins principal components analysis as a dimension reduction model with bayesian learning as a statistical learning theory. For performance evaluation of proposed algorithm, Iris and Glass identification data from UCI Machine Learning repository are used. The experimental results shows a happy outcome of proposed model.

• Archives of design research
• /
• v.18 no.2 s.60
• /
• pp.79-90
• /
• 2005

The aim of this study was to investigate how the psychological factors of human interrelation or human socialization are associated with the visual design based on sociological and psychological theories. To accomplish this goal, human socialization was examined on the basis of physiology, philosophy, and psychology. Then a case study was employed to assess how they function in the area of visual design. In literature, the sources of psychological factors of human socialization were categorized into 11 items including the sexual hedonic pursuit. These items were used for the evaluation of 40 printed media advertisements, all of which were the winners of the Korea Advertising Awards from 1994 to 2003. As a result, it was revealed that most advertisements responded to the items of adaptive value and cultural imprinting as biological bases. Also, it was discovered that the existential foundation of advertising has been based on mutual distrust and the payoff matrix as a mind of social unrest. In conclusions, it was illustrated that future advertising will remain based on adaptive value, cultural imprinting, social learning, and imitation learning, as long as advertising continue to hold its reason for existence.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.6-11
• /
• 2011

In this paper, we propose a gait-based human identification system using eigenfeature regularization and extraction (ERE). First, a gait feature for human identification which is called gait energy image (GEI) is generated from walking sequences acquired from a camera sensor. In training phase, regularized transformation matrix is obtained by applying ERE to the gallery GEI dataset, and the gallery GEI dataset is projected onto the eigenspace to obtain galley features. In testing phase, the probe GEI dataset is projected onto the eigenspace created in training phase and determine the identity by using a nearest neighbor classifier. Experiments are carried out on the CASIA gait dataset A to evaluate the performance of the proposed system. Experimental results show that the proposed system is better than previous works in terms of correct classification rate.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2003.05a
• /
• pp.87-91
• /
• 2003

It has well known that MUSIC and ESPRIT algorithms estimate angle of arrival(AOA) with high resolution by eigenvalue decomposition of the covariance matrix which were obtained from the array antennas. However, the disadvantage of MUSIC and ESPRIT is that they are computationally ineffective, and then they are difficult to implement in real time. The other problem of MUSIC and ESRPIT is to require calibrated antennas with uniform features, and are sensitive to the manufacturing facult and other physical uncertainties. To overcome these disadvantages, several method using neural model have been study. For multiple signals, those require huge training data prior to AOA estimation. This paper proposes the algorithm for AOA estimation by interconnected hopfield neural model. Computer simulations show the validity of the proposed algorithm. The proposed method does not require huge training procedure and only assigns interconnected coefficients to the neural network prior to AOA estimation.