• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.988-999
• /
• 2021

AOI (Automatic Optical Inspection) of PCB (Printed Circuit Board) is a very important step to guarantee the product performance. The process of registering components called teaching mode is first perform, and AOI is then carried out in a testing mode that checks defects, such as recognizing and comparing the component mounted on the PCB to the stored components. Since most of registration of the components on the PCB is done manually, it takes a lot of time and there are many problems caused by mistakes or misjudgement. In this paper, A components classifier is proposed using YOLO (You Only Look Once) v2's object detection model that can automatically register components in teaching modes to reduce dramatically time and mistakes. The network of YOLO is modified to classify small objects, and the number of anchor boxes was increased from 9 to 15 to classify various types and sizes. Experimental results show that the proposed method has a good performance with 99.86% accuracy.

• Journal of Platform Technology
• /
• v.11 no.5
• /
• pp.3-15
• /
• 2023

Requirements traceability link information is the basis for determining whether requirement change requested throughout the software development life cycle should be reflected in the system. Setting up complete requirements traceability links requires considerable effort. However, the commensurate benefits can be obtained in later development or further maintenance phases. For this reason, setting up and managing requirements traceability links in the software development phase are tasks that cause considerable resistance to developers. This study proposes a method for generating requirement traceability links in business applications. The key feature of the proposed method is that the traceability link from the requirements element, which is the basis of the corresponding element to the analysis element, is automatically established at the same time the elements of the analysis model are identified. This can be a way to reduce developer effort while increasing the efficiency of the traceability model. A case study on a Course Registration System demonstrates the feasibility of applying the proposed requirements traceability management method to actual software development.

• Journal of Digital Contents Society
• /
• v.11 no.3
• /
• pp.407-416
• /
• 2010

As the mobile internet rapidly progress and mobile terminals are activated, business entities which want to operate mobile web contents and individuals who want to use it increase. 6005plus.com as "I wish the mobile world" which is mobile UCC(User Created Contents) ponpy/invitation service web site(www.6005plus.com) was constructed. In 6005plus.com web site, which users could easily produce mobile contents and establish mobile web service servers as well, in order for mobile service users to create mobile invitation or ponpy and use it. But the service 6005plus.com advocates is that users can attach ponpy and invitations to the MMS/SMS Call back URL, which needs resolution since it has several inactivated problems. In this paper, we allow users who registered 6005plus.com can create mobile card, invitation, and personal ponpy with registration, so that apply automatic generation technique for users to experience ponpy/invitation service into MMS/SMS Call back URL which 6005plus.com advocates through registration. We also designed my page to which users can send their contents easily, conveniently and by one-stop.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.1
• /
• pp.18-23
• /
• 2008

In this paper, we propose the input image selection-method to improve the reconstructed high-resolution (HR) image quality. To obtain ideal super-resolution (SR) reconstruction image, all input images are well-registered. However, the registration is not ideal in practice. Due to this reason, the selection of input images with low registration error (RE) is more important than the number of input images in order to obtain good quality of a HR image. The suitability of a candidate input image can be determined by using statistical and restricted registration properties. Therefore, we propose the proper candidate input Low Resolution(LR) image selection-method as a pre-processing for the SR reconstruction in automatic manner. In video sequences, all input images in specified region are allowed to use SR reconstruction as low-resolution input image and/or the reference image. The candidacy of an input LR image is decided by the threshold value and this threshold is calculated by using the maximum motion compensation error (MMCE) of the reference image. If the motion compensation error (MCE) of LR input image is in the range of 0 < MCE < MMCE then this LR input image is selected for SR reconstruction, else then LR input image are neglected. The optimal reference LR (ORLR) image is decided by comparing the number of the selected LR input (SLRI) images with each reference LR input (RLRI) image. Finally, we generate a HR image by using optimal reference LR image and selected LR images and by using the Hardie's interpolation method. This proposed algorithm is expected to improve the quality of SR without any user intervention.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.807-812
• /
• 2020

In order to prevent the national wide spread of the COVID-19 virus, the government enforces to use an electronic access registration system for public facilities to effectively track and manage the spread. Initially, there was a lot of hassle to write a directory, but recently a system for creating an electronic access list using QR codes, what is called KI-Pass, is mainly used. However, the procedure for generating a QR code is somewhat cumbersome. In this paper, we propose a new electronic access registration system that does not require QR code. This system effectively controls the suspicious visitor by using a mask wearing discriminator which has been implemented using deep learning technology, and a non-contact thermometer package. In addition, by linking the beacon, a short-range wireless communication technology, and the visitor's smartphone application, basic information of the facility visitor is automatically registered to KDCA through the server. On the other hand, the user access information registered in the server is encrypted and stored, and is automatically destroyed after up to 4 weeks. This system is expected to be very effective in preventing the spread of other new infectious diseases as well as responding to the coronavirus which is recording a high spread worldwide.

• Journal of Internet Computing and Services
• /
• v.18 no.2
• /
• pp.1-11
• /
• 2017

There are two kinds of wireless network access to a certain place by using smart devices - 1) open (anonymous) - access and 2) user-authorized access. The open-access is a non-authorization connection method which does not need to require Smart device's user authorized information. It means open-access use only user's SSID (Service Set Identifier) information to access the wireless AP devices following public wireless network standard. This access mechanism is not suitable to use all of public wireless networks because users have to get all wireless network information around them. As a result, huge data for smart devices should be one of the most critical overload problems for them. Secondly, the user-authorized access method uses wireless network information (SSID and password) chosen by the users. So, the users have to remember and use the network access information data manually whenever accessing the network. Like open-access, this access method also has the operational and inconvenient problem for the users - manually inputting access information whenever connecting to the network. To overcome this problem in both schemes, we propose two improved wireless network access methods: 1) the implementation of automatic AP connection mechanism using user-authorization and iBeacon messages, and 2) SSID registration form for public wireless networks.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.137-145
• /
• 2014

This paper suggests an LDA-based long distance face recognition algorithm for intelligent surveillance system. The existing face recognition algorithm using single distance face image as training images caused a problem that face recognition rate is decreased with increasing distance. The face recognition algorithm using face images by actual distance as training images showed good performance. However, this also causes user inconvenience as it requires the user to move one to five meters in person to acquire face images for initial user registration. In this paper, proposed method is used for training images by using single distance face image to automatically create face images by various distances. The test result showed that the proposed face recognition technique generated better performance by average 16.3% in short distance and 18.0% in long distance than the technique using the existing single distance face image as training. When it was compared with the technique that used face images by distance as training, the performance fell 4.3% on average at a close distance and remained the same at a long distance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.3A
• /
• pp.250-258
• /
• 2011

In this paper we propose a load balancing scheme for heterogeneous multiple AS's (Application Server) in IMS (IP Multimedia Subsystem) based network. In IMS network, to perform load balancing among multiple ASs with different registration pattern, different weight value should be set for each AS. In previous systems, there exists an inconvenience that the weight value should be set manually by the operator after monitoring the result. In this paper we propose a method to calculate optimal weight in automatic manner and to perform load balancing simultaneously. We also propose a simplified algorithm to reduce calculation in specific situation and present a way to apply our proposed scheme in adaptive manner according to the situation. Through simulation result, we verify that our proposing scheme outperforms previous schemes in load balancing and adjusts well to the change of the system in automatic manner with fast convergence.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.1
• /
• pp.33-42
• /
• 2018

The purpose of this study is to suggest the shortcomings and the direction of the web accessibility evaluation studies by analyzing the research trends on web accessibility evaluation in Korea. For this aim, a total of 59 theses presented in the registered academic journal and the candidate of registration academic journals from January 2000 to March 2017 were selected. The selected dissertations have been analyzed based on the evaluators, the evaluation targets, the evaluation methods, and the evaluation results with regard to web accessibility. As a result of the analysis, the highest rate in the evaluator aspect was 'independent evaluation (66 percent)' and the highest percentage in the evaluation target aspect was 'web site (83 percent)'. When it came to the evaluation methods, automatic evaluation and the mixture of automatic evaluation and manual evaluation had a similar percentage. Lastly, only two papers showed that web accessibility did not have any problems. This study is meaningful in the sense that it suggested a desirable direction for the web accessibility studies in Korea and web accessibility evaluation studies in the situation when the meta studies which analyzed research trends are insufficient.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.3C
• /
• pp.233-240
• /
• 2012

Unlike traditional factory environment, in an industrial factory network applied wireless sensor network technologies, all procedures of discovery, identification and verification of devices should be performed in an automatic fashion. To address these challenges, we design a management system using the device registry server that we propose in this paper. In the phase of device discovery, the proposed system utilizes properties of routing protocol running in factories. Also, in the phase of identification and verification, the system uses unique and general information of a device stored within the device registration server. Such a way allows management system to reduce implementation complexity and to easily manage devices in a factory applied with a wireless network consisting of heterogeneous devices.