• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.147-153
• /
• 2023

In recent times, an absence of effective crowd management has led to numerous stampede incidents in crowded places. A crucial component for enhancing on-site crowd management effectiveness is the utilization of crowd counting technology. Current approaches to analyzing congested scenes have evolved beyond simple crowd counting, which outputs the number of people in the targeted image to a density map. This development aligns with the demands of real-life applications, as the same number of people can exhibit vastly different crowd distributions. Therefore, solely counting the number of crowds is no longer sufficient. CSRNet stands out as one representative method within this advanced category of approaches. In this paper, we propose a crowd counting network which is adaptive to the change in the density of people in the scene, addressing the performance degradation issue observed in the existing CSRNet(Congested Scene Recognition Network) when there are changes in density. To overcome the weakness of the CSRNet, we introduce a system that takes input from the image's information and adjusts the output of CSRNet based on the features extracted from the image. This aims to improve the algorithm's adaptability to changes in density, supplementing the shortcomings identified in the original CSRNet.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2230-2252
• /
• 2024

Advances in deep learning technology have enabled the generation of more realistic deepfakes, which not only endanger individuals' identities but also exploit vulnerabilities in face recognition systems. The majority of existing deepfake detection methods have primarily focused on RGB-based analysis, offering unreliable performance in terms of detection accuracy and time. To address the issue, a grayscale-based deepfake detection method has recently been proposed. This method significantly reduces detection time while providing comparable accuracy to RGB-based methods. However, despite its significant effectiveness, the "key components" that directly affect the performance of grayscale-based deepfake detection have not been systematically analyzed. In this paper, we target three key components: RGB-to-grayscale conversion method, brightness level in grayscale, and resolution level in grayscale. To analyze their impacts on the performance of grayscale-based deepfake detection, we conducted comprehensive evaluations, including component-wise analysis and comparative analysis using real-world datasets. For each key component, we quantitatively analyzed its characteristics' performance and identified differences between them. Moreover, we successfully verified the effectiveness of an optimal combination of the key components by comparing it with existing deepfake detection methods.

• Cartoon and Animation Studies
• /
• s.35
• /
• pp.227-253
• /
• 2014

The purpose of this article is to prove the fun of cartoon has related in Reality. Ultimately, it will be occurred the expanding result in contact with reader's reality perception. I had pointed out this issue in introduction. Although Fun is our vital power, almost people recognize it as imagination result which is not related in Reality. As the result, we overlooked Fun is contacted in Reality recognition. Creation method of cartoon story emphasize "the Individual character" and "the original nature" also. As this result, it has limitation which neglect "Reality". In main subject, I explained the meaning of Fun and Reality in feeling Korea Cartoon. First, we looked around a theoretical background of fun. With take surveying for various fun characters in several category of cartoon. We can confirm that it was occurred the results contacting "Enlargement of actual recognition" commonly. Second, the main issue of Korea cartoon was "Reality" historically. But, described Reality in cartoon is different from true Reality. Therefore, cartoon is imagined Reality of writer. So he make a heros and make a fun putting a folk tail. Third, described Reality in Korea cartoons make a fun and reader's consensus which is from emotional reality. With limitation of writer's "Reality recognition", almost writers adapted to ideology of ruling classes. Forth, we surveyed Korean cartoons which described "true Reality". Newspaper cartoons during imperialism and Min-joong cartoon in 80' period and 2000th period life documentary cartoon, we participated three sector and surveyed each character. Especially, I am dealing with important inconsistency of true reality. As this result, My cartoon enlarge reader's true reality and make "Fun" of recognizing a true reality.

• Journal of Information Technology Services
• /
• v.8 no.3
• /
• pp.83-100
• /
• 2009

Even though the success of the information system (IS) protect becomes a critical issue to an enterprise and there has been a lot of research about finding critical success factors of IS projects, the scope management for the success of IS protect has received little attention in the literature. The purpose of this research is to investigate the effects of the project scope management activities defined by PMI (Project Management Institute) on the performance of the information system project. The focus of this paper is on the project supplier's point of view. This study shows the priority of the scope management activities during the IS Project. The results show the different results depending on the types of the project clients and the project scale. This research reveals that the scope verification is important for the project supplier from the project process view, and that the scope planning/definition is important for the protect client from the project result view. It also shows different results comparing to the conventional recognition about project success. The research results show that the positive relationships between the project scale and the importance of scope management activities, and between the familiarity of suppliers and clients and the importance of the scope management activities. Through this research, we expect that the importance of the scope management in a project will be considered as an important issue, and that this research will lead to various detailed research about this issue.

• Journal of Korea Trade
• /
• v.25 no.7
• /
• pp.108-121
• /
• 2021

Purpose - This paper studies whether the CISG is applicable to the arbitration agreement when the validity of the arbitration agreement becomes an issue. To make the study clear, it limits the cases assuming that the governing law of the main contract is the CISG and the arbitration agreement is inserted in the main contract as a clause. Also, this paper discusses only substantive and formal validity of the arbitration agreement because the CISG does not cover the questions of the parties' capacity and arbitrability of the dispute. Design/methodology - This paper is based on scholarly writings and cases focusing on the principle of party autonomy, formation of contract and the doctrine of separability to discuss characteristic of arbitration agreement. In analyzing the cases, it concentrates on the facts and reasonings that show how the relative regulations and rules are interpreted and applied. Findings - The findings of this paper are; regarding substantive validity of arbitration agreement, the courts and arbitral tribunals consider general principles of law for the contract and the governing law for the main contract. In relation to formal validity of arbitration agreement, the law at the seat of arbitration or the law of the enforcing country are considered as the governing law in preference to the CISG because of the recognition and enforcement issues. Originality/value - This paper attempts to find the correlation between the CISG and the arbitration agreement. It studies scholars' writing and cases which have meaningful implication on this issue. By doing so, it can provide contracting parties and practitioners with some practical guidelines about the governing law for the arbitration agreement. Furthermore, it can help them to reduce unpredictability that they may confront regarding this issue in the future.

• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.333-338
• /
• 2012

Human resource management is bringing the various changes with the IT technology. In particular, if HRM is non-scientific method such as group management, physical plant, working hours constraints, personal contacts, etc, the current enterprise human resources management(e-HRM) appeared in the individual dimension management, virtual workspace (for example: smart work center, home work, etc.), working time flexibility and elasticity, computer-based statistical data and the scientific method of analysis and management has been a big difference in the sense. Therefore, depending on changes in the environment, companies have introduced a variety of techniques as RFID card, fingerprint time & attendance systems in order to build more efficient and strategic human resource management system. In this paper, time and attendance, access control management system was developed using multi camera for 2D and 3D face recognition technology-based for efficient enterprise human resource management. We had an issue with existing 2D-style face-recognition technology for lighting and the attitude, and got more than 90% recognition rate against the poor readability. In addition, 3D face recognition has computational complexities, so we could improve hybrid video recognition and the speed using 3D and 2D in parallel.

• Journal of Internet Computing and Services
• /
• v.16 no.3
• /
• pp.21-32
• /
• 2015

Since spatio-temporal local features for video representation have become an important issue of modeless bottom-up approaches in action recognition, various methods for feature extraction and description have been proposed in many papers. In particular, BoF(bag of features) has been promised coherent recognition results. The most important part for BoF is how to represent dynamic information of actions in videos. Most of existing BoF methods consider the video as a spatio-temporal volume and describe neighboring 3D interest points as complex volumetric patches. To simplify these complex 3D methods, this paper proposes a novel method that builds BoF representation as a way to learn 2D interest points directly from video data. The basic idea of proposed method is to gather feature points not only from 2D xy spatial planes of traditional frames, but from the 2D time axis called spatio-temporal frame as well. Such spatial-temporal features are able to capture dynamic information from the action videos and are well-suited to recognize human actions without need of 3D extensions for the feature descriptors. The spatio-temporal BoF approach using SIFT and SURF feature descriptors obtains good recognition rates on a well-known actions recognition dataset. Compared with more sophisticated scheme of 3D based HoG/HoF descriptors, proposed method is easier to compute and simpler to understand.

• Journal of the HCI Society of Korea
• /
• v.6 no.1
• /
• pp.1-8
• /
• 2011

As virtual realty has become an issue of providing immersive services, in the area of virtual realty, it has been actively investigated to develop user interfaces for immersive interaction. In this paper, we propose a gesture recognition based immersive user interface by using an IR LED embedded helmet and data gloves in order to reflect the user's movements to the virtual reality environments effectively. The system recognizes the user's head movements by using the IR LED embedded helmet and IR signal transmitter, and the hand gestures with the data gathered from data gloves. In case of hand gestures recognition, it is difficult to recognize accurately with the general recognition model because there are various hand gestures since human hands consist of many articulations and users have different hand sizes and hand movements. In this paper, we applied the Mixture-of-Experts based gesture recognition for various hand gestures of multiple users accurately. The movement of the user's head is used to change the perspection in the virtual environment matching to the movement in the real world, and the gesture of the user's hand can be used as inputs in the virtual environment. A head mounted display (HMD) can be used with the proposed system to make the user absorbed in the virtual environment. In order to evaluate the usefulness of the proposed interface, we developed an interface for the virtual orchestra environment. The experiment verified that the user can use the system easily and intuituvely with being entertained.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.2
• /
• pp.67-76
• /
• 2012

In this study, we established objective appraisal standard by applying newly made appraisal standard to those areas equipped with the protection system targeted to the Mobility handicapped announced in this edition (issue 5, volume 9(Oct., 2010)) beyond simple evaluation related to protector satisfaction. Additionally, we achieved efficient budget execution by conducting the preliminary estimation assessment regarding those areas on which recognition devices should be newly deployed. Through the assessment of the system coordination, the maximum safety distance is proved to be 72.2m. On the basis of this result, we applied dangerous grade to the deployment of recognition devices considering both psychological and accidental risk. With this, we proposed valuation basis to enable us to do future business. Based on this assessment standard, the degree of risk is proved to decrease by 35.2% compared to before conducting the demonstration project in terms of evaluation of comprehensive risk regarding intended areas. Additionally, we confirmed the fact that the degree of risk can decrease by 33.1% totally after having recognition devices built according to the deployment standard within budget. Furthermore, comprehensive risk can decrease up to 94% compared to the level of the demonstration project even though we spend 21.9% less of the existing budget. Hence, we can say that the deployment method of recognition devices related to the degree of risk is applied efficiently in the near future in terms of controlling comprehensive risk and cutting down budget through this study.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.156-161
• /
• 2018

Recently, as the population rapidly increases, food shortages and waste are emerging serious problem. In order to solve this problem, various countries and enterprises are trying research and product development such as a study of consumers' purchasing patterns of food and a development of smart refrigerator using IoT technology. However, the smart refrigerators which currently sold have high price issue and another waste due to malfunction and breakage by complicated configurations. In this paper, we proposed a low-cost smart refrigerator system based on IoT for solving the problem and efficient management of ingredients. The system recognizes and registers ingredients through QR code, image recognition, and speech recognition, and can provide various services of the smart refrigerator. In order to improve an accuracy of image recognition, we used a model using a deep learning algorithm and proved that it is possible to register ingredients accurately.