• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.457-464
• /
• 2021

The advent of the big data era has enabled the rapid development of deep learning that learns rules by itself from data. In particular, the performance of CNN algorithms has reached the level of self-adjusting the source data itself. However, the existing image processing method only deals with the image data itself, and does not sufficiently consider the heterogeneous environment in which the image is generated. Images generated in a heterogeneous environment may have the same information, but their features may be expressed differently depending on the photographing environment. This means that not only the different environmental information of each image but also the same information are represented by different features, which may degrade the performance of the image analysis model. Therefore, in this paper, we propose a method to improve the performance of the image color constancy model based on Adversarial Learning that uses image data generated in a heterogeneous environment simultaneously. Specifically, the proposed methodology operates with the interaction of the 'Domain Discriminator' that predicts the environment in which the image was taken and the 'Illumination Estimator' that predicts the lighting value. As a result of conducting an experiment on 7,022 images taken in heterogeneous environments to evaluate the performance of the proposed methodology, the proposed methodology showed superior performance in terms of Angular Error compared to the existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.594-596
• /
• 2022

This paper relates to a system for pre-processing high-definition images acquired through a camera mounted on an unmanned aerial vehicle(UAV) and transmitting them to a server through a mobile communication network. In the case of the existing UAV system for image acquisition service, the acquired image was stored in the external storage device of the camera mounted on the UAV, and the image was checked by directly moving the storage device after the flight was completed. In the case of this method, there is a limitation in that it is impossible to check whether image acquisition or pre-processing is properly performed before directly checking image data through an external storage device. In addition, since the data is stored only in an external storage device, there is a disadvantage that data sharing is cumbersome. In this paper, to solve the above problems, we propose a system that can remotely check images in real time. Furthermore, we propose a system and method capable of performing pre-processing such as geo-tagging and transmission through a mobile communication network in addition to image acquisition through shooting in an UAV.

• Journal of Korea Game Society
• /
• v.21 no.6
• /
• pp.75-86
• /
• 2021

Brand image refers to how customers, stakeholders and the market see and recognize the brand. A positive brand image leads to continuous purchases, but a negative brand image is directly linked to consumers' buying behavior, such as stopping purchases, so from the corporate perspective, it needs to be quickly and accurately identified. Currently, methods of investigating brand images include surveys and SNS surveys, which have limited number of samples and are time-consuming and costly. Therefore, in this study, we are going to conduct an emotional analysis of text data on social media by utilizing the machine learning based KoBERT model, and then suggest how to use it for game corporate brand image analysis and verify its performance. The result has proved some degree of usability showing the same ranking within five brands when compared with the BRI Korea's brand reputation ranking.

• Science of Emotion and Sensibility
• /
• v.11 no.4
• /
• pp.653-667
• /
• 2008

Despite of the importance of design, relatively little research has been conducted on consumers' behavioral responses to product design and especially, the empirical studies which are related to consumers' psychological responses to product design. Understanding of the relationship between the response to product design and brand image or brand equity is limited. This research investigated the effect of the design image which can be formed by the response to product design on brand image and equity in two kinds of product types (utilitarian and symbolic product). The result shows that the product design image has a strong effect on the brand image in both products. Design image of the product influences brand equity in the symbolic product. However, there was no significant effect of the product design image on brand equity in the utilitarian product. In addition, the research found that brand image has a strong effect on brand equity in both products.

• Journal of the Korean Society for information Management
• /
• v.29 no.4
• /
• pp.273-294
• /
• 2012

Images have been substantially searched and used due to not only the advanced internet and digital technologies but the characteristics of a younger generation. The purpose of this study aims to discuss the ways on expanding the access points to images by analyzing the needs of users in context of everyday life. In order to achieve the purpose of this study, 105 questions of image seeking in NAVER, which is one of social Q&A services in Korea, were analyzed. For the analysis, a two-dimensional framework with image uses and image attributes were utilized. The findings of this study demonstrate that considerable use purposes on data oriented pole, such as information processing, information dissemination and learning are identified. On the other hand, image attributes from the needs of image show that non-visual aspects including contextual attributes are recognized substantially in addition to the traditional semantic attributes.

• Archives of design research
• /
• v.14 no.1
• /
• pp.83-92
• /
• 2001

Apartment exterior colors have an important effect on the images of cities and communities. Therefore planning the apartment exterior colors have to proceed systematically and synthetically based on the theoretical background. In this research, the first step is to investigate the apartment exterior colors which is located around the Han River in Seoul. And the second step is to survey the images of the S construction company in Korea. The results of this study are as follows: 1. The trends of apartment exterior colors on the basis of 1996 are showed differently. Bright and high saturation colors are more used after 1996, and divers color combinations are more tried than before. 2. Common customer Has positive images about the S construction company such as young, fresh, confidence and smart. Also they want the other images such as comfort, ease and coziness. 3. Two color combination palettes were proposed in this research. The first color combination is blue and yellow which is based on the dear and smart images. And the second color combination is green and orange which is based on the comfort and ease images.

• Journal of Internet Computing and Services
• /
• v.17 no.3
• /
• pp.45-54
• /
• 2016

Medical images are an effective means to identity medical abnormalities.. Patients typically have medical images taken at different clinics during lifetime, and they often wish to have second interpretation on medical images showing substantial diseases. At present, since personal medical images are distributed to multiple clinics, there is a bit discomfort that patients directly bring their images by hands to get the second interpretation from another physician. With these two motivations, we design a cloud service for archiving medical images and interpreting medical images by physicians. We present the design and implementation of the service, and show its practical value as low-cost personal healthcare service. By using the service, patients can retrieve and review their medical images anytime and have a convenience of acquiring second opinions on their medical images at low-cost without visiting a clinic.

• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.385-392
• /
• 2017

The aim of this study was to examine the image for dental hygienists and influence factor in academic high school students. A self-reported questionnaire was surveyed by 211 high school student in G area. the data were analyzed for frequency analysis, average, standard deviation, independent t-test, one-way ANOVA, pearson's correlation coefficient by using SPSS 21.0 program. In case of general high-school students, occupational and business images were higher significantly. The social images were higher significantly in case of having introduction or explanation for dental hygienists. In addition, the self-esteem showed significant differences depending on the oral condition. There were positive correlations among the occupational, business, personal, social images of dental hygienists and self-esteem. Multiple regression analysis showed that highest in occupational images.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.10
• /
• pp.489-496
• /
• 2016

Thousands of pathological images are produced daily per hospital and they are stored and managed by a pathology information system (PIS). Since image edge detection is one of fundamental analysis tools for pathological images, many researches are targeted to improve accuracy and performance of image edge detection algorithm of HIS. In this paper, we propose a novel image edge detection method. It is based on Canny algorithm with adaptive threshold configuration. It also uses a dividing ruler to configure the two threshold instead of whole image to improve the detection ratio of ruler itself. To verify the effectiveness of our proposed method, we conducted empirical experiments with real pathological images(randomly selected image group, image group that was unable to detect by conventional methods, and added noise image group). The results shows that our proposed method outperforms and better detects compare to the conventional method.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.121-126
• /
• 2006

In this paper, we propose an approach to increase the power of clustering Web images by using high-level semantic features from text information relevant to Web images as well as low-level visual features of image itself. These high-level text features can be obtained from image URLs and file names, page titles, hyperlinks, and surrounding text. As a clustering engine, self-organizing map (SOM) proposed by Kohonen is used. In the SOM-based clustering using high-level text features and low-level visual features, the 200 images from 10 categories are divided in some suitable clusters effectively. For the evaluation of clustering powers, we propose simple but novel measures indicating the degrees of scattering images from the same category, and degrees of accumulation of the same category images. From the experiment results, we find that the high-level text features are more useful in SOM-based Web image clustering.