• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1439-1447
• /
• 2018

Palm image acquisition without contact has advantages in user convenience and hygienic issues, but such images generally display more image variations than those acquired employing a contact plate or pegs. Therefore, it is necessary to develop a palmprint identification method which is robust to affine variations. This study proposes a deep learning approach which can effectively identify contactless palmprints. In general, it is very difficult to collect enough volume of palmprint images for training a deep convolutional neural network(DCNN). So we adopted an approach to use a pretrained DCNN. We designed two new DCNNs based on the VGGNet. One combines the VGGNet with SVM. The other add a shallow network on the middle-level of the VGGNet. The experimental results with two public palmprint databases show that the proposed method performs well not only contact-based palmprints but also contactless palmprints.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1387-1395
• /
• 2018

Core algorithm of deep learning Convolutional Neural Network(CNN) shows better performance than other machine learning algorithms. However, if there is not sufficient data, CNN can not achieve satisfactory performance even if the classifier is excellent. In this situation, it has been proven that the use of transfer learning can have a great effect. In this paper, we apply two transition learning methods(freezing, retraining) to three CNN models(ResNet-50, Inception-V3, DenseNet-121) and compare and analyze how the classification performance of CNN changes according to the methods. As a result of statistical significance test using various evaluation indicators, ResNet-50, Inception-V3, and DenseNet-121 differed by 1.18 times, 1.09 times, and 1.17 times, respectively. Based on this, we concluded that the retraining method may be more effective than the freezing method in case of transition learning in image classification problem.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1447-1453
• /
• 2020

In this paper, we propose a method for no-reference quality assessment of sports videos using 3D shearlet transform and deep residual neural networks. In the proposed method, 3D shearlet transform-based spatiotemporal features are extracted from the overlapped video blocks and applied to logistic regression concatenated with a deep residual neural network based on a conditional video block-wise constraint to learn the spatiotemporal correlation and predict the quality score. Our evaluation reveals that the proposed method predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.186-198
• /
• 2021

Security control using surveillance cameras is established when people observe all surveillance videos directly. However, this task is labor-intensive and it is difficult to detect all abnormal situations. In this paper, we propose a deep neural network model, called AT-Net, that automatically detects abnormal situations in the surveillance video, and introduces an automatic video surveillance system developed based on this network model. In particular, AT-Net alleviates the ambiguity of existing abnormal situation detection methods by mapping features representing relationships between people and objects in surveillance video to the new tensor structure based on sparse coding. Through experiments on actual surveillance videos, AT-Net achieved an F1-score of about 89%, and improved abnormal situation detection performance by more than 25% compared to existing methods.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1020-1025
• /
• 2021

Facial alignment is very important task for human life. And facial landmark detection is one of the instrumental methods in face alignment. We introduce the stacked hourglass networks with transposed convolutional layers for facial landmark detection. our method substitutes nearest neighbor upsampling for transposed convolutional layer. Our method returns better accuracy in facial landmark detection compared to stacked hourglass networks with nearest neighbor upsampling.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1068-1075
• /
• 2021

Wireless sensor network (WSN) can be usefully used in battlefields requiring rapid installation and operation by enabling surveillance and reconnaissance using small sensors in areas where any existing network infrastructure is not formed. As WSN uses battery, energy efficiency acts as a very important issue in network survivability. Layer-based routing protocols have been studied a lot in the aspect of energy efficiency. Many research selected LEACH and PEGASIS protocols as their comparison targets. This study examines the two protocols and LECEEP, a protocol designed by combining their advantages, and proposes a new protocol, A-LECEEP, which is more energy efficient than the others. The proposed protocol can increase energy efficiency compared to the existing ones by eliminating unnecessary transmissions with multiple chains configuration.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1122-1137
• /
• 2021

PM_2.5 concentration in Seoul could be predicted by deep neural network model. In this paper, the contribution of input factors to the model's prediction results is analyzed using the LRP(Layer-wise Relevance Propagation) technique. LRP analysis is performed by dividing the input data by time and PM concentration, respectively. As a result of the analysis by time, the contribution of the measurement factors is high in the forecast for the day, and those of the forecast factors are high in the forecast for the tomorrow and the day after tomorrow. In the case of the PM concentration analysis, the contribution of the weather factors is high in the low-concentration pattern, and that of the air quality factors is high in the high-concentration pattern. In addition, the date and the temperature factors contribute significantly regardless of time and concentration.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.121-126
• /
• 2022

The shortest path betweenness value of a node quantifies the amount of information passing through the node when all the pairs of nodes in the network exchange information in full capacity measured by the number of the shortest paths between the pairs assuming that the information travels in the shortest paths. It is calculated as the cumulative of the fractions of the number of shortest paths between the node pairs over how many of them actually pass through the node of interest. It's possible for a node to have zero or underrated betweenness value while sitting just next to the giant flow of information. These nodes may have a significant influence on the network when the normal flow of information is disrupted. We propose a betweenness centrality measure called collective betweenness that takes into account the surroundings of a node. We will compare our measure with other centrality metrics and show some applications of it.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.676-684
• /
• 2022

As realistic media are widespread in various image processing areas, image or video compression is one of the key technologies to enable real-time applications with limited network bandwidth. Generally, image or video compression cause the unnecessary compression artifacts, such as blocking artifacts and ringing effects. In this study, we propose a Deep Residual Channel-attention Network, so called DRCAN, which consists of an input layer, a feature extractor and an output layer. Experimental results showed that the proposed DRCAN can reduced the total memory size and the inference time by as low as 47% and 59%, respectively. In addition, DRCAN can achieve a better peak signal-to-noise ratio and structural similarity index measure for compressed images compared to the previous methods.

• Journal of Korea Multimedia Society
• /
• v.6 no.7
• /
• pp.1266-1276
• /
• 2003

Multimedia information containing voice and image is transmitted on Internet, which is ten times or hundred times larger than ordinary information. Analysis types for network management in this environment consist of a real time analysis, a basic analysis and an intensive analysis. The intensive analysis is useful for gathering the trend information of specific objects periodically for certain period in order to monitor network status. When SNMP is applied to collect the trend information of intensive analysis, it brings on the increase of network load, the delay of response time and the decrease of data collection accuracy since an agent responds to manager's every polling. In this paper, an efficient SNMP is proposed and implemented to add time variables in the existing SNMP PDU. It minimizes unnecessary traffic in the intensive analysis between manager and agent, and collects trend information more accurately. The results of experiments show that it has compatibility with the existing SNMP, decreases the amount of network traffic greatly and increases the accuracy of data collection.