• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.677-687
• /
• 2022

We propose a detection algorithm based on tree-structured convolutional neural networks (TsCNNs) that finds pornography, propaganda, or other inappropriate content on a social media network. The algorithm sequentially applies the typical convolutional neural network (CNN) algorithm in a tree-like structure to minimize classification errors in similar classes, and thus improves accuracy. We implemented the detection system and conducted experiments on a data set comprised of 6 ordinary classes and 11 inappropriate classes collected from the Korean military social network. Each model of the proposed algorithm was trained, and the performance was then evaluated according to the images and videos identified. Experimental results with 20,005 new images showed that the overall accuracy in image identification achieved a high-performance level of 99.51%, and the effectiveness of the algorithm reduced identification errors by the typical CNN algorithm by 64.87 %. By reducing false alarms in video identification from the domain, the TsCNNs achieved optimal performance of 98.11% when using 10 minutes frame-sampling intervals. This indicates that classification through proper sampling contributes to the reduction of computational burden and false alarms.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.207-210
• /
• 2007

As the Internet is prevalent in our life, harmful contents have been increasing on the Internet, which has become a very serious problem. Among them, pornographic video is harmful as poison to our children. To prevent such an event, there are many filtering systems which are based on the keyword based methods or image based methods. The main purpose of this paper is to devise a system that classifies the pornographic videos based on the audio information. We use Mel-Cepstrum Modulation Energy (MCME) which is modulation energy calculated on the time trajectory of the Mel-Frequency cepstral coefficients (MFCC) and MFCC as the feature vector and Gaussian Mixture Model (GMM) as the classifier. With the experiments, the proposed system classified the 97.5% of pornographic data and 99.5% of non-pornographic data. We expect the proposed method can be used as a component of the more accurate classification system which uses video information and audio information simultaneously.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.671-682
• /
• 2024

Violence can be committed anywhere, even in crowded places. It is hence necessary to monitor human activities for public safety. Surveillance cameras can monitor surrounding activities but require human assistance to continuously monitor every incident. Automatic violence detection is needed for early warning and fast response. However, such automation is still challenging because of low video resolution and blind spots. This paper uses ResNet50v2 and the gated recurrent unit (GRU) algorithm to detect violence in the Movies, Hockey, and Crowd video datasets. Spatial features were extracted from each frame sequence of the video using a pretrained model from ResNet50V2, which was then classified using the optimal trained model on the GRU architecture. The experimental results were then compared with wavelet feature extraction methods and classification models, such as the convolutional neural network and long short-term memory. The results show that the proposed combination of ResNet50V2 and GRU is robust and delivers the best performance in terms of accuracy, recall, precision, and F1-score. The use of ResNet50V2 for feature extraction can improve model performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.8
• /
• pp.3806-3825
• /
• 2016

This paper brings out a neoteric frame of reference for visual semantic based 3d video search and retrieval applications. Newfangled 3D retrieval application spotlight on shape analysis like object matching, classification and retrieval not only sticking up entirely with video retrieval. In this ambit, we delve into 3D-CBVR (Content Based Video Retrieval) concept for the first time. For this purpose we intent to hitch on BOVW and Mapreduce in 3D framework. Here, we tried to coalesce shape, color and texture for feature extraction. For this purpose, we have used combination of geometric & topological features for shape and 3D co-occurrence matrix for color and texture. After thriving extraction of local descriptors, TB-PCT (Threshold Based- Predictive Clustering Tree) algorithm is used to generate visual codebook. Further, matching is performed using soft weighting scheme with L₂ distance function. As a final step, retrieved results are ranked according to the Index value and produce results .In order to handle prodigious amount of data and Efficacious retrieval, we have incorporated HDFS in our Intellection. Using 3D video dataset, we fiture the performance of our proposed system which can pan out that the proposed work gives meticulous result and also reduce the time intricacy.

• Journal of the Korea Computer Industry Society
• /
• v.6 no.5
• /
• pp.767-774
• /
• 2005

In this paper, we propose an efficient coding method of digital hologram using standard compression tools for video images. At first, we convert fringe patterns into video data using a principle of CGH(Computer Generated Hologram), and then encode it. In this research, we propose a compression algorithm is made up of various method such as pre-processing for transform, local segmentation with global information of object image, frequency transform for coding, scanning to make fringe to video stream, classification of coefficients, and hybrid video coding. The proposed algorithm illustrated that it have better properties for reconstruction and compression rate than the previous methods.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.1
• /
• pp.136-146
• /
• 2013

Truck demand analysis based on TCS data has limitation in that TCS data can not provide truck O/D data for each type of truck vehicle. This study conducted video survey for classifying truck vehicle types. By using TCS data and vehicle ratio by region/cities type, truck O/D data on expressway were estimated. It was found that average travel distances of small truck, medium truck and large truck were 52km/veh, 56km/veh and 97km/veh, respectively by analysing truck O/D data estimated in this study. The reliability analysis showed that check points where error rate is lower than 30% comprise of 87.3%. It is considered that estimated O/D data by truck vehicle types would be useful for the analysis of truck demand of expressway.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.3
• /
• pp.145-153
• /
• 2009

Trajectory data are ubiquitous in the real world. Recent progress on satellite, sensor, RFID, video, and wireless technologies has made it possible to systematically track object movements and collect huge amounts of trajectory data. Accordingly, there is an ever-increasing interest in performing data analysis over trajectory data. In this paper, we develop a data mining tool for massive trajectory data. This mining tool supports three operations, clustering, classification, and outlier detection, which are the most widely used ones. Trajectory clustering discovers common movement patterns, trajectory classification predicts the class labels of moving objects based on their trajectories, and trajectory outlier detection finds trajectories that are grossly different from or inconsistent with the remaining set of trajectories. The primary advantage of the mining tool is to take advantage of the information of partial trajectories in the process of data mining. The effectiveness of the mining tool is shown using various real trajectory data sets. We believe that we have provided practical software for trajectory data mining which can be used in many real applications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1183-1189
• /
• 2021

There have been recently an increasing number of people working out at home. However, many of them do not have face-to-face guidance from experts, so they cannot effectively correct their wrong pose. This may lead to strain and injury to those doing home training. To tackle this problem, this paper proposes a video data-based pose classification and correction system for home training. The proposed system classifies poses using the multi-layer perceptron and pose estimation model, and corrects poses based on joint angels estimated. A voting algorithm that considers the results of successive frames is applied to improve the performance of the pose classification model. Multi-layer perceptron model for post classification shows the highest accuracy with 0.9. In addition, it is shown that the proposed voting algorithm improves the accuracy to 0.93.

• Journal of the Korean Institute of Oriental Medical Informatics
• /
• v.15 no.1
• /
• pp.1-10
• /
• 2009

In these days everyone search the information easily with the Internet as the rapid distribution and active usage of the Internet. The search engines were developed specially to accuracy of information retrieval. User search the information more quickly and variously with them. The search portal system will be embossed with representation and basic services. The Internet user needs the result of text, image and video, knowledge search. The keyword based search is used generally for getting result of the information retrieval and another method is category based search. This paper investigates the classification of knowledge search structure for oriental medicine in market leader of search portal system by ranking web site. As a result, each classification system is unified and there is a possibility of getting up a many confusion to the user who approaches with classification systematic search method. This treatise proposed the improved oriental medicine classification system of internet information retrieval in knowledge search area. if the service provider amends about the classification system, there will be able to guarantee the compatibility of data. Also the proper access path of the knowledge which seeks is secured to user.

• Korean Journal of Applied Biomechanics
• /
• v.26 no.1
• /
• pp.51-69
• /
• 2016

Objective: The purpose of this study is to suggest new terminology for the ninety-five hand techniques based on the significance of their angular momentum, determined by analyzing each technique's influence or impact on the compartmentalized angular momentum of the trunk, upper arm, and forearm in the Taekwondo Poomsae. Method: An athlete who won the 2014 World Taekwondo Poomsae championship was selected and agreed to participate in the data collection phase of our investigation. The video data was collected using eight infrared cameras (Oqus 300, Qualysis, Sweden) and the Qualisys Track Manager software (Qualisys, Sweden). The angular momentum of each movement was then calculated using the Matlab R2009a software (The Mathworks, Inc., USA). Results: The classification of the ninety-five hand techniques in the Taekwondo Poomsae based on the significance of each segment's momentum is as follows. Makgi (blocking) is classified into fourteen categories, jireugi (punching) is classified into three categories, chigi (hitting) was classified into six categories, palgupchigi (elbow hitting) was classified into four categories, and jjireugi (thrusting) was classified two categories. Conclusion: This study offers a new approach, based on a biomechanical method, to the classification of the hand techniques that reflect kinesthetic motions in the Taekwondo Poomsae.