• Geomechanics and Engineering
• /
• 제37권5호
• /
• pp.467-474
• /
• 2024

Monitoring and managing the condition of underground utilities is crucial for ground stability. This study aims to determine whether images obtained using ground penetrating radar (GPR) accurately reflect the characteristics of buried pipelines through image analysis. The investigation focuses on pipelines made from different materials, namely concrete and steel, with concrete pipes tested under various diameters to assess detectability under differing conditions. A total of 400 images are acquired at locations with pipelines, and for comparison, an additional 100 data points are collected from areas without pipelines. The study employs GPR at frequencies of 200 MHz and 600 MHz, and image analysis is performed using machine learning-based convolutional neural network (CNN) techniques. The analysis results demonstrate high classification reliability based on the training data, especially in distinguishing between pipes of the same material but of different diameters. The findings suggest that the integration of GPR and CNN algorithms can offer satisfactory performance in exploring the ground's interior characteristics.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1533-1538
• /
• 2008

The development of new material systems like Carbon Fiber Reinforced Polymer (CFRP) places ever higher demands on the techniques for non-destructive material characterisation. Image-producing eddy current methods also need to satisfy these demands. Eddy-current imaging of FRP is based on the anisotropic electrical properties of the material investigated. Significant differences in conductivity between carbon fibres, polymer matrix and integrated functional components can be found. The availability of high-resolution sensors enables access to the local distribution of the electromagnetic properties. The static and dynamic procedures for isolating influential characteristics, already in use in eddy-current technology, can now be supplemented by topographical images. The precondition for a successful implementation of the eddy-current procedure is a deeper understanding of the image-generating process which allows correct interpretation of the images obtained.

• 패션비즈니스
• /
• 제25권4호
• /
• pp.14-35
• /
• 2021

This study compares and analyzes the designs of Burberry creative directors, Christopher Bailey and Riccardo Tisci. For this purpose, 322 photographs (176 Christopher Bailey and 146 Riccardo Tisci) were collected and the data analysis criteria were classified into color, shape, material, decoration, item, and fashion style. With respect to the data analysis method, statistical analysis and content analysis were combined. First, the design characteristics of Christopher Bailey top and bottom combined bright tone, tone-in-tone color scheme, H-line, heterogeneous material combination, and smart casual appeared very frequently. Second, the design characteristics of Riccardo Tisci top and bottom combined were monotone, tone-on-tone color scheme, H-line, heterogeneous material combinations, and street culture. Third, the design differences between creative directors were significantly different in color, tone, color arrangement, pattern, material type, material combination, detail, top and bottom items, and fashion style. Burberry men's wear maintains Burberry's traditional design identity with achromatic colors, beige-based colors, and beige checks. Christopher Bailey's design direction is characterized by modernity in a casual mood that emphasizes practicality. The design direction of Riccardo Tisci is characterized by a wide gap between images in a semi-formal style that emphasizes Burberry's tradition and a free-spirited casual style.

• 복식
• /
• 제59권8호
• /
• pp.152-165
• /
• 2009

The purpose of this study was to expand the expression of Fashion Illustration using Lenticular imaging process. In the 2-dimensional pictures, Lenticular imaging process can be effective to make multiple, virtual and variable images, which are assumed the main characteristics of modern Fashion Illustration. For this study, the main characteristics of digital based fashion trend and Fashion Illustration were analyzed. The main characteristics of digital based fashion were 'Interaction, Variableness, Virtuality, Multiples and Hyper-text' which were related with Simulacre thinking. The main characteristics of expression in Fashion Illustration were 'Virtuality and Multiples'. The image of 'Variableness' was an important factor in digital based fashion, but it was restricted within Fashion Illustration because of the 2-dimensional picture. Therefore, the Lenticular imaging process was proposed as an effective method to expand 2-dimensional limit, giving an effect of 'Variableness' in Fashion Illustration. Based on this study, 5 illustration works were proposed. The Lenticular imaging process was applied in making the images of 'Virtuality, Multiples and Variableness' in 5 works. The result of this study can be a basic material to understand the characteristics of modern Fashion Illustration as a meaningful sub-culture, and diverse expressions corresponding with the phases of the times.

• 대한조선학회논문집
• /
• 제56권6호
• /
• pp.473-479
• /
• 2019

Welding is one of the most popular joining methods and most welding quality estimation methods are executed using joined material. This paper propose welding quality estimation methods using dynamic current, voltage and resistance which are obtained during welding in real time. There are many kinds of welding method. Among them, we focused on the projection welding and gathered dynamic characteristics from two different types of projection welding. For image learning, graphs are drawn using obtained current, voltage and resistance, and the graphs are converted to images. The images are labeled with two sub-categories - normal and defect. For deep learning of images obtained from welding, Convolutional Neural Network (CNN) is applied, and Tensorflow was used as a framework for deep learning. With two resistance welding test datasets, we conclude that the Convolutional Neural Network helps in predicting the welding quality.

• 한국방사선학회논문지
• /
• 제15권3호
• /
• pp.273-279
• /
• 2021

전산화단층촬영 검사 시 인체 내에 삽입되어 있는 금속물질은 금속주위에 있는 인체조직이나 뼈와 큰 밀도차이가 있어 인공물을 발생시킨다. 이 실험을 통해 Single source Dual energy CT에서 Dual energy검사 및 MAR 알고리즘의 특성을 비교분석하여 임상적으로 적용방법에 대한 기초자료를 제시하려 한다. MAR 알고리즘을 적용하거나 Dual Energy를 이용하여 검사하였을 때 금속 인공물이 감소하였는데 MAR알고리즘을 적용한 영상은 세부적인 부분을 왜곡시키는 단점이 있다. Dual Energy로 검사한 영상은 MAR알고리즘을 적용한 영상보다 세부적인 부분까지 구현해 낼 수 있다는 장점이 있으나 재구성에 소요되는 시간이 길며 피폭선량이 MAR알고리즘을 적용한 영상보다 약 4배 가량 높았다. 수술 후 Follow up 및 금속물질의 위치를 파악하기 위해서는 MAR알고리즘을 적용하여 영상을 획득하는 것이 검사적 측면에서 유용하며 미세 병변 확인 및 수술계획을 세우거나 진단적인 측면에서 검사를 시행하였을 때는 Dual Energy로 검사하는 것이 더 유용하다.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.361-370
• /
• 2020

Automatic building material recognition has been a popular research interest over the past decade because it is useful for construction management and facility management. Currently, the extensively used methods for automatic material recognition are mainly based on 2D images. A terrestrial laser scanner (TLS) with a built-in camera can generate a set of coloured laser scan data that contains not only the visual features of building materials but also other attributes such as material reflectance and surface roughness. With more characteristics provided, laser scan data have the potential to improve the accuracy of building material recognition. Therefore, this research aims to develop a TLS-based building material recognition method by combining machine learning techniques. The developed method uses material reflectance, HSV colour values, and surface roughness as the features for material recognition. A database containing the laser scan data of common building materials was created and used for model training and validation with machine learning techniques. Different machine learning algorithms were compared, and the best algorithm showed an average recognition accuracy of 96.5%, which demonstrated the feasibility of the developed method.

• 감성과학
• /
• 제14권3호
• /
• pp.347-360
• /
• 2011

본 연구는 TV화면에 입체감을 표현하여 소비자의 구매 욕구를 촉진하는 TV홈쇼핑 식공간 연출에서 표현되는 공간 깊이감이 표현되는 연출의 특성을 파악하기 위해 2005년 3월에서 2010년 11월까지 $C^*$홈쇼핑에서 실제로 방영된 식기 판매 방송 중 6개 브랜드 식기 판매 방송의 실제 연출 이미지 자료를 분석하고, 신뢰도 분석, 요인 분석과 다중 회귀분석기법을 사용하여 설문 조사를 통해서 감성 형용사 이미지어를 분석하였다.TV화면이라는 평면에 입체를 표현되는 연출의 특징은 크기의 비교, 중첩, 사선배치와 원근법적 배치로 추출하여 분석하였고, 식기방송에 주로 사용되는 카메라 앵글의 종류를 버즈 아이 뷰, 하이 앵글, 아이 레벨 등으로 구분하여 적용하였다. 이 분석의 결과로 정리되는 것은 소비자 선호도가 높은 연출은 브랜드 식기의 주요인에 높은 상관도를 보인 이미지어를 인식하는 경우라는 것이다. 따라서 카메라 앵글과 특성에 의한 선호 연출의 방향 제시가 가능하며, 소비자가 선호하는 정량적 데이터 베이스를 이용하는 새로운 개념의 공간 연출 개념이 가능하다고 본다.

• 복식문화연구
• /
• 제13권3호
• /
• pp.425-438
• /
• 2005

This study is to examine the types of expression and aesthetic characteristics of on-line game characters by analyzing those game characters' body and their costume that appear in various domestic on-line game sites. It is shown in this study that types of the human bodies and costume expressed through the game characters are grouped into five categories such as exposure and tightness, enlargement and exaggeration, curtailment and simplification, gender stereotype and unification. Furthermore, there are four typical aesthetic characteristics resulting from those types of expressions; First, 'grotesque' is expressed in the form of extreme enlargement and exaggeration, extreme exposure and concealment, combined images among human, animal or machine, or monstrous devilish images. Second, in an effort to express 'eroticism', bodies are directly exposed, see-through costumes are used in order to emphasize the body lines or very tight designs are used. Third, 'futuristic' characteristics are shown through geometrical shape and silhouette, machine-like details, strong artificial colors or glossy hi-tech material. Lastly, 'pastiche' is expressed with reconciliation of variety of costumes of game characters. Various opposite or heterogeneous styles are combined or harmonized each other to show pastiche, of which examples are male and female, superior culture and inferior one, rich and poor, oriental and western, human and machine, human and nature or past and future, etc.

• 한국실내디자인학회논문집
• /
• 제33호
• /
• pp.19-26
• /
• 2002

This study analyzed the characteristics of spatial expression in the Barcelona Pavilion to be based on tectonics. Mies pointed out the image of materiality about the material rather than the process of tectonics using the material, and he also expressed demateriality in the image of each material through the reflection. To be liberated from structural matters, the wall has been introduced. He intended to show the design plan as the independent structural system, however, the wall actually seems to be supporting the roof that shows rather clearly self-contradictory because of the expression of materiality in the material. In terms of architectural elements; wall, roof, column, floor, and so forth, tectonic expression and abstract aesthetics stands face to face, because of hiding the productional process and transforming to line and surface in the image of materiality. The interior of the glass wall seems fairly closed space from the exterior, because materiality and reflection of materials of columns and podium. The character of experiential space is inconsistent and fragmentary because of the splendid images from maternality and reflection on the wall, and collision with the reality and the image the wall reflects, even though the geometrical space of the Pavilion's plan has the mutual penetrability and organic character.