• Journal of Internet Computing and Services
• /
• v.19 no.4
• /
• pp.45-52
• /
• 2018

A single-image super-resolution is a process of restoring a high-resolution image from a low-resolution image. Recently, the super-resolution using the deep neural network has shown good results. In this paper, we propose a neural network structure that improves speed and performance over conventional neural network based super-resolution methods. To do this, we analyze the conventional neural network based super-resolution methods and propose solutions. The proposed method reduce the 5 stages of the conventional method to 3 stages. Then we have studied the optimal width and depth by experimenting on the width and depth of the network. Experimental results have shown that the proposed method improves the disadvantages of the conventional methods. The proposed neural network structure showed superior performance and speed than the conventional method.

• Journal of Fashion Business
• /
• v.24 no.1
• /
• pp.88-101
• /
• 2020

The music videos of BTS go beyond the limit of media promoting music and shows their meaning in various ways and complete the visual message of music through fashion style. BTS' fashion style in the music videos shows a change in symbolic representation of the genre of each album and song, of which gender images are changing aligned with the music messages of BTS. The purpose of this study was to derive gender images of fashion style in BTS music videos and to interpret their meaning based on Judith Butler's theory that performativity creates discourse through iterative process. It is conducted as a research method, an analytical study was conducted in parallel with literature studies and empirical case analysis. The scope of the study was limited to 301 costumes that appeared in 21 official music videos from debut single album '2Cool 4 Skool' released in 2013 to the mini album 'Map of the Soul: Persona' released in 2019. As a result of the analysis, the controversial fashion style, challenging fashion style, boyish fashion style, hybrid fashion style, the playful fashion style were revealed. The conclusion of studying the gender image of BTS, interpreted by this analysis using Judith Butler's theory, is as follows. The gender image of BTS is the traditional image that identifies with the dominant gender discourse, the resistive gender image that intentionally distances mainstream culture, the eclectic image parodying the gender of the opposing term, and the deconstructive image that transcends the dominant gender discourse.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.397-404
• /
• 2021

Product image location in search engine advertising plays an important role in consumer perception when the product is relatively low involved and has functional value. The purpose of this research is to investigate the interaction effects of product image location and product type on advertising effectiveness. Building on the literature of location effects, we show that for products for which heaviness is considered a positive attribute, product image placed on the right are preferred. To test hypotheses, a 2(product image location: left vs. right) × 2(product type: single vs. bundle) experiment is conducted and a total of 144 paricipants took part in the experiment. The results revealed that respondents show higher brand attitude and purchse intention toward a bundle product's advertising with product image place on the right. The results provide implications and suggestions for improving search engine advertising and marketing strategies.

• Journal of Fashion Business
• /
• v.23 no.4
• /
• pp.13-23
• /
• 2019

This study aims to understand the concept of pixel, the most important factor in constituting a digital image, draw the formative characteristics of pixelation image expressed through non-digital media, and develop fashion design reflecting the characteristics. As a research method, the literature review was conducted in the present study by involving domestic and foreign publications, related academic journals, and theses and dissertations on the pixel and pixelation image based on a qualitative research process. In addition, through an analysis of the cases that borrowed pixelation images in non-digital media like contemporary art and design, etc., an attempt was made to draw the formative characteristics of the pixelation image. Apparently, six fashion design looks are presented in the present study. The formative characteristics of the pixelation image include: first, the repeatability that repeats the minimum unit; second, the incompleteness of the shape appearing through the phenomenon of aliasing due to the characteristics of the pixel; and third, the combination that completes the shape through the combination of individual independent pixels. The results of the expression through reflecting them in fashion design are as follows: first, this study chose one small geometric formative element and presented repeatability by repetitively expressing that element in a textile pattern; second, for incompleteness, this study expressed an incomplete form, handling the edge part of the shape with the method of disentangling the strand; and third, the combination by completing a single look through overlapping of independent textiles and the combination of different independent individuals is expressed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.8
• /
• pp.896-902
• /
• 2019

In this paper, we proposed two methods to automatically generate color images similar to existing images using genetic algorithms. Experiments were performed on two different sizes($256{\times}256$, $512{\times}512$) of gray and color images using each of the proposed methods. Experimental results show that there are significant differences in the evolutionary performance of each technique in genetic modeling for image generation. In the results, evolving the whole image into sub-images evolves much more effective than modeling and evolving it into a single gene, and the generated images are much more sophisticated. Therefore, we could find that gene modeling, selection method, crossover method and mutation rate, should be carefully decided in order to generate an image similar to the existing image in the future, or to learn quickly and naturally to generate an image synthesized from different images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4290-4309
• /
• 2020

In recent years, advancements in machine learning capabilities have allowed it to see widespread adoption for tasks such as object detection, image classification, and anomaly detection. However, despite their promise, a limitation lies in the fact that a network's performance quality is based on the data which it receives. A well-trained network will still have poor performance if the subsequent data supplied to it contains artifacts, out of focus regions, or other visual distortions. Under normal circumstances, images of the same scene captured from differing points of focus, angles, or modalities must be separately analysed by the network, despite possibly containing overlapping information such as in the case of images of the same scene captured from different angles, or irrelevant information such as images captured from infrared sensors which can capture thermal information well but not topographical details. This factor can potentially add significantly to the computational time and resources required to utilize the network without providing any additional benefit. In this study, we plan to explore using image fusion techniques to assemble multiple images of the same scene into a single image that retains the most salient key features of the individual source images while discarding overlapping or irrelevant data that does not provide any benefit to the network. Utilizing this image fusion step before inputting a dataset into the network, the number of images would be significantly reduced with the potential to improve the classification performance accuracy by enhancing images while discarding irrelevant and overlapping regions.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1537-1549
• /
• 2020

The ground sample distance of KOMPSAT-3 is 0.7 m for panchromatic band, 2.8 m for multi-spectral band, and the swath width of KOMPSAT-3 is 16 km. Therefore, an image of an area wider than the swath width (16 km) cannot be acquired with a single scanning. Thus, after scanning multiple areas in units of swath width, the acquired images should be made into one image. At this time, the necessary algorithm is called image mosaicking or image stitching, and is used for cartography. Mosaic algorithm generally consists of the following 4 steps: (1) Feature extraction and matching, (2) Radiometric balancing, (3) Seamline estimation, and (4) Image blending. In this paper, we have studied an effective seamline estimation method for satellite images. As a result, we can estimate the seamline more accurately than the existing method, and the heterogeneity of the mosaiced images was minimized.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1136-1141
• /
• 2022

Researches of face recognition on masked faces have been increasingly important due to the COVID-19 pandemic. To realize a stable and practical recognition performance, large amount of facial image data should be acquired for the purpose of training. However, it is difficult for the researchers to obtain masked face images for each human subject. This paper proposes a novel method to synthesize a face image and a virtual mask pattern. In this method, a pair of masked face image and unmasked face image, that are from a single human subject, is fed into a convolutional autoencoder as training data. This allows learning the geometric relationship between face and mask. In the inference step, for a unseen face image, the learned convolutional autoencoder generates a synthetic face image with a mask pattern. The proposed method is able to rapidly generate realistic masked face images. Also, it could be practical when compared to methods which rely on facial feature point detection.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.90-99
• /
• 2023

In this paper, we propose a super resolution network for raw sensor image which data size is lower comparatively to RGB image. But the actual capabilities of raw image super resolution depends on color correction because its absent of camera post processing that leads to unintended result having different white balance, saturation, etc. Thus, we introduce novel color corrector attention network by adopting the idea of precedent raw super resolution research, and tune to the our faced problem from data specification. The result is not superior to former researches but shows decent output on certain performance matrix. In the same time, we encounter new challenging problem of unexpected shadowing artifact around image objects that cause performance declination despite its good result overall. This problem remains a task to be solved in the future research.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.494-500
• /
• 2023

Image processing is currently used in various fields. Among them, autonomous vehicles, medical image processing, and robot control require fast image processing response speeds. To fulfill this requirement, hardware design for real-time processing is being actively researched. In addition to the size of the input image, the hardware processing speed is affected by the size of the inactive video periods that separate lines and frames in the image. In this paper, we design three different scaler structures based on the type of line memories, which is closely related to the inactive video periods. The structures are designed in hardware using the Verilog standard language, and synthesized into logic circuits in a field programmable gate array environment using Xilinx Vivado 2023.1. The synthesized results are used for frame rate analysis while comparing standard image sizes that can be processed in real time.