• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.411-427
• /
• 2022

Digging historical and cultural information from seals in ancient books is of great significance. However, ancient Chinese seal samples are scarce and carving methods are diverse, and traditional digital image processing methods based on greyscale have difficulty achieving superior segmentation and recognition performance. Recently, some deep learning algorithms have been proposed to address this problem; however, current neural networks are difficult to train owing to the lack of datasets. To solve the afore-mentioned problems, we proposed an SEL-RefineMask which combines selector of feature pyramid network (SEL-FPN) with RefineMask to segment and recognize seals. We designed an SEL-FPN to intelligently select a specific layer which represents different scales in the FPN and reduces the number of anchor frames. We performed experiments on some instance segmentation networks as the baseline method, and the top-1 segmentation result of 64.93% is 5.73% higher than that of humans. The top-1 result of the SEL-RefineMask network reached 67.96% which surpassed the baseline results. After segmentation, a vision transformer was used to recognize the segmentation output, and the accuracy reached 91%. Furthermore, a dataset of seals in ancient Chinese books (SACB) for segmentation and small seal font (SSF) for recognition were established which are publicly available on the website.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1777-1783
• /
• 2021

The use of drones is gradually increasing for the efficient maintenance of large-scale renewable energy power generation complexes. For a long time, photovoltaic panels have been photographed with drones to manage panel loss and contamination. Various approaches using artificial intelligence are being tried for efficient maintenance of large-scale photovoltaic complexes. Recently, semantic segmentation-based application techniques have been developed to solve the image classification problem. In this paper, we propose a classification model using semantic segmentation to determine the presence or absence of failures such as arcs, disconnections, and cracks in solar panel images obtained using a drone equipped with a thermal imaging camera. In addition, an efficient classification model was implemented by tuning several factors such as data size and type and loss function customization in U-Net, which shows robust classification performance even with a small dataset.

• Journal of Fashion Business
• /
• v.25 no.6
• /
• pp.102-118
• /
• 2021

The purpose of this study was to derive the characteristics of fashion that appeared in the daily life of bourgeois women in Paris in the late 19th-century, and to examine the attitudes women showed toward fashion in the modernized city of Paris. The research method was a literature study and a visual data analysis study targeting fashion of bourgeois women from 1860s to 1900s out of Mary Cassatt's 155 works and Berthe Morisot's 147 works from Wikiart's digital images. The characteristics and attitudes showed in fashion in terms of women's painter's work, women's daily life, and women's space are as follows. First, while the subject matter of their works was restricted to the house, fashion was described with the sensual colors, elegance, and sophistication anticipated of a woman's nature. The represented attitude toward women and fashion includes advice for pursuing the dignity of maternal love and women's intellectual life, as well as an attempt to reflect a current point of view on the woman image. Second, the daily life of bourgeois women was childcare, needlework, reading, and grooming. They valued socialization and entertainment as well as intimacy and education with children, so they wore different clothes depending on the situation. This suggested that it was necessary to dress appropriately both at home and when going out. Third, despite the fact that the public space for women was limited, they dressed elegantly in a variety of trends when they went out. This was fashion worn only for appearance.

• Korean Journal of Remote Sensing
• /
• v.39 no.1
• /
• pp.65-76
• /
• 2023

The Gamma Portable Radar Interferometer (GPRI) is a ground-based real aperture radar (RAR) that can acquire images with high spatial and temporal resolution. The GPRI ground-based radar used in this study composes three antennas with a Ku-band frequency of 17.1-17.3 GHz (1.73-1.75 cm of wavelength). It can measure displacement over time with millimeter-scale precision. It is also possible to adjust the observation mode by arranging the transmitting and receiving antennas for various applications: i) obtaining differential interferograms through the application of interferometric techniques, ii) generation of digital elevation models and iii) acquisition of full polarimetric data. We introduced the hardware configuration of the GPRI ground-based radar, image acquisition, and characteristics of the collected radar images. The interferometric phase difference has been evaluated to apply the multi-temporal interferometric SAR application (MT-InSAR) using the first observation campaigns at Pusan National University in Geumjeong-gu, Busan.

• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.288-294
• /
• 2022

The media content market has been growing, as various types of content are being mass-produced owing to the recent proliferation of the Internet and digital media. In addition, platforms that provide personalized services for content consumption are emerging and competing with each other to recommend personalized content. Existing platforms use a method in which a user directly inputs video metadata. Consequently, significant amounts of time and cost are consumed in processing large amounts of data. In this study, keyframes and audio spectra based on the YCbCr color model of a movie trailer were extracted for the automatic generation of metadata. The extracted audio spectra and image keyframes were used as learning data for genre recognition in deep learning. Deep learning was implemented to determine genres among the video metadata, and suggestions for utilization were proposed. A system that can automatically generate metadata established through the results of this study will be helpful for studying recommendation systems for media super-personalization.

• Journal of the Korean Society of Safety
• /
• v.37 no.5
• /
• pp.7-13
• /
• 2022

Digital image correlation (DIC) is a method used to measure the displacement and strain of structures. It involves transforming and analyzing images before and after deformation using correlation coefficients from irregular light and shade on the surface of structures. In the present study, a microspeckle pattern was applied to the surface of a specimen to identify initial cracking. The test specimen constituted CFRP composites laminated on a curved Al liner The specimen was manufactured by stacking 100 ply of CFRP prepregs in the 0° and 90° directions in a three-point bending test. The equivalent strain was evaluated through DIC analysis after monitoring deformation using a CCD camera. Fracture shape was observed using a microscope. The equivalent strain contour distribution was checked until the maximum load fracture occurred at the center of the test specimen. Variations in the strain indicated the initial occurrence and progression of microcracks. These results can be used to improve the accuracy of detecting micro crack initiation and to achieve structural stability.

• Journal of Fashion Business
• /
• v.26 no.3
• /
• pp.50-71
• /
• 2022

This study aimed to present pioneering data on the use of Metaverse through a case study on the use of Metaverse by luxury brands and to reveal the intrinsic value of Metaverse in the fashion industry. The study was conducted based on literature data such as various articles and papers related to Metaverse and cases of luxury brands. For luxury brands data, we used Interbrand and LYST. As a result, Gucci, Louis Vuitton, Balenciaga, and Burberry were selected. Examples of the use of luxury brands' Metaverse use include; Gucci actively embraced digital technology and used Metaverse technology for the most diverse purposes such as promoting new products, opening seasons, and experiences. Louis Vuitton and Balenciaga focused on the entertainment and games. Burberry focused on promoting and experimenting with new products. As a result of the study, the intrinsic value of the Metaverse is as follows. First, there are no restrictions on time, scale, and institution. Second, active information acceptance is possible; Information can be selectively accommodated through participation and communication using Metaverse. Third, customers and businesses interact in equal positions. As customers participate and communicate, their ties with companies deepen, thus the can create a brand image together. Through Metaverse fashion, customers experiences are not limited to reality and the can directly access optional information. Based on the above examples and values, we hope those fashion companies and Metaverse media will innovate desings to match the trends and the seasons.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.3
• /
• pp.51-57
• /
• 2010

Steganography techniques can be used to hide data within digital images with little or no visible change in the perceived appearance of the image. I propose a steganalysis to detecting hidden message in sequential steganography. This paper presents adjusted technique for detecting abrupt jumps in the statistics of the stego signal during steganalysis. The repeated statistical test based on CUSUM-SPRT runs constantly until it reaches decision. In this paper, I deal with a new and improved statistic $g_t$ by computing $S^{t^*}_j$.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.5 no.2
• /
• pp.215-222
• /
• 2015

This paper presents the measurement of stress intensity factors of inclined cracks by use of photoelasticity. The distributions of isochromatics near a crack tip of the specimen loaded by uniaxially tensile load are used for analysis. Accuracy and reliability is enhanced by twice multiplying and sharpening the measured isochromatics using digital image processing. Photoelastic results are compared with those obtained by finite element method. Good agreement between them shows that the photoelastic analysis is reliable.