• 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.

• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.161-176
• /
• 2022

There has been active research in image classification using deep learning convolutional neural network (CNN) models. ImageNet large-scale visual recognition challenge (ILSVRC) (2010-2017) was one of the most important competitions that boosted the development of efficient deep learning algorithms. This paper introduces and compares six monumental models that achieved high prediction accuracy in ILSVRC. First, we provide a review of the models to illustrate their unique structure and characteristics of the models. We then compare those models under a unified framework. For this reason, additional devices that are not crucial to the structure are excluded. Four popular data sets with different characteristics are then considered to measure the prediction accuracy. By investigating the characteristics of the data sets and the models being compared, we provide some insight into the architectural features of the models.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.372-380
• /
• 2022

This study proposes a distributed parallel processing system, called the Fast Analysis System for remote sensing daTa(FAST), for large-scale satellite image processing and analysis. FAST is a system that designs jobs in vertices and sequences, and distributes and processes them simultaneously. FAST manages data based on the Hadoop Distributed File System, controls entire jobs based on Apache Spark, and performs tasks in parallel in multiple slave nodes based on a docker container design. FAST enables the high-performance processing of progressively accumulated large-volume satellite images. Because the unit task is performed based on Docker, it is possible to reuse existing source codes for designing and implementing unit tasks. Additionally, the system is robust against software/hardware faults. To prove the capability of the proposed system, we performed an experiment to generate the original satellite images as ortho-images, which is a pre-processing step for all image analyses. In the experiment, when FAST was configured with eight slave nodes, it was found that the processing of a satellite image took less than 30 sec. Through these results, we proved the suitability and practical applicability of the FAST design.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1126-1134
• /
• 2017

A variety of medical service applications in the field of the Internet of Things (IoT) are being studied. Segmentation is important to identify meaningful regions in images and is also required in 3D images. Previous methods have been based on gray value and shape. The Visible Korean dataset consists of serially sectioned high-resolution color images. Unlike computed tomography or magnetic resonance images, automatic segmentation of color images is difficult because detecting an object's boundaries in colored images is very difficult compared to grayscale images. Therefore, skilled anatomists usually segment color images manually or semi-automatically. We present an out-of-core 3D segmentation method for large-scale image datasets. Our method can segment significant regions in the coronal and sagittal planes, as well as the axial plane, to produce a 3D image. Our system verifies the result interactively with a multi-planar reconstruction view and a 3D view. Our system can be used to train unskilled anatomists and medical students. It is also possible for a skilled anatomist to segment an image remotely since it is difficult to transfer such large amounts of data.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.6
• /
• pp.67-74
• /
• 2006

In this paper, a tiled display system is developed to get a high-resolution image in visualization of large-scale structural analysis data with low-resolution display devices and low-cost cluster computer system. Concerning the hardware system, some of the crucial points are investigated, and a new beam-projector positioner is designed and manufactured to resolve the keystone phenomena which result in distorted image. In the development of tiled display software, Qt and OpenGL are utilized for GUI and rendering, respectively. To obtain the entire tiled image, LAM-MPI is utilized to synchronize the several sub-images produced from each cluster computer node.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.2 no.1
• /
• pp.21-35
• /
• 2000

The purpose of this study was to evaluate the preference of image for modern application of Korean traditional patterns. A survey was conducted using the randomly selected 292 undergraduate women students of Taegu city. The degree of interest and preference in Korean traditional style or something like that had measured by 5 scale method. And then they had two groups which are interest/non-interest group, and preference/non-preference group in Korean traditional style. Also, preference of Korean traditional patterns was measured by 5 scale method. The image of Korean traditional patterns consisted of semantic differential scales. Analysis was by frequency, percentage, and mean. For difference of groups analysis was by t-test. The results were as follows:1. For the survey, 53.8% showed the interest and 40.4% did the preference for the traditional patterns. There was the positive correlation(0.782) between the degree of the interest and preference. 2. Among twenty traditional patterns, the patterns of plants and nature were very preferred, but the patterns of geometrical things was not preferred. 3. For the nature pattern, the image seemed to be elegant and feminine(womanly). For the plant pattern, the image seemed to be feminine, neat, weak, light and mild. For the animal pattern, the image seemed to be heavy, gorgeous, deluxe, virile(manly), strong and active. Last, for the geometrical pattern, the image seemed to be elegant, deluxe, rigid and strong. 4. Between the interest／non­interest groups, there was the significant difference in pattern of cloud, mountain, lotus flower, plum blossoms, orchid, dragon, chinese phoenix and bogy. Especially, for the orchid pattern, the preference difference between these groups was large. 5. For the plant pattern, the image difference between these groups was very large as the elegant-rustic image. Especially, the interest group evaluated as the elegant image. 6. Between the preference／non­preference groups, there was the strongly significant difference in the preference for the orchid pattern. 7. For the geometrical pattern, the image difference between these groups was very large as the mild­cold image. Especially, the preference groups evaluated as the cold image.

• Imaging Science in Dentistry
• /
• v.50 no.4
• /
• pp.331-337
• /
• 2020

Purpose: As cone-beam computed tomography (CBCT) has become the most widely used 3-dimensional (3D) imaging modality in the dental field, storage space and costs for large-capacity data have become an important issue. Therefore, if 3D data can be stored at a clinically acceptable compression rate, the burden in terms of storage space and cost can be reduced and data can be managed more efficiently. In this study, a deep learning network for super-resolution was tested to restore compressed virtual CBCT images. Materials and Methods: Virtual CBCT image data were created with a publicly available online dataset (CQ500) of multidetector computed tomography images using CBCT reconstruction software (TIGRE). A very deep super-resolution (VDSR) network was trained to restore high-resolution virtual CBCT images from the low-resolution virtual CBCT images. Results: The images reconstructed by VDSR showed better image quality than bicubic interpolation in restored images at various scale ratios. The highest scale ratio with clinically acceptable reconstruction accuracy using VDSR was 2.1. Conclusion: VDSR showed promising restoration accuracy in this study. In the future, it will be necessary to experiment with new deep learning algorithms and large-scale data for clinical application of this technology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3942-3961
• /
• 2019

Recently, the models of deep super-resolution networks can successfully learn the non-linear mapping from the low-resolution inputs to high-resolution outputs. However, for large scaling factors, this approach has difficulties in learning the relation of low-resolution to high-resolution images, which lead to the poor restoration. In this paper, we propose Stage Generative Adversarial Networks (Stage-GAN) with semantic maps for image super-resolution (SR) in large scaling factors. We decompose the task of image super-resolution into a novel semantic map based reconstruction and refinement process. In the initial stage, the semantic maps based on the given low-resolution images can be generated by Stage-0 GAN. In the next stage, the generated semantic maps from Stage-0 and corresponding low-resolution images can be used to yield high-resolution images by Stage-1 GAN. In order to remove the reconstruction artifacts and blurs for high-resolution images, Stage-2 GAN based post-processing module is proposed in the last stage, which can reconstruct high-resolution images with photo-realistic details. Extensive experiments and comparisons with other SR methods demonstrate that our proposed method can restore photo-realistic images with visual improvements. For scale factor ${\times}8$, our method performs favorably against other methods in terms of gradients similarity.

• Korean Journal of Poultry Science
• /
• v.26 no.1
• /
• pp.35-42
• /
• 1999

According to the importance(production ratio) of special brand eggs, poultry farma can be classified into four types(Types I to IV). A close relation can be observed between these types and farm scale. Special brand eggs used to be the speciality of small-scale, suburban poultry farms. Recently, however, the production of these eggs has been adopted by medium and large farms, too, and is increasing throughout Japan. In particular, small-scale farms specializing in these eggs have attained a high profit and take a characteristic management from as opposed to large-scale poultry farming that adopts the \"small profit and quick returns\" strategy. Because of this, the meaning of special brand egg production to farm management differs according to farm scale. For small poultry farmers, it means securing a high profitability and for medium and large producers, improving the corporate image or meeting the needs for assortment of retailers.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.10
• /
• pp.1548-1558
• /
• 2008

The goal of this study was to investigate the impacts of service quality, product quality, and perceived price on store loyalty of the clothes shops at a large-scale discount store. The subjects were 357 female adults living in Suncheon City, Jeollanam Province. The questionnaires were conveniently sampled from June 1 to 30, 2006. The collected data were factor and reliability analyzed using the SPSS program. And Regression was used to verified the relationships between the constructs. Among the five hypotheses set in the research model, total four were selected through empirical analysis and the rest one were rejected. The empirical results showed the following managerial implications. First, consumer' perceived service quality has a positive relationship with store image and store loyalty. Second, product quality has a positive relationship with store image. Third, store image has positively related with store loyalty. Fourth, perceived price has not significantly related with store loyalty. Finally, store image in large-scale discount store is 'sales people', 'VMD/atmosphere', and 'assortment' on forming the store image. Especially, 'assortment', 'oust and friendship', and 'symbol' have significantly related with store loyalty.