• Management & Information Systems Review
• /
• v.28 no.4
• /
• pp.175-197
• /
• 2009

Numerous researches related to internet shopping malls have been researched by numerous researchers. Such as, establishing criteria to evaluate service quality of electronic commerce, identifying factors affecting successful internet shopping mall operation, and examining relationships among the factors in electronic commerce based shopping mall needed to be focused on. However, most researches that have been undertaken only consider the service quality model or basic functional dimension. In accordance with this indispensability, the integrated structural relationship among variables, which are potentially inherent in customer's perception and affect personnel royalty on internet shopping mall needs to be acknowledged. The purpose of this study is to examine which factors should be able to facilitate performance of internet shopping mall. Based on the relevant literature, it has been empirically analyzed how corporate image, system quality, service quality and delivery quality affect customer satisfaction as well as customer royalty. The research's problem is that it was tested with data collected from 212 respondents. This study developed and empirically analyzed a model representing the relationship by using the Structural Equation Model. The major findings of this study are, firstly, that the higher corporate image is positively affecting the system quality and delivery quality. Secondly, the higher delivery quality is positively affecting the service quality. Thirdly, the higher service quality is positively affecting the customer satisfaction. Finally, the higher customer satisfaction is affecting the customer royalty.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.69-72
• /
• 2024

모델 역추론 공격은 공격 대상 네트워크를 훈련하기 위해 사용되는 훈련 데이터셋 중 개인 데이터셋을 공개 데이터셋을 사용하여 개인 훈련 데이터셋을 복원하는 것이다. 모델 역추론 방법 중 적대적 생성 신경망을 사용하여 모델 역추론 공격을 하는 과거의 논문들은 딥러닝 모델 전체의 역추론에만 초점을 맞추기 때문에, 이를 통해 얻은 원본 이미지의 개인 데이터 정보는 제한적이다. 따라서, 본 연구는 대상 모델의 중간 출력을 사용하여 개인 데이터에 대한 더 품질 높은 정보를 얻는데 초점을 맞춘다. 본 논문에서는 적대적 생성 신경망 모델이 원본 이미지를 생성하기 위해 사용되는 계층별 역추론 공격 방법을 소개한다. MNIST 데이터셋으로 훈련된 적대적 생성 신경망 모델을 사용하여, 원본 이미지가 대상 모델의 계층을 통과하면서 얻은 중간 계층의 출력 데이터를 기반으로 원본 이미지를 재구성하고자 한다. GMI 의 공격 방식을 참고하여 공격 모델의 손실 함수를 구성한다. 손실 함수는 사전 손실 및 정체성 손실항을 포함하며, 역전파를 통해서 원본 이미지와 가장 유사하게 복원할 수 있는 표현 벡터 Z 를 찾는다. 원본 이미지와 공격 이미지 사이의 유사성을 분류 라벨의 정확도, SSIM, PSNR 값이라는 세 가지 지표를 사용하여 평가한다. 공격이 이루어지는 계층에서 복원한 이미지와 원본 이미지를 세 가지 지표를 가지고 평가한다. 실험 결과, 공격 이미지가 원본 이미지의 대상 분류 라벨을 정확하게 가지며 원본 이미지의 필체를 유사하게 복원하였음을 보여준다. 평가 지표 또한 원본 이미지와 유사하다는 것을 나타낸다.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.280-287
• /
• 2023

Deep learning advancements can solve computer vision problems, but large-scale datasets are necessary for high accuracy. In this paper, we propose an image generation technique using object bounding boxes and image edge components. The object bounding boxes are extracted from the images through object detection, and image edge components are used as input values for the image generation model to create new image data. As results of experiments, the images generated by the proposed method demonstrated similar image quality to the source images in the image quality assessment, and also exhibited good performance during the deep learning training process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.153-155
• /
• 2022

Recently, we are using robots and drones to collect images. However, as the robot or drone is shaken by external influences, pre-processing technology to register images is required. Therefore, in this paper, we use autonomous robots, drones dataset and improve the quality of shaken image data through the Deblur deep learning model. We confirmed through the experimental results that the shaken images were registered and evaluated the model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.129-132
• /
• 2022

Super-resolution is the process of converting a low-quality image into a high-quality image. This study was conducted using ESPCN. In a super-resolution deep neural network, different quality images can be output even when receiving the same input data according to the activation function that determines the weight when passing through each node. Therefore, the purpose of this study is to find the most suitable activation function for super-resolution by applying the activation functions ReLU, ELU, and Swish and compare the quality of the output image for the same input images. The CelebaA Dataset was used as the dataset. Images were cut into a square during the pre-processing process then the image quality was lowered. The degraded image was used as the input image and the original image was used for evaluation. As a result, ELU and swish took a long time to train compared to ReLU, which is mainly used for machine learning but showed better performance.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.3
• /
• pp.925-934
• /
• 2018

The purpose of this study was to study the quality of service, student satisfaction, and university image of the university sports center as part of the university education service in order to find necessary marketing measures to secure university competitiveness. To this end, we used the convenience sampling method for sports centers of three universities in the Seoul metropolitan area. and analyzed the final 326 copies, excluding 24 questionnaires out of a total of 350 questionnaires. Using the SPSS 21.0 program, frequency analysis, exploratory factor analysis, correlation and multiple regression analysis were conducted. The results showed that the geographical, human and convenience factors of the university's sports center affect student satisfaction. Second, it was found that the facility and convenience factors of the university sports center affect the university image. Third, it was revealed that the university sports center's satisfaction with the quality of its service affected the university image.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.80-83
• /
• 2008

상업용 장비보다 저가인 스캐너를 이용하여 얻은 인쇄물의 이미지 정보를 이용하여 ISO13660과 본 연구에서 새로이 정의한 색상 품질 항목 기반으로 하는 정량적인 평가 방법을 제안하고 구현하였다. 상업용 장비에서 비교 가능한 항목들에 대한 유의성 평가를 수행한 결과 비교적 유사한 결과를 얻을 수 있었다.

• International Area Studies Review
• /
• v.15 no.1
• /
• pp.315-339
• /
• 2011

As the Korean economy grows, the brand value of Korean companies such as Samsung, LG and Hyundai Motor has been elevated greatly. Compared to the brand value of Korean companies, Korea's national image is very lowly ranked. In addition Korea's national brand is undervalued compared to economic volume. So, the purpose of this study is to find way to enhance the Korea's national brand in Japanese Market through brand credibility. The results as follows. First, this study find that brand credibility is consist of expertise and trustworthiness in Japanese market. Second Korea national image positive impact on brand credibility. Third, brand credibility positive impact on perceived quality and information cost saving. Finally, brand credibility negative impact on perceived risk. In conclusion, all hypothesis are significant. So these results are very useful to Korea government and Korean companies.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.342-353
• /
• 2020

The purpose of this study is to identify priority factors for improving service quality of cosmetic stores in drug stores(DRS) and department stores(DES) and to provide basic data for improving service quality of cosmetic stores by analyzing the service quality based on the Kano model and the Potential Customer Satisfaction Improvement (PCSI) Index. As a result, most items of quality factors of cosmetic stores in both stores were evaluated as attractive quality factors. As a result of PCSI Index comparison, the quality factors of 'Reliability', 'Responsiveness', and 'Empathy' items for DRS and 'Empathy' and 'Reliability' items for DES had higher priority for improvement. That is, if these factors are improved, there is a high potential to improve customer satisfaction. Through this study, practical implications were provided by identifying service quality factor classification and priorities for customer satisfaction improvement of DRS and DES. This is expected to contribute to the guidelines for improving customer satisfaction in the future.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.1
• /
• pp.23-30
• /
• 2022

Recently, there are various studies underway on the deep learning-used image matting methods. Even in the field of photogrammetry, a process of extracting information about relics from images photographed is essential to produce a high-quality realistic model. Such a process requires a great deal of time and manpower, so chroma-key has been used for extraction so far. This method is low in accuracy of sub-classification, however, it is difficult to apply the existing method to high-quality realistic models. Thus, this study attempted to remove background information from high-resolution relic images by using prior background information and trained learning data and evaluate both qualitative and quantitative results of the relic images extracted. As a result, this proposed method with FBA(manual trimap) showed quantitatively better results, and even in the qualitative evaluation, it was high in accuracy of classification around relics. Accordingly, this study confirmed the applicability of the proposed method in the indoor relic photography since it showed high accuracy and fast processing speed by acquiring prior background information when classifying high-resolution relic images.