• 한국측량학회지
• /
• 제26권1호
• /
• pp.73-83
• /
• 2008

국토 및 도시정보의 공간분석과 의사결정을 위하여 디지털 영상자료를 이용한 3D GIS와 구축된 3D 도형정보를 현실적으로 가시화하기 위한 사실적 3D 영상모형(3D photo-realistic model)에 관한 기술이 급속히 발전하고 있다. 현재, 3D 모형 구축을 위하여 위성영상, 항공영상 및 항공라이다 데이터가 주로 이용되고 있으며, 항공경사사진 또는 지상사진에서 취득된 텍스쳐를 이용하여 3D 영상모형을 구축하고 있다. 그러나, 상기 데이터만을 이용하여 구축된 모형은 지형 및 지물을 세밀하고 사실감 있게 표현하는데 제한적이기 때문에 고품질의 영상모형 구축이 필요한 실정이다. 따라서, 본 연구에서는 인공지물과 특수지형을 대상으로 공간정확도, 세밀묘사 및 현실감이 강조된 실세계에 근접한 3D 영상모형을 구축하기 위하여 항공사진, 항공라이다, 지상사진 및 지상라이다 데이터로 실세계를 표현하기 위한 기법을 분석하고, 위치정확도와 함께 사진과 같은 사실감을 확보한 3D 영상모형을 구축하고 인터넷 3D 영상지도 서비스를 통하여 제공할 수 있도록 하였다. 또한, 3D 영상모형은 이용목적 및 디스플레이 축척에 따라 표현요소를 구분하여 구축할 필요가 있으며, 본 연구에서는 LoD(Level of Detail) 개념을 도입하여 건물 3D 영상모형을 5단계로 정의하고 단계별로 모형을 구축하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.220-223
• /
• 2004

Automatic image registration is an essential element of remote sensing because remote sensing system generates enormous amount of data, which are multiple observations of the same features at different times and by different sensor. The general process of automatic image registration includes three steps: 1) The extraction of features to be used in the matching process, 2) the feature matching strategy and accurate matching process, 3) the resampling of the data based on the correspondence computed from matched feature. For step 2) and 3), we have developed an algorithms for automated registration of satellite images with RANSAC(Random Sample Consensus) in success. However, for step 1), There still remains human operation to generate GCP Chips, which is time consuming, laborious and expensive process. The main idea of this research is that we are able to automatically generate GCP chips with comer detection algorithms without GPS survey and human interventions if we have systematic corrected satellite image within adaptable positional accuracy. In this research, we use SUSAN(Smallest Univalue Segment Assimilating Nucleus) algorithm in order to detect the comer. SUSAN algorithm is known as the best robust algorithms for comer detection in the field of compute vision. However, there are so many comers in high-resolution images so that we need to reduce the comer points from SUSAN algorithms to overcome redundancy. In experiment, we automatically generate GCP chips from IKONOS images with geo level using SUSAN algorithms. Then we extract reference coordinate from IKONOS images and DEM data and filter the comer points using texture analysis. At last, we apply automatically collected GCP chips by proposed method and the GCP by operator to in-house automatic precision correction algorithms. The compared result will be presented to show the GCP quality.

• 한국의류산업학회지
• /
• 제9권4호
• /
• pp.401-408
• /
• 2007

The study aims to examine consumer awareness of green fashion products and demographic characteristics by subdividing environmentally conscious consumers of such products in the current domestic fashion market. It then compares the result with the characteristics of environmentally conscious consumers studied by 1999 in order to understand the trend of the consumer group in the fashion market and to promote the use of green fashion products. Marketing strategies for green fashion products suggested by the study are as follows: First, fashion firms are required to develop and publicize shops selling recycled or second-hand clothing that environmentally conscious consumers show constant interest. For instance, clothing patterns may be developed to enable consumers to make their kids' clothing easily at home, and various garments made from recycled materials may stimulate environmentally conscious consumers' desire to buy. Particularly, advanced technologies should be developed and publicized to manufacture garments that can excel existing ones made of normal materials in their features in order to satisfy consumers' interest in clothing made from recycled PET bottles. In addition, various natural dyes should be developed to decrease water pollution. Second, it seems imperative to develop clothing made of recycled knitted apparel that attracts consumers' interest more than ever, fashionable multi-purpose clothing, and environmentally friendly materials. As the use of natural fur or leather can cause the endangerment of wild animals and the destruction of the ecosystem, synthetic fur or leather may be used to develop sophisticated products with the same texture as real ones to attract environmentally conscious consumers' interest.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1998년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.153-158
• /
• 1998

Since the mid-1990′s, researches on 3D GIS have been regarded as one of main issues both in the academic sites and commercial vendors; recently, some prototyped systems or the first versioned software systems of commercial basis are being reported and released. Unlike conventional 2D GIS, which consists in intelligent structured GIS or desktop GIS, every 3D GIS has its own distinguished features according to data structure-supporting capability, GIS-styled functionality, external database accessibility, interfacing extents with 2D GIS, 3D visualization/texture mapping ability, and so forth. In this study, technical aspects related to system development, SERI-Web3D GIS ver. 1.2, are explained. Main features in this revised 3D GIS can be summarized: 2-tier system model(client-server), VGFF(Virtual GIS File Format), internal GIS import, Feature manager(zoning, layering, visualization evironment), Scene manager(manage 3D geographic world), Scene editor, Spatial analyzer(Intersect, Buffering, Network analysis), VRML exporter. While, most other 3D GISes or cartographic mapping systems may be categorized into 3D visualization systems handling terrain height-field processing, 2D GIS extension modules, or 3D geometric feature generation system using orthophoto image: actually, these are eventually considered as several parts of "real 3D GIS". As well as these things, other components, especially web-based 3D GIS, are being implemented in this study: Surface/feature integration, Java/VRML linkage, Mesh/Grid problem, LOD(Level of Detail)/Tiling, Public access security problem, 3-tier architecture extension, Surface handling strategy for VRML.

• 한국산업정보학회논문지
• /
• 제12권3호
• /
• pp.60-68
• /
• 2007

본 논문에서는 자동으로 사용자의 얼굴 표정을 인식할 수 있는 시스템을 제안한다. 제안된 시스템은 휴리스틱 정보를 기반으로 설계된 트리 구조를 이용하여 행복, 역겨움, 놀람의 감정과 무표정을 인식한다. 카메라로부터 영상이 들어오면 먼저 얼굴 특징 검출기에서 피부색 모델과 연결성분 분석을 이용하여 얼굴 영역을 획득한다. 그 후에 신경망 기반의 텍스처 분류기를 사용하여 눈 영역과 비 눈 영역으로 구분한 뒤 눈의 중심 영역과 에지 정보를 기반으로 하여 눈, 눈썹, 입 등의 얼굴 특징을 찾는다. 검출된 얼굴 특징들은 얼굴 표정 인식기에 사용되며 얼굴 인식기는 이를 기반으로 한 decision tree를 이용하여 얼굴 감정을 인식한다. 제안된 방법의 성능을 평가하기 위해 MMI JAFFE, VAK DB에서 총 180장의 이미지를 사용하여 테스트하였고 약 93%의 정확도를 보였다.

• 한국의류학회지
• /
• 제36권4호
• /
• pp.400-411
• /
• 2012

This study analyzes the formative changes and trends of cape design in modern fashion. In this study, a total of 496 cape designs were collected through the four major fashion collections of Paris, Milan, New York, and London from 2006S/S to 2010F/W, and a literature overview on capes was performed. The results of this study show that the cases with collars and hoods attached outnumbered the non-collared designs. In addition, the cases of lengthy cape in the hip or knee line represent more portions in designs. As to the material, it indicated that generic cloth was used the most. In most cases, decorations with various details and trimmings were also used. For expression characteristics, cases only with unique texture to cloth material and formative beauty were the most remarkable without decoration. For the formative feature, the independent item style was found the most, even though it was worn together with other kinds of clothing. Integration with other types also appeared such as cape jacket, cape dress, cape one-piece, or cape coat. Cape design features in contemporary fashion and could be characterized as feministic elegancy, harmony of practical value and fashion, authoritativeness, and decorativeness from the design trend analysis.

• 한국비블리아학회지
• /
• 제16권2호
• /
• pp.157-175
• /
• 2005

본 논문의 목적은 멀티미디어 내용을 표현하기 위해 제정된 MPEG-7의 비주얼 디스크립터를 설명하고 분석하기 위한 것이다. MPEG-7의 비주얼 디스크립터는 컬러, 모양, 질감, 모션으로 구성되어 있으며 이들 각각의 요소들에 대해 예제 및 응용분야와 더불어서 자세히 설명하고 있다. 마지막으로 본 연구에서는 이들 비주얼 디스크립터에 대한 전반적인 응용분야를 기술하고 있다. 이러한 비주얼 디스크립터들은 다양한 모양의 멀티미디어 내용을 인간의 개입 없이 자동으로 풍부하고 상세하게 표현할 수 있으며 내용 표현의 일관성을 유지하게 함으로써 멀티미디어 검색의 성능을 향상시킬 뿐 아니라 시스템간의 상호운영성을 향상 시킬 수 있을 것으로 기대된다.

• Journal of Electrical Engineering and Technology
• /
• 제10권2호
• /
• pp.670-675
• /
• 2015

Medical imaging is one of the most powerful tools for gaining information about internal organs and tissues. It is a challenging task to develop sophisticated image analysis methods in order to improve the accuracy of diagnosis. The objective of this paper is to develop a Computer Aided Diagnostics (CAD) scheme for Brain Tumour detection from Magnetic Resonance Image (MRI) using active contour models and to investigate with several approaches for improving CAD performances. The problem in clinical medicine is the automatic detection of brain Tumours with maximum accuracy and in less time. This work involves the following steps: i) Segmentation performed by Fuzzy Clustering with Level Set Method (FCMLSM) and performance is compared with snake models based on Balloon force and Gradient Vector Force (GVF), Distance Regularized Level Set Method (DRLSE). ii) Feature extraction done by Shape and Texture based features. iii) Brain Tumour detection performed by various tree classifiers. Based on investigation FCMLSM is well suited segmentation method and Random Forest is the most optimum classifier for this problem. This method gives accuracy of 97% and with minimum classification error. The time taken to detect Tumour is approximately 2 mins for an examination (30 slices).

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.40-48
• /
• 2021

Content-Based Image Retrieval (CBIR) system plays a vital role to retrieve the relevant images as per the user perception from the huge database is a challenging task. Images are represented is to employ a combination of low-level features as per their visual content to form a feature vector. To reduce the search time of a large database while retrieving images, a novel image retrieval technique based on feature dimensionality reduction is being proposed with the exploit of metaheuristic optimization techniques based on Genetic Algorithm (GA), Extended Binary Cuckoo Search (EBCS) and Whale Optimization Algorithm (WOA). Each image in the database is indexed using a feature vector comprising of fuzzified based color histogram descriptor for color and Median binary pattern were derived in the color space from HSI for texture feature variants respectively. Finally, results are being compared in terms of Precision, Recall, F-measure, Accuracy, and error rate with benchmark classification algorithms (Linear discriminant analysis, CatBoost, Extra Trees, Random Forest, Naive Bayes, light gradient boosting, Extreme gradient boosting, k-NN, and Ridge) to validate the efficiency of the proposed approach. Finally, a ranking of the techniques using TOPSIS has been considered choosing the best feature selection technique based on different model parameters.

• 한국의상디자인학회지
• /
• 제15권4호
• /
• pp.129-142
• /
• 2013

Fabrics created unique features through the change in various ways depending on the elements including fabric structure, threads, thickness, weaving, patterns and processing. This study examined the difference between texture and image depending on components of fabrics. In order to understand the trend of components of fabrics, the actual components of fabrics was analyzed by year, using the women's apparel trend books, Nelly Rodi Fabrics and Promostyl Fabrics. This study analyzed Spring/Summer season and Fall/Winter season from 2002 to 2012. Frequency analysis, cross-tabulation analysis, multiple response cross tabulation analysis were implemented using SPSS 18.0. The followings are the analysis results. For fabric composition, Spring/Summer season used cotton fabric the most. Cotton fabric accounted for relatively high usage in 2005, 2007 and 2008. Fall/Winter season used wool the most in 2002, 2003, 2004 and 2005. In case of fiber blend by fabric composition, cotton was blended with other fibers in Spring/Summer season except wool. The fiber blending ratio of wool was the highest in Fall/Winter season. Wool was blended in most fabrics. More than two patterns were mixed for fabric patterns. The fabric patterns were applied the most in 2012. For fabric processing, the fabrics by sensitivity-functional processing were continuously used every year and the surface finish showed relatively high usage in 2002 and 2011. In conclusion, this study will build the systematic data for 11 years including fabric trends in the past. It can improve specialization, systematization and efficiency in fabric planning.