• Journal of the FoodService Safety
• /
• v.4 no.1
• /
• pp.35-41
• /
• 2023

This study was based on the results of the study of 'Cheonyeon and Chunghyun Taste Alley Pilgrimage- Introducing Hidden Restaurants in Our Town', which was adopted as a project to revitalize urban regeneration as part of the Cheonyeon and Chunghyun Urban Regeneration New Deal project. This study was conducted in total of two stages, as a first step, the commercial district of Seodaemun Station was analyzed by analyzing the hashtag (#) mentioned along with the "Seodamun Station Restaurant" on Instagram from 2015 to 2020. As a result of the analysis, it was found to be an office commercial district related to "office workers", and it was found to be a commercial district with the characteristics of "small but certain happiness" where you can find hidden restaurants in front of your house. Based on the characteristics of these commercial districts, five stores utilizing the characteristics of the region were selected and cooking classes were conducted for students of Kyonggi University, who are local residents. The purpose of this study was to revitalize the aging Seoul city and contribute to the formation of positive relationships between local residents and merchants through cooking classes. In addition, the process was produced as digital media content and used as local promotional materials.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.6
• /
• pp.45-52
• /
• 2023

Recently, as the importance of walking in daily life has been emphasized, projects to guarantee walking rights and create a pedestrian environment are being promoted throughout the region. In previous studies, a pedestrian environment assessment was conducted using Jeonju-si road images, and an image comparison pair data set was constructed. However, data sets expressed in numbers have difficulty in generalizing the judgment criteria of pedestrian environment assessors or visually identifying the pedestrian environment preferred by pedestrians. Therefore, this study proposes a method to interpret the results of the pedestrian environment assessment through data visualization by building a web application. According to the semantic segmentation result of analyzing the walking environment components that affect pedestrian environment assessors, it was confirmed that pedestrians did not prefer environments with a lot of "earth" and "grass," and preferred environments with "signboards" and "sidewalks." The proposed study is expected to identify and analyze the results randomly selected by participants in the future pedestrian environment evaluation, and believed that more improved accuracy can be obtained by pre-processing the data purification process.

• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.293-300
• /
• 2008

This paper takes a bottom-up attention module into consideration for digital image watermarking. A bottom-up attention module is employed to obtain the region of interest, and watermark information is embedded into the obtained region. Previous studies in digital image watermarking have been focused on the signal processing techniques, especially in waveform coding spreading watermarks over the entire target image. However, we notice that the third party's visual attention is usually concentrated on a few regions in an image but not on all of them. These regions are easy to be the target of attacks. If watermark information is inserted into these regions from the beginning, it can be detected with high correlation. Various kinds of images are tested, and the results showed good quality.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.12
• /
• pp.547-552
• /
• 2014

As social multimedia sites are getting popular such as Flickr and Facebook, the amount of image information has been increasing very fast. So there have been many studies for accurate social image retrieval. Some of them were web image classification using semantic relations of image tags and BoVW(Bag of Visual Words). In this paper, we propose a method to detect salient region in images using GBVS(Graph Based Visual Saliency) model which can eliminate less important region like a background. First, We construct BoVW based on SIFT algorithm from the database of the preliminary retrieved images with semantically related tags. Second, detect salient region in test images using GBVS model. The result of image classification showed higher accuracy than the previous research. Therefore we expect that our method can classify a variety of images more accurately.

• 대한공업교육학회지
• /
• v.35 no.2
• /
• pp.25-42
• /
• 2010

This research aims to understand how students of technical high schools view 'engineering' as well as to identify the main elements that contribute to the perception on 'engineering.' The research targets are 695 senior students of technical high schools nationwide. The researcher developed the measuring tool for the experiment by referencing the adjective value criteria utilized in the semantic difference method developed by Osgood (1957). There were a grand total of 30 criteria following the preliminary studies. The results of the research are as follows. Firstly, the average value of the overall perception of technical high school students on 'engineering' is 4.27 points. This value just exceeds the standard (4 points). Secondly, when examining the general tendency it can be noticed that there is a sense of stigma that although 'engineering' is significant and valuable it is a field that is overly difficult, complex and even dangerous. Thirdly, 6 main elements that influence the perception on 'engineering' were extracted as results of the factor analysis. The first element is practicality; the second element is emotions; the third element is aesthetics; the fourth is simplicity; the fifth is responsibility; and finally the sixth element is assertiveness. Fourthly, when comparing the average values of the perception on 'engineering' by region, it was seen that there existed a difference on the perception towards 'engineering' based on differing regions.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.2
• /
• pp.111-124
• /
• 2011

The apartment' share of the housing has steadily increased and property assets have been valued in importance as the one of asset value. Information retrieval system using internet is particularly active in the real estate market. However, user satisfaction on real estate information system is not very high, and there is a lack of research on real estate retrieval to increasing efficiency until now. This study presents a new knowledge information system developed to consider region-related factor and individual-related factor in the real estate market. In addition it enables a real estate knowledge system to search various preferential requirements for buyers such as school district, living convenience, easy maintenance as well as price. We made a survey of the search condition preference of experts on 30 real estate agents and then analyzed the result using AHP methodology. Furthermore, this research is to build apartment ontology using semantic web technologies to standardize various terminologies of apartment information and to show how it can be used to help buyers find apartments of the interest. After designing architecture of a real estate knowledge information system, this system is applied to the Busan real estate market to estimate the solutions of retrieval through Multi-Attribute Decision Making(MADM). Based on the results of the analysis, we endowed the buyer and expert's selected factors with weights in the system. Evaluation results indicate that this new system is to raise not only the value satisfaction of user, but also make it possible to effectively search and analyze the real estate through entropy analysis of MADM. This new system is to raise not only the value satisfaction of buyer's real estate, but also make it possible to effectively search and analyze the related real estate, consequently saving the searching cost of the buyers.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.70-77
• /
• 2008

This paper proposes a new text candidate region detection method that uses genetic algorithm based on information of the segmented regions. In image segmentation, a classification of the pixels at each color channel and a reclassification of the region-unit for reducing inhomogeneous clusters are performed. EWFCM(Entropy-based Weighted C-Means) algorithm to classify the pixels at each color channel is an improved FCM algorithm added with spatial information, and therefore it removes the meaningless regions like noise. A region-based reclassification based on a similarity between each segmented region of the most inhomogeneous cluster and the other clusters reduces the inhomogeneous clusters more efficiently than pixel- and cluster-based reclassifications. And detecting text candidate regions is performed by genetic algorithm based on energy and variance of the directional edge components, the number, and a size of the segmented regions. The region information-based detection method can singles out semantic text candidate regions more accurately than pixel-based detection method and the detection results will be more useful in recognizing the text regions hereafter. Experiments showed the results of the segmentation and the detection. And it confirmed that the proposed method was superior to the existing methods.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.18 no.4
• /
• pp.101-115
• /
• 1991

A study on the method of evaluation the urban amenity structure in Pusan city was established. Finally a survey sites out of 41 regions were selected on the basis of questionnaires : Taejong-dae and Haeun-dae as a seascape, Pumosa and Daesin-park as a mountain, Daechong-park and Seongjigok-park as a mixed, and Chungryulsa, Yongdoosan-park and U. N. Cemetry as a urban type. The abstracted results of amenity elements were revealed as natural environments including convex type as beach, reservoir, valley and mountain, and plant elements including woods and flower beds which raised amenity. The elements of social surroundings including children's playing, the aged's rest, and elements of structures including historic and memorial structures and high buildings. Amenity element made up of each space by region were abstracted from the Semantic Differential method. According to the factor analysis on the ground SD scale values, Kaiser's measure of sampling adequacy for 24 variables is 08602 and very high. Four factors including pleasantness, healthiness, convenience and safety showed 54.42 percent for total variance. By means of multiple regression, the model was as follows : Y=1.6636+0.3684X4+0.1955X11+0.1614X15-0.1688X23+0.1468X24. Therefore, Y:amenity, X4:beautiful-ugly, X11:clean-dirty, X15:creative-imitative, X23:cozy-dreary, X24:free-restrained. All variables in the model were significant at 0.001 level. According to the results of regression on satisfaction, the variables of satisfaction affecting amenity are the size of green space, the condition of management and the harmony with the surroundings. I think the considerating on the above could improve amenity of each region and further Pusan city.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.151-158
• /
• 2022

The Cardiac Gated Blood Pool (GBP) scintigram, a nuclear medicine imaging, calculates the left ventricular Ejection Fraction (EF) by segmenting the left ventricle from the heart. However, in order to accurately segment the substructure of the heart, specialized knowledge of cardiac anatomy is required, and depending on the expert's processing, there may be a problem in which the left ventricular EF is calculated differently. In this study, using the DeepLabV3 architecture, GBP images were trained on 93 training data with a ResNet-50 backbone. Afterwards, the trained model was applied to 23 separate test sets of GBP to evaluate the reproducibility of the region of interest and left ventricular EF. Pixel accuracy, dice coefficient, and IoU for the region of interest were 99.32±0.20, 94.65±1.45, 89.89±2.62(%) at the diastolic phase, and 99.26±0.34, 90.16±4.19, and 82.33±6.69(%) at the systolic phase, respectively. Left ventricular EF was calculated to be an average of 60.37±7.32% in the ROI set by humans and 58.68±7.22% in the ROI set by the deep learning segmentation model. (p<0.05) The automated segmentation method using deep learning presented in this study similarly predicts the average human-set ROI and left ventricular EF when a random GBP image is an input. If the automatic segmentation method is developed and applied to the functional examination method that needs to set ROI in the field of cardiac scintigram in nuclear medicine in the future, it is expected to greatly contribute to improving the efficiency and accuracy of processing and analysis by nuclear medicine specialists.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.855-870
• /
• 2020

Windows are key components of building facades. Detecting windows, crucial to 3D semantic reconstruction and scene parsing, is a challenging task in computer vision. Early methods try to solve window detection by using hand-crafted features and traditional classifiers. However, these methods are unable to handle the diversity of window instances in real scenes and suffer from heavy computational costs. Recently, convolutional neural networks based object detection algorithms attract much attention due to their good performances. Unfortunately, directly training them for challenging window detection cannot achieve satisfying results. In this paper, we propose an approach for window detection. It involves an improved Faster R-CNN architecture for window detection, featuring in a window region proposal network, an RoI feature fusion and a context enhancement module. Besides, a post optimization process is designed by the regular distribution of windows to refine detection results obtained by the improved deep architecture. Furthermore, we present a newly collected dataset which is the largest one for window detection in real street scenes to date. Experimental results on both existing datasets and the new dataset show that the proposed method has outstanding performance.