• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.197-202
• /
• 2021

Biometric technology using finger veins is receiving a lot of attention due to its high security, convenience and accuracy. And the recent development of deep learning technology has improved the processing speed and accuracy for authentication. However, the training data is a subset of real data not in a certain order or method and the results are not constant. so the amount of data and the complexity of the artificial neural network must be considered. In this paper, the deep learning model of Inception-Resnet-v2 was used to improve the high accuracy of the finger vein recognizer and the performance of the authentication system, We compared and analyzed the performance of the deep learning model of DenseNet-201. The simulations used data from MMCBNU_6000 of Jeonbuk National University and finger vein images taken directly. There is no preprocessing for the image in the finger vein authentication system, and the results are checked through EER.

• Journal of Korea Multimedia Society
• /
• v.24 no.4
• /
• pp.583-592
• /
• 2021

Obsessive-compulsive disorder (OCD) is a mental disorder in which a person repeated a particular thought or feels. The domain of beliefs and guilt predicted OCD symptoms. Although there were some neuroimaging studies investigating OCD symptoms, resting-state functional magnetic resonance imaging (rs-fMRI) study investigating intra-network functional connectivity associated with guilt for OCD is not reported yet. Therefore, in the current study, we assessed the differences between intra-network functional connectivity of healthy control group and OCD group using independent component analysis (ICA) method. In addition, we also aimed to investigate the correlation between changed functional connectivity and guilt score in OCD. Total 86 participants, which consisted of 42 healthy control volunteers and 44 OCD patients, acquired rs-fMRI data using the 3T MRI. After preprocessing the fMRI data, a functional connectivity was used for group independent component analysis. The results showed that OCD patients had higher score in emotion state in beliefs and lower functional connectivity in fronto-parietal network (FPN) than control group. A decrease of functional connectivity in FPN was negatively correlated with feelings of guilt in OCD. Our results suggest excessive increase in guilt negatively affect to process emotional state and behavior or cognitive processing by influencing intrinsic brain activity.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.19-26
• /
• 2019

In this paper, the classification performance of learning algorithms is compared for TAB digit recognition. The TAB digits that are segmented from TAB musical notes contain TAB lines and musical symbols. The labeling method and non-linear filter are designed and applied to extract fret digits only. The shift operation of the 4 directions is applied to generate more data. The selected models are Bayesian classifier, support vector machine, prototype based learning, multi-layer perceptron, and convolutional neural network. The result shows that the mean accuracy of the Bayesian classifier is about 85.0% while that of the others reaches more than 99.0%. In addition, the convolutional neural network outperforms the others in terms of generalization and the step of the data preprocessing.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.525-531
• /
• 2019

Efforts to utilize human gestures to effectively implement a more natural and interactive interface between humans and computers have been ongoing in recent years. In this paper, we propose a new algorithm that accepts consecutive three-dimensional (3D) depth images, defines a hand model, and robustly extracts the human hand region based on six palm joints and 15 finger joints. Then, the 3D depth images are adaptively binarized to exclude non-interest areas, such as the background, and accurately extracts only the hand of the person, which is the area of interest. Experimental results show that the presented algorithm detects only the human hand region 2.4% more accurately than the existing method. The hand region extraction algorithm proposed in this paper is expected to be useful in various practical applications related to computer vision and image processing, such as gesture recognition, virtual reality implementation, 3D motion games, and sign recognition.

• The Korean Journal of Applied Statistics
• /
• v.32 no.2
• /
• pp.301-317
• /
• 2019

There has been significant research conducted on how to discover various insights through text data using statistical techniques. In this study we analyzed text data produced by the Korean National Police Agency to identify trends in the work by year and compare work characteristics among local authorities by identifying distinctive keywords in documents produced by each local authority. A preprocessing according to the characteristics of each data was conducted and the frequency of words for each document was calculated in order to draw a meaningful conclusion. The simple term frequency shown in the document is difficult to describe the characteristics of the keywords; therefore, the frequency for each term was newly calculated using the term frequency-inverse document frequency weights. The L2 norm normalization technique was used to compare the frequency of words. The analysis can be used as basic data that can be newly for future police work improvement policies and as a method to improve the efficiency of the police service that also help identify a demand for improvements in indoor work.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.5
• /
• pp.380-388
• /
• 2019

Jet engine modulation(JEM) signals are widely used for target recognition. These signals coming from a potentially hostile aircraft provide specific information about the jet engine. In order to obtain the number of blades, which is uniquely provided by the JEM signal, one must extract the spool rate, which is the rotation speed of the blades. In this paper, we propose an algorithm to extract the spool rate from a weak JEM signal. A criterion is developed to extract the spool rate from the JEM signal by analyzing the intensity of the JEM signal component. The weak signal is first subjected to a high-pass filtering-based process, which modifies it to facilitate spool rate extraction. We then apply a peak detection process and extract the spool rate. The technique is simpler than the existing CEMD or WD method, is accurate, and greatly reduces the time required.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.3-24
• /
• 2019

Techniques related to 360 VR service have been developed to improve the quality of the stitched image and video, where illumination compensation scheme is one of the important tools. Among the conventional illumination compensation algorithms, Gain-based compensation and Block Gain-based compensation algorithms have shown the outstanding performances in the process of making panorama picture. However, those are ineffective in the 360 VR service, because the disparity between illuminations of the multiple pictures in 360 VR is much more than that in making the panorama picture. In addition, the number of the pictures to be stitched in 360 VR system is more than that in the conventional panorama image system. Thus, we propose a preprocessing tool to enhance the illumination compensation algorithm so that the method reduces the degradation in the stitched picture of 360 VR systems. The proposed algorithm consists of 'color compensation' and 'illumination compensation'. The simulation results show that the proposed technique improve the conventional techniques without additional complexity.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.128-138
• /
• 2019

In this paper, we present fusion methods for two different lofargrams. Since the conventional method synthesizes the lofargrams using frequency spectrum, it has limited performance in fusion of tonal signals which have two-dimensional information of the time-frequency domain. Proposed algorithm uses a two-dimensional directional bilateral filter for preprocessing and fuses two lofargrams based on comparison of local anisotropy of the lofargrams. After noise is suppressed and tonals are sharpened, the local anisotropy can be used as a criterion to divide tonals and noise. The experiment results using simulated data and real data showed that the proposed algorithms result in similar or lower noise level of the fused lofargram than conventional algorithms and decrease tonal omission in fusion process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1310-1316
• /
• 2021

Recently, with the development of artificial intelligence and IoT technology, the importance of video processing such as object tracking, medical imaging, and object recognition is increasing. In particular, the noise reduction technology used in the preprocessing process demands the ability to effectively remove noise and maintain detailed features as the importance of system images increases. In this paper, we provide a modified weight filter based on pixel matching in an AWGN environment. The proposed algorithm uses a pixel matching method to maintain high-frequency components in which the pixel value of the image changes significantly, detects areas with highly relevant patterns in the peripheral area, and matches pixels required for output calculation. Classify the values. The final output is obtained by calculating the weight according to the similarity and spatial distance between the matching pixels with the center pixel in order to consider the edge component in the filtering process.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.10
• /
• pp.231-238
• /
• 2019

Analyzing next-generation genome sequencing data in a conventional way using single server may take several tens of hours depending on the data size. However, in order to cope with emergency situations where the results need to be known within a few hours, it is required to improve the performance of a single genome analysis. In this paper, we propose a parallelized method for pre-processing genome sequence data which can reduce the analysis time by utilizing the big data technology and the highperformance computing cluster which is connected to the high-speed network and shares the parallel file system. For the reliability of analytical data, we have chosen a strategy to parallelize the existing analytical tools and algorithms to the new environment. Parallelized processing, data distribution, and parallel merging techniques have been developed and performance improvements have been confirmed through experiments.