• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.288-296
• /
• 2021

Automated face recognition in a runtime environment is gaining more and more important in the fields of surveillance and urban security. This is a difficult task keeping in mind the constantly volatile image landscape with varying features and attributes. For a system to be beneficial in industrial settings, it is pertinent that its efficiency isn't compromised when running on roads, intersections, and busy streets. However, recognition in such uncontrolled circumstances is a major problem in real-life applications. In this paper, the main problem of face recognition in which full face is not visible (Occlusion). This is a common occurrence as any person can change his features by wearing a scarf, sunglass or by merely growing a mustache or beard. Such types of discrepancies in facial appearance are frequently stumbled upon in an uncontrolled circumstance and possibly will be a reason to the security systems which are based upon face recognition. These types of variations are very common in a real-life environment. It has been analyzed that it has been studied less in literature but now researchers have a major focus on this type of variation. Existing state-of-the-art techniques suffer from several limitations. Most significant amongst them are low level of usability and poor response time in case of any calamity. In this paper, an improved face recognition system is developed to solve the problem of occlusion known as FRS-OCC. To build the FRS-OCC system, the color and texture features are used and then an incremental learning algorithm (Learn++) to select more informative features. Afterward, the trained stack-based autoencoder (SAE) deep learning algorithm is used to recognize a human face. Overall, the FRS-OCC system is used to introduce such algorithms which enhance the response time to guarantee a benchmark quality of service in any situation. To test and evaluate the performance of the proposed FRS-OCC system, the AR face dataset is utilized. On average, the FRS-OCC system is outperformed and achieved SE of 98.82%, SP of 98.49%, AC of 98.76% and AUC of 0.9995 compared to other state-of-the-art methods. The obtained results indicate that the FRS-OCC system can be used in any surveillance application.

• Journal of Platform Technology
• /
• v.8 no.4
• /
• pp.20-28
• /
• 2020

In this paper, a voice, object, and optical character recognition platform including voice recognition-based smart wearable devices, smart devices, and web AI servers was proposed as an appropriate technology to help the visually impaired to live independently by learning the life cycle of the visually impaired in advance. The wearable device for the visually impaired was designed and manufactured with a reverse neckband structure to increase the convenience of wearing and the efficiency of object recognition. And the high-sensitivity small microphone and speaker attached to the wearable device was configured to support the voice recognition interface function consisting of the app of the smart device linked to the wearable device. From experimental results, the voice, object, and optical character recognition service used open source and Google APIs in the web AI server, and it was confirmed that the accuracy of voice, object and optical character recognition of the service platform achieved an average of 90% or more.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.1-9
• /
• 2021

The hologram pyramid is an application of floating holograms, allowing the observer to see three-dimensional holograms from various angles without wearing wearable devices. Due to the low cost and ease of manufacturing, it has been used in a wide variety of fields as diverse as education, prototyping, showcase, and etc. But, when the observer looks at the hologram from the place where each side of the hologram pyramid is connected, the hologram looks cut and distorted. Also, the observer can see the only hologram of angles viewed head-on from each side. In this paper, we propose a method of generating a hologram image corresponding to the observer's gaze angle by tracking the observer's position and conducting reverse distortion. It provide a hologram of the angle viewed by the observer without cutting and distortion. In addition, the existing method and the proposed method were applied and compared in the hologram pyramid.

• Journal of the Korean Orthopaedic Association
• /
• v.56 no.3
• /
• pp.266-271
• /
• 2021

Osteoporosis associated with pregnancy and lactation is a rare disease that can cause osteoporotic vertebral compression fracture (OVCF). Patients usually complain of severe back pain, which is easily mistaken for pain due to pregnancy, childbirth, and lactation, making a rapid diagnosis and treatment difficult. The authors diagnosed OVCF related to pregnancy and lactation through a physical examination, simple radiography, whole-body bone scan, magnetic resonance image, bone marrow density, and blood tests in a 29-year-old female patient and a 31-year-old female patient who presented with low back pain. This paper reports two cases of symptom improvement through a teriparatide injection, wearing thoracic lumbar sacral orthosis and taking calcium and vitamin D with a review of the literature.

• Fashion & Textile Research Journal
• /
• v.24 no.5
• /
• pp.493-504
• /
• 2022

This study aims to gain a deeper understanding of the fashion styles of underground rappers in China and South Korea. Due to rappers' fashion influence on modern fashion trends, research on rapper fashion has been conducted steadily in the field of apparel. Qualitative research methodologies including literature research and in-depth interviews were the primary techniques used to solve the research questions. In-depth interviews were conducted with 10 Chinese underground rappers and 10 Korean underground rappers to reveal and explore their fashion style and view of fashion. As a result, the participants' fashion styles were categorized into four styles: authentic hip-hop fashion style, popularized hip-hop fashion style, easy sports casual style, and trendy street style. Rappers from both countries consider that their identity as rappers can be demonstrated through their hip-hop fashion style. The influence of hip-hop culture and the popularity of rap music differs between China and Korea. It affects not only the rapper's musical characteristics, but also their fashion style. While Korean underground rappers' fashions style is trendier, Chinese underground rappers' fashions style displays stronger characteristics of hip-hop fashion. Due to the public's negative view of rappers, some Korean underground rappers intentionally try to hide their identity by wearing a fashion style that differs from the authentic rapper image. Understanding the fashion styles of underground rappers in Korea and China is expected to assist in predicting future hip-hop culture and rapper fashion trends.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.569-570
• /
• 2022

Failure situations occur frequently in the industry, and the existing 2D-based manual for this purpose is not intuitive to understand and it is difficult to immediately interact with maintenance experts. In this paper, we propose a technology that enables workers to perform maintenance in real time with the help of experts without restrictions in time and place based on augmented reality when a failure situation occurs at a remote location. A local virtual human-based expert diagnoses a failure situation based on an adapted panoramic image of a remote failure situation while wearing an HMD headset, and gives instructions to a remote operator. In addition, in an augmented reality (AR) environment in a remote location, for the interaction between the operator and the expert, the HMD's microphone is used to create the expert's hand as well as verbal communication. You can use to point or draw a picture. If this technology is used, it is possible to overcome the limitations of the existing 2D-based manual, and to provide assistance in performing maintenance smoothly remotely even if an expert does not directly visit a remote location.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.25 no.4
• /
• pp.107-122
• /
• 2023

This study analyzed the style, dimensions, fabric patterns, colors, and fabrics of a traditional Chinese women's dress from the Zhou Dynasty, and reconstructed it in the form of a virtual garment using 3D CLO. Based on ancient flat image data and three-dimensional portrait data, who wore them, how they were worn, and how they were coordinated was analyzed. In order to analyze the size and pattern of the straight Ju Chines dress, data from the excavation report and the tomb owner's anthropometric measurements were combined to infer the wearing condition and organize the sculptural features. Dimensional analysis was carried out using a well-preserved small-scale woven cotton cloth as a restoration model, and the horizontal and vertical dimensions were reasonably estimated using the shape proportioning method. The analysis of the colors and patterns of the fabrics was based on the colors and patterns of the fabrics excavated from Masan Tomb No. 1 during the Eastern Zhou, Qin, and Han periods. Finally, a virtual model was created using data from the excavation report and the age and height information of the owner of the excavated robe, and the pose and size of the virtual model were determined using 3D CLO. Based on the previous research data, the garment was virtually sewn and simulated. The shape, pressure, and strain of the garment in different postures was also compared. Through the research direction of pattern and 3D restoration, this research maximizes the restoration of Chinese traditional women's dress and presents it in a more intuitive, comprehensive, and vivid way.

• Journal of the Korean Society of Costume
• /
• v.46
• /
• pp.17-30
• /
• 1999

The purpose of this study is to investigate the philosophy behind the Kasaya and its evolution through its clothing material colour structure and sewing. According to the study the results were as follows. 1. The philosophy behind the dressing of the Kasaya can be found in the Therefore wearing the Kasaya symbolizes the Buddhist philosophy of Jat'ailshisongbul ("Simultaneous attaining of Buddhahood for Everyone") 2. The material symbolizes endurance and contentiment by being satisfied with any kind of clothes may they be good or bad. The material of the kasaya comes to signify the harmony among the monk's community 3. The Kasaya uses peculiar colours and the prohibits the use of the five primary and seconary colous. This is to symbolize equality wherein there is no distinction between the noble and the mean. 4. The structure of the Kasaya according the takes the form of a field The Jo is cut lengthwise and divided in nine grades following the Mahayana tradition as written in the This idea reflects the philosophy of salvation of the Pure land thought. The Je has many Jang('long') and fex Dan('short') The meaning of this is that all living beings by self-cultivation can overcome the dirty law of the secular world and follow the way of the sage who have attained their Buddha nature. 5. With respect to the sewing after finishin the sewing the Jang and the Dan are combined together representing the interdependence between the holy person and the common person. Therefore the sewing ssymbolizes the interconnection among all living beings as it arise from the "conditional causation" law. As I have shown above the philosophy behind of the Kasaya developed and was enriched as it cross over China from India to the Original Buddhist thought with which was created in India was added the richness of the Mahayana buddhist thought. As I have shown above the philosophy behind of the Kasaya developed and was enriched as it cross over China from India to the Original Buddhist thought with which was created in India was added the richness of the Nahayana Buddhist thought with which was created in India was added the richness of the Mahayana buddhist thought. As a result the Dasaya came to signify the "field image". The field-image symbolized by the kasaya came to signify the "heart-field" of all living beings. The "heart-field" by its cultivation is field with blessings. Therefore from the sanghati the Nine Grade the evolution and changes in the designs of the kasaya through the different periods of history became clearly an expression how it is possible for anybody to attend the Buddha nature. This changes also show how the Buddhist precepts became reformed from the original Buddhism.ecepts became reformed from the original Buddhism.

• Journal of Cadastre & Land InformatiX
• /
• v.49 no.1
• /
• pp.85-101
• /
• 2019

Recently, thank to the popularization of light-weight drone through the significant developments in computer technologies as well as the advanced automated procedures in photogrammetry, Unmanned Aircraft Systems have led to a growing interest in industry as a whole. Documentation, maintenance, and restoration projects of large scaled cultural property would required accurate 3D phenomenon modeling and efficient visual inspection methods. The object of this study verify on the accuracies achieved of 3D phenomenon reconstruction as well as on the validity of the preservation, maintenance and restoration of large scaled cultural property by UAS photogrammetry. The test object is cltural heritage(treasure 1324) that is the rock-carved standing Bodhisattva in Soraesan Mountain, Siheung, documented in Goryeo Period(918-1392). This standing Bodhisattva has of particular interests since it's size is largest stone Buddha carved in a rock wall and is wearing a lotus shaped crown that is decorated with arabesque patterns. The positioning accuracy of UAS photogrammetry were compared with non-target total station survey results on the check points after creating 3D phenomenal models in real world coordinates system from photos, and also the quantified informations documented by Culture Heritage Administration were compared with UAS on the bodhisattva image of thin lines. Especially, tests the validity of UAS photogrammetry as a alternative method of visual inspection methods. In particular, we examined the effectiveness of the two techniques as well as the relative fluctuation of rock surface for about 2 years through superposition analysis of 3D points cloud models produced by both UAS image analysis and ground laser scanning techniques. Comparison studies and experimental results prove the accuracy and efficient of UAS photogrammetry in 3D phenomenon modeling, maintenance and restoration for various large-sized Cultural Heritage.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.313-315
• /
• 2019

Although Korea's fashion market has negative growth, it has been growing again since 2018. This phenomenon means that people are becoming more interested in fashion. As interest in fashion grows, people visit various community sites for reference to find a suitable coordination for themselves. Most community sites, however, are manually categorizing each garment. Not only do these tasks take a lot of time, but they also make it difficult to search for multiple clothing at the same time. In other words, I can't choose what I want at the same time, and if I choose what I want, I have to look at what the model is wearing and refer to it. The problem with this may not help because the coordination in which the model provided is worn is more likely to be the one that the user does not want. In this paper, when the image is uploaded to improve the problem, the clothing is analyzed with AI analysis model and automatically classified and stored. Therefore, not only can you search for one clothes in the existing way, but you can also search for multiple clothes at the same time. The service is expected to allow more people to easily find and refer to the code for themselves.