• Journal of the Korea Convergence Society
• /
• v.11 no.9
• /
• pp.109-115
• /
• 2020

With the continuous development of automobile design industry, fastback design style has become the main popular trend of automobile appearance design, and it has an important impact on the future automobile appearance design. This study summarizes the basic rules and characteristics of the design style base don combing, analyzing and verifying the data of the fastback design style. It provides the necessary basic research for the better application of the fastback design style in the future automobile design. Firstly, through the literature research method to sort out and analyze the de finition, origin and history of fastback design style. Secondly, through the comparative study, the author compares and analyzes the characteristics, advantages and disadvantages of the fastback design style and the step back design style. Thirdly, through case analysis, it studies the classification and characteristics of fastback design style. Finally, this paper summarizes the influence of the fastback design style on the future automobile appearance design, and the specific design methods. Forecasts the development trend of fastback design style in the field of automobile exterior design in the future. Through this research, we sorted out the related historical development of fastback design and the characteristics and advantages of fastback design style (from the perspective of functionality, economy and aesthetics).The fastback design style has formed a more systematic research theory, which provides basic research materials for future fastback design research. In the next stage, this study will be further subdivided, focusing on the different design features of different automobile manufacturers which subdivide the fastback design style into different design features according to their own needs.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.35-45
• /
• 2022

Even in recent years, treatment of first-aid patients is still often delayed due to a shortage of medical resources in marginalized areas. Research on automating the analysis of medical data to solve the problems of inaccessibility for medical services and shortage of medical personnel is ongoing. Computer vision-based medical inspection automation requires a lot of cost in data collection and labeling for training purposes. These problems stand out in the works of classifying lesion that are rare, or pathological features and pathogenesis that are difficult to clearly define visually. Anomaly detection is attracting as a method that can significantly reduce the cost of data collection by adopting an unsupervised learning strategy. In this paper, we propose methods for detecting abnormal images on chest X-RAY images as follows based on existing anomaly detection techniques. (1) Normalize the brightness range of medical images resampled as optimal resolution. (2) Some feature vectors with high representative power are selected in set of patch features extracted as intermediate-level from lesion-free images. (3) Measure the difference from the feature vectors of lesion-free data selected based on the nearest neighbor search algorithm. The proposed system can simultaneously perform anomaly classification and localization for each image. In this paper, the anomaly detection performance of the proposed system for chest X-RAY images of PA projection is measured and presented by detailed conditions. We demonstrate effect of anomaly detection for medical images by showing 0.705 classification AUROC for random subset extracted from the PadChest dataset. The proposed system can be usefully used to improve the clinical diagnosis workflow of medical institutions, and can effectively support early diagnosis in medically poor area.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.33-42
• /
• 2022

In this paper, we proposed a deep learning model based on multi-scale dilated convolution feature fusion for the segmentation of black ice region in road image to send black ice warning to drivers in real time. In the proposed multi-scale dilated convolution feature fusion network, different dilated ratio convolutions are connected in parallel in the encoder blocks, and different dilated ratios are used in different resolution feature maps, and multi-layer feature information are fused together. The multi-scale dilated convolution feature fusion improves the performance by diversifying and expending the receptive field of the network and by preserving detailed space information and enhancing the effectiveness of diated convolutions. The performance of the proposed network model was gradually improved with the increase of the number of dilated convolution branch. The mIoU value of the proposed method is 96.46%, which was higher than the existing networks such as U-Net, FCN, PSPNet, ENet, LinkNet. The parameter was 1,858K, which was 6 times smaller than the existing LinkNet model. From the experimental results of Jetson Nano, the FPS of the proposed method was 3.63, which can realize segmentation of black ice field in real time.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.67-75
• /
• 2006

Facial expressions exhibit not only facial feature motions, but also subtle changes in illumination and appearance. Since it is difficult to generate realistic facial expressions by using only geometric deformations, detailed features such as textures should also be deformed to achieve more realistic expression. The existing methods such as the expression ratio image have drawbacks, in that detailed changes of complexion by lighting can not be generated properly. In this paper, we propose a nonlinear model for skin color change and a model-based synthesis method for facial expression that can apply realistic expression details under different lighting conditions. The proposed method is composed of the following three steps; automatic extraction of facial features using active appearance model and geometric deformation of expression using warping, generation of facial expression using a model for nonlinear skin color change, and synthesis of original face with generated expression using a blending ratio that is computed by the Euclidean distance transform. Experimental results show that the proposed method generate realistic facial expressions under various lighting conditions.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.49-66
• /
• 2015

The increase of social interest for the e-Learning industry leads to the increase of e-learning contents and the system providers which are targeted at private education companies and public institutions. As the e-Learning is used in various areas, the evaluation for evaluation criteria and suitability are needed to provide a high-quality service and reliability. Previous works suggested the evaluation criteria for quality certification, however, the technical evaluation criteria are not provided. In this paper, we suggest the technical evaluation criteria for quality certification of e-Learning contents and describe the detailed features. Through the proposed work, we can establish the technical evaluation criteria and suggest detailed evaluation items for them by providing examples. It is expected that the proposed study is able to be utilized in e-Learning industry, if the policy is reflected and notified according to the feedback of the results of the trial service.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.3
• /
• pp.152-163
• /
• 2009

This study identified characteristics of households in Seo Geumsa based on factors related to how well each household understood and agreed or disagreed with the Newtown project and the resettlement process that is required to establish the renewal promotion plan. To this end, the authors applied the unit of spatial analysis developed by Tong, segmented the land intended for large-scale development, and then developed a method for analyzing and comparing the segmented lands by certain characteristics. The results of the survey were analyzed in three stages: the characteristics of districts; the relationships between agreement and disagreement factors and differences among segmented districts. And, to assess districts with features that differed from the overall features of households in renewal districts, the authors developed a two-way stage division plan and conducted a cluster analysis. The authors analyzed districts with individual characteristics based on the household features developed by Tong, and then analyzed the features of household distribution in these districts along with spatial location.

• Korea Science and Art Forum
• /
• v.20
• /
• pp.409-419
• /
• 2015

Service Design Platform which has been developing under the sponsorship of the Ministry of Knowledge Economy is aimed at facilitating service design consultancy to carry out service design projects smoothly online. In the development process in order to verify and improve the usability of the platform, heuristic evaluations by usability experts along with usability test done by user participation are required. This study was conducted for the purpose of deriving appropriate evaluation areas and detailed evaluation indices prior to carrying out the heuristic evaluation. For the study, first, the concept of the service design platform was identified and the features of its component were analyzed. Second, based on literature study of standards which are related to usability evaluation indices, usability evaluation areas and indices were analyzed. Third, in order to establish and verify evaluation areas and indices which are appropriate for the evaluation, Delphi survey was conducted and its validity was verified. Through this study, evaluation indices with 4 evaluation areas and 45 detailed items were derived. Derived evaluation indices was made in the form of checklist and will be utilized for heuristic evaluation by usability experts.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.2
• /
• pp.110-125
• /
• 2010

We present a novel scheme for generating line drawings from 2D images, aiming to facilitate effective visual communication. In contrast to conventional edge detectors, our technique imitates the human line drawing process to generate lines effectively and intuitively. Our technique consists of three parts: line extraction, line rendering, and user guidance. In line extraction, we extract lines by estimating a likelihood function to effectively find the genuine shape boundaries. In line rendering, we consider the feature scale and the blurriness of lines with which the detail and the focus-level of lines are controlled. We also employ stroke textures to provide a variety of illustration styles. User guidance is allowed to modify the shapes and positions of lines interactively, where immediate response is provided by GPU implementation of most line extraction operations. Experimental results demonstrate that our technique generates various kinds of line drawings from 2D images enabled by the control over detail, focus, and style.

• Journal of Korean Elementary Science Education
• /
• v.26 no.1
• /
• pp.87-96
• /
• 2007

The purpose of this study was to examine the features of the standards of observation and measurement in foreign national science curriculums. For the purpose of this study, we analyzed the science standards of the USA (National Science Education Standards, the Science Standards of the State of California, Massachusetts, Colorado, Nebraska, Virginia and Florida), the United Kingdom (England), Singapore, Canada (the State of Alberta), Australia (the State of Victoria) and New Zealand. The results of the study indicated that foreign national science curriculums put an emphasis on accurate and systematical observation, usage of the five senses, usage of observation tools, and an understanding of observation. Regarding the 'measurement' factors, foreign national science curriculums emphasized systematic and accurate measurement. Measurement targets and tools were presented for each grade. The usage of appropriate units was also included in the foreign national curriculums which we examined.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.607-611
• /
• 2008

This paper proposes new video signature using spatio-temporal information for copy detection. The proposed video copy detection method is based on concentric circle partitioning method for each key frame. Firstly, key frames are extracted from whole video using temporal bilinear interpolation periodically and each frame is partitioned as a shape of concentric circle. For the partitioned sub-regions, 4 feature distributions of average intensity, its difference, symmetric difference and circular difference distributions are obtained by using the relation between the sub-regions. Finally these feature distributions are converted into binary signature by using simple hash function and merged together. For the proposed video signature, the similarity distance is calculated by simple Hamming distance so that its matching speed is very fast. From experiment results, the proposed method shows high detection success ratio of average 97.4% for various modifications. Therefore it is expected that the proposed method can be utilized for video copy detection widely.