• The Transactions of the Korea Information Processing Society
• /
• v.5 no.12
• /
• pp.3025-3035
• /
• 1998

In this paper, we describe the design and implementationof COIRS COncept,based Image Retricval System). It differs from extant content-based image retrieval systems in that it enables users to query based on concepts- it allows users to get images concepmally relevant. A concept is basically an aggregation of promitive objects in an image. For such a cencept based image retrieval functionality. COIRS aglopts an image descriptor called triple and includes a triple thesaurus used for capturing concepts. There are four facilities in COIRS: a visual image indeses a triple thesaurus, an inverted fiel, and a user query interface. The visnal image indeser facilitates object laeling and the percification of positionof objects. It is an assistant tool designed to minimize manual work when indexing images. The thesarrus captires the concepts by analyzing triples, thereby extracting image semantics. The triples are then for formalating queries as well as indexing images. The user query interiare enables users to formulate...

• Archives of design research
• /
• v.14 no.2
• /
• pp.197-207
• /
• 2001

A designed object reveals its meaning and image through form, color and material. Among these three elements, material has more powerful influence with its tactile and visual characteristics. In Korea, traditionally materials itself were mainly used to design artifacts rather than various color or formal decoration. The purpose of this study is to investigate the Korean traditional materials, and to classify them by the characteristics of their texture. For this study, the pictures of Korean traditional artifacts were collected from the national museums and literature. Those are architectural and interior elements, furniture, cloths and textiles, arts and crafts. Total of 533 collected artifacts were classified into seven categories, metal, day, stone, paper, wood, straw, fabric things. : 59 metal things, 115 clay things, 62 stone things, 73 paper things, 80 wood things, 47 straw things, 97 fabric things. Each materials were classified into its forming methods and surface treatment focused on the he characteristics of their surface texture. Throughout this study, the uniqueness of forming method and surface treatment of each materials in Korea has been clarified. And furthermore the classification by this various traditional methods of materials will provide plentiful information and ideas to today's designers of the world.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1462-1468
• /
• 2022

Among the data used for the diagnosis of calf disease, feces play an important role in disease diagnosis. In the image of calf feces, the health status can be known by the shape, color, and texture. For the fecal image that can identify the health status, data of 207 normal calves and 158 calves with diarrhea were pre-processed according to fecal status and used. In this paper, images of fecal variables are detected among the collected calf data and images are trained by applying GLCM-CNN, which combines the properties of CNN and GLCM, on a dataset containing disease symptoms using convolutional network technology. There was a significant difference between CNN's 89.9% accuracy and GLCM-CNN, which showed 91.7% accuracy, and GLCM-CNN showed a high accuracy of 1.8%.

• Conservation Science in Museum
• /
• v.29
• /
• pp.111-132
• /
• 2023

Terahertz radiation cannot pass through metal and therefore reflect and return most signals. Utilizing this property, this study analyzed information on paintings to verify the usage of metal materials on paintings and the scope of their application. First, the study tested specimens of metal-based pigments and synthetic pearl pigments with metallic colors and textures in order to compare basic characteristics of terahertz images, such as signal severance caused by metallic substances, traits reflected in cross-section images, and high degree of reflection. Subsequently, based on the collected information, the study diagnosed various types of paintings including Korean traditional paintings and oil paintings using the terahertz imaging technique to confirm the usage of metal-based pigments in the inner layers of paintings and their scope of application. The terahertz imaging technique could has the potential to provide scientific evidence for previously-undiscovered information and art-historical records about various types of paintings that used metalbased pigments, thereby rendering significant utility for the conservation and authentication of paintings.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05b
• /
• pp.874-877
• /
• 2011

본 연구의 목적은 기업의 활동 중 감각적 이미지 전략 구축 중 디자인 요소의 선택과 같은 프로세스를 체계화하며, 제품 제작 담당자에게 전달자와 수용자의 감각 이미지 연구를 통하여 감각의 효율적 활용에 대한 연구를 하고자 하였다. 연구방법은 여러 감각이 혼합되어 있는 공감각이라는 인간의 감각이 브랜드 관련 기업, 제품, 서비스, 기관 등에 어떠한 형태로 적용되어 표현되는지 현황조사를 통하여 분석하였다. 이론적 이해와 고찰 및 사례분석 등은 유사한 논제의 국내 외 문헌조사와 2009년 후반기까지 시판 중인 제품의 인터넷 자료를 병행 하였다. 연구 결과에 의하면 첫째, 시각적인 공감각은 제품의 연상되는 형태, 로고디자인의 형태, 재료의 색상을 통하여 식감을 자극하고 있었다. 둘째, 청각적 공감각은 의성어나 소리를 연상시키는 심볼마크를 통하여 표현하고 있었다. 셋째, 후각적 공감각은 향기 나는 소리나 향기 나는 원재료, 향기 나는 매장 등을 통하여 후각을 사용하고 있었다. 넷째, 미각적 공감각은 제품의 신속함이나 달콤함 또는 연상되는 맛을 통하여 독특한 미각을 메타포로 사용하는 경우가 많았다. 마지막 다섯째, 촉각적 공감각은 패키지 모양이나 형태, 제품명에서 느껴지는 온도, 제품 표면질감을 다른 소재로 표현하는 방식으로 촉각을 자극하고 있었다. 이러한 공감각을 이용한 브랜드와 디자인은 소비자로 하여금 오감을 자극하여 감성시대에 능동적 감성디자인 소비자로 변화시키고 있다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Archives of design research
• /
• v.13
• /
• pp.83-91
• /
• 1996

In this paper, proposed through the development process of a VCR the process of making exact three-dimensional modeling data using the Alias-one of the popular workstation in product design development process. At first, the features of the NURBS curve which is the basic curve in the modeling of Alias system and the methods of building surface are reviewed. The methods of rendering, lighting and textures are reviewed for application of realistic image presentation after building basic surfaces. The synthetic application methode of these factors necessary for the product design modeling is presented through the development process of a VCR.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.837-840
• /
• 2000

동영상에서 움직이는 객체 분할 및 모션 예측을 동시에 수행할 수 있는 연구는 다양한 방법으로 시도 되어 왔다. 실제 이미지를 서로 다른 움직임이나 서로 다른 공간적인 특정 영역으로 분리 될 수 있다고 가정 한다면 복수의 객체 또는 객체의 움직임으로 표현 할 수 있다. 객체 분할 측면에서 볼 때 효율적인 분할을 위해서는 특징 입력 벡터의 선택이 중요한 변수로 작용한다. 본 연구에서는 정밀한 객체 분할을 위해 밝기, 질감(Texture) 정보와 같은 정지영상의 특징 입력 벡터와 움직임 벡터 같은 동영상의 특징 입력 벡터를 동시에 사용한다. 분리된 객체는 각각의 클래스를 구성하게 되고 이를 위한 클래스 분류기로서 Median Radial Basis 신경 회로망을 사용한다. 객체 분할과 움직임 예측을 위해서 확률적 방법을 통한 에너지 함수를 구하고 비용함수를 도입한다. 신경 회로망의 각 Basis 함수는 영상의 특정한 영역에서 활성화되며 객체의 분류를 위해 신경 회로망 출력으로 가중치의 합으로서 나타나게 된다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.328-331
• /
• 2000

In this paper , we propose a texture feature extraction method of reduce the massive computational time on extracting texture, features of large sized medical such as MRI, CT-scan , and an index structure, called GLTFT, to speed up the retrieval performance. For these, the original image is transformed into a compressed image by Wavelet transform , and textural features such as contrast, energy, entropy, and homogeneity of the compressed image is extracted by using GLCM(Gray Level Co-occurrence Metrix) . The proposed index structure is organized by using the textural features. The processing in compressed domain can give the solution of storage space and the reduction of computational time of feature extracting . And , by GLTFT index structure, image retrieval performance can be expected to be improved by reducing the retrieval range . Our experiment on 270 MRIs as image database shows that shows that such expectation can be got.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.976-978
• /
• 2017

포장 도로의 균열 또는 유실에 따라 발생하는 포트홀은 환경 변화에 따라 지속적으로 발생하며 이로 인한 교통사고도 지속적으로 발생한다. 포트홀 탐지를 위해 크게 3가지 방법들이 시도되고 있다. 그 중 이미지 처리를 이용한다. 포트홀은 내부에 깊이가 있으며 거친 질감을 가진다. 이러한 특성을 이용하여 포트홀을 탐지한다.