• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.5
• /
• pp.697-704
• /
• 2018

Since the face in image content corresponds to individual information that can distinguish a specific person from other people, it is important to accurately detect faces not hidden in an image. In this paper, we propose a method to accurately detect a face from input images using a deep learning algorithm, which is one of the machine learning methods. In the proposed method, image input via the red-green-blue (RGB) color model is first changed to the luminance-chroma: blue-chroma: red-chroma ($YC_bC_r$) color model; then, other regions are removed using the learned skin color model, and only the skin regions are segmented. A CNN model-based deep learning algorithm is then applied to robustly detect only the face region from the input image. Experimental results show that the proposed method more efficiently segments facial regions from input images. The proposed face area-detection method is expected to be useful in practical applications related to multimedia and shape recognition.

• Journal of KIISE:Information Networking
• /
• v.36 no.2
• /
• pp.118-129
• /
• 2009

The ISO 18000-7 Active RFID standard, a single channel system operating in the 433Mhz, faces technical difficulties in supporting some recently introduced application demands because of its low transmission rates and radio interference between readers. We propose a new multi-channel active RFID system operating in the 2.4Ghz. The special feature of the proposed system is that a reader makes use of multiple interfaces to improve its performance like a multi-core processor. However if only a small part of interfaces are actually used, the performance improvement would not meet the expectation. To overcome this problem, a new multi-channel multi-interface active RFID protocol, which balances communication loads among all available interfaces, is necessary. 3 protocols, named as "Aggregated", "LP-Combined", "AP-Balanced", are proposed. Through simulation, we compare them for various conditions by changing number of tags, number of interfaces, tag data size. AP-Balanced shows the best performance and its performance increases almost linearly as the number of interface increases, which meets our expectation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.7
• /
• pp.655-661
• /
• 2017

It is a very important task to extract character regions contained in various input color images, because characters can provide significant information representing the content of an image. In this paper, we propose a new method for extracting character regions from various input images using MCT features and an AdaBoost algorithm. Using geometric features, the method extracts actual character regions by filtering out non-character regions from among candidate regions. Experimental results show that the suggested algorithm accurately extracts character regions from input images. We expect the suggested algorithm will be useful in multimedia and image processing-related applications, such as store signboard detection and car license plate recognition.

• Journal of Advanced Navigation Technology
• /
• v.6 no.2
• /
• pp.104-112
• /
• 2002

Nowadays, many countries are interested in using CPS far navigation system of aircrafts, because it has technical and economic benefits. For the CPS based navigation system, the most important thing is reliability of the system. GPS navigation solution is very accurate. But when some faults are raised in the CPS navigation system of an aircraft, if they cannot be detected and alerts are not generated for pilots, the aircraft cannot be safe. So, I implemented an DGPS integrity monitoring system that detects faults of measurements and exclude the fault measurement from the satellite constellation used for calculating a navigation solution. This paper introduces 'the Least Square Residual Method' used to detect faults of measurements and the implemented real time integrity monitoring system using DGPS. To test the system, I operated the system under many different conditions. And from analysis of the data recorded, I could conclude that when the number of visible satellites was enough to detect faults, the system could detect the faults of measurements perfectly, isolate and exclude the fault measurement well. But for more reliable system, the measurement errors must be estimated more accurately and integrations of CPS and other instruments must be developed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.11
• /
• pp.6856-6862
• /
• 2014

Web usage mining is a method to extract meaningful patterns based on the web users' log data. Most existing patterns of web usage mining, however, do not consider the users' diverse inclination but create general models. Web users' keywords can have a variety of meanings regarding their tendency and background knowledge. This study evaluated the extraction web-user's pattern after collecting and analyzing the web usage information on the users' keywords of interest. Web-user's pattern can supply a web page network with various inclination information based on the users' keywords of interest. In addition, the Web-user's pattern can be used to recommend the most appropriate web pages and the suggested method of this experiment was confirmed to be useful.

• The Journal of the Korea Contents Association
• /
• v.10 no.10
• /
• pp.152-160
• /
• 2010

Modern comics find their roots in caricatures, which have a basic element of comics as a combination of wrings and drawings. In three East Asian countries, new media, comics have been developed by joining modern arts and cartoons which is a news form of western comics. As modern comics have evolved according to situations of the three countries, they expand from the satire on the system, foreign invasions, and internal corruption to the enlightenment of the people. However, the criticism on the system lead to the oppression, and the imperialism in East Asian countries enforce the agitation, war engagement, propaganda of the colonialism on the comics. Current East Asian comics have been occupying the largest part in the world comics, and have their roots in the modern comics. So it is meaningful to investigate the characteristic of modern East Asian comics.

• The Journal of the Korea Contents Association
• /
• v.14 no.7
• /
• pp.169-177
• /
• 2014

Recently, this government is implementing the "eradication of four social evils" policy to root out social evils which includes sexual violence, school violence, domestic violence and substandard food. In retrospect, these social evils are the crimes that have sprung from rapid social changes in Korea. These main four crimes not only badly affect certain victims but also spread their viciousness to broad population. Moreover, the prevention of the occurrence of the crime and the problem solving as an individual unit are hardly possible. Due to their critical effects and continuity, governmental safety policy enforcement is achieving higher support. As an alliance with the calling from the public for happier and safer life, this paper especially focus on regulating substandard food issue, according to the idea that food safety is an essential prerequisite for the healthy and happy life of the people. Through the reviewing, definition of the substandard food will be cleared and specified substandard food crimes will be introduced as well. And the paper will also pose questions in order to propose improved legal measures against the existing regulations, such as newly adding additional penalty article to food sanitation law.

• The Journal of the Korea Contents Association
• /
• v.14 no.7
• /
• pp.541-549
• /
• 2014

This study aims to propose measures to support students' English literacy development in collaboration with public libraries in the community. The literature review shows that students can improve their English literacy skills by not only reading authentic books, but also participating in English literacy programs at the public library. The analysis of the gathered data reveals that public libraries provide extensive programs customized to students' needs. It is also shown that reading programs at the public libraries play an important role in improving students' literacy skills. With the analysis of the literacy programs at various libraries nationwide or abroad, we can understand the importance of the English literacy programs. Especially English Literacy programs in public libraries can be more effective to improve students' English literacy skills. It is suggested that we need to support children's literacy development in collaboration with public libraries in the community.

• Journal of Satellite, Information and Communications
• /
• v.10 no.2
• /
• pp.54-59
• /
• 2015

UHD(Ultra High Definition) Broadcasting is the focus of attention recent days. However, current broadcasting system faces with difficulty of bandwidth, encoding and so on. To solve this problem, MMT was suggested as the one of solutions. MMT is designed to be based on IP network and it has characteristics that can deliver multimedia through many networks at the same time. UHD Media service can be available with the current broadcasting system that divides media data into hierarchical data based on MMT. To provide this service, information about heterogeneous network should be delivered and signalling should be given to perceive it. For UHD media data service, the information about data from heterogeneous networks should be transported for providing presentation information and service for the receiver models. The present MMT signalling has not much information about heterogeneous services with hierarchical media data. In this paper, we suggest the design of service signaling structure based on MMT for UHD broadcasting systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.4
• /
• pp.964-969
• /
• 2008

This paper proposes a HMM-based recognition method using DMSVQ(Dynamic Multi-Section Vector Quantization) codebook by DMS(Dynamic Multi-Section) model and fuzzy concept, as a study for speaker- independent speech recognition. In this proposed recognition method, training data are divided into several dynamic section and multi-observation sequences which are given proper probabilities by fuzzy rule according to order of short distance from DMSVQ codebook per each section are obtained. Thereafter, the HMM using this multi-observation sequences is generated, and in case of recognition, a word that has the most highest probability is selected as a recognized word. Other experiments to compare with the results of recognition experiments using proposed method are implemented as a data by the various conventional recognition methods under the equivalent environment. Through the experiment results, it is proved that the proposed method in this study is superior to the conventional recognition methods.