• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.301-307
• /
• 2018

The most of the IR focus on the method for searching the document, so the keyword-based IR system is not able to reflect the feature information of the image. In order to overcome these limitations, we have developed a system that can search similar images based on the vector information of images, and it can search for similar images based on sketches. The proposed system uses the GAN to up sample the sketch to the image level, convert the image to the vector through the CNN, and then retrieve the similar image using the vector space model. The model was learned using fashion image and the image retrieval system was developed. As a result, the result is showed meaningful performance.

• Convergence Security Journal
• /
• v.18 no.3
• /
• pp.53-59
• /
• 2018

In this paper, we propose a hierarchical image classification scheme for efficient object image classification. In the non-hierarchical image classification, which classifies the existing whole images at one time, it showed that objects with relatively similar shapes are not recognized efficiently. Therefore, in this paper, we introduce the image classification method in the hierarchical structure which attempts to classify object images hierarchically. Also, we introduce to the efficient class structure and algorithms considering the scalability that can occur when a deep learning image classification is applied to an actual system. Such a scheme makes it possible to classify images with a higher degree of confidence in object images having relatively similar shapes.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.05a
• /
• pp.295-299
• /
• 2002

본 연구에서는 피륙의 물리화학적 특성에 의해 결정되는 촉감, 태 이외에도 색채, 무의 등 여러 요소들의 영향을 받아 복합적으로 표현되는 의류소재의 총체적인 개념인 의류소재 이미지는 어떤 것들이 있으며 이러한 이미지들은 어떻게 분류될 수 있는지를 알아보기 위하여 의류소재 이미지의 평가를 위한 축을 개발해 보았다. 1995년부터 2000년까지의 Texjournal과 인터패션플래닝에서 발간되는 98/99FW부터 0255까지 트렌드 북에서 소재를 설명하는 형용사를 조사하여 유사한 형용사를 통합 처리하여 87개의 형용사를 최종 추출하여 형용사쌍을 만들고 소재 자극 없이 형용사쌍이 주는 소재이미지만을 가지고 쌍비교법을 통해 유사성을 7점 척도로 표시하도록 하였다. 얻어진 결과를 다차원척도법을 이용하여 분석하여 87개의 형용사의 평가차원을 살펴보았다. 의류소재 이미지를 평가하는 축을 다차원 척도법을 이용하여 개발한 결과 '남성적-여성적', '새로운-낡은 듯한', '캐주얼-클래식', '모호한-정돈된'의 4가지 차원의 8개축이 개발되었다.

• Journal of the Korean association of regional geographers
• /
• v.21 no.3
• /
• pp.569-582
• /
• 2015

This study deals with six spa touristy places to analyze the similarity in image and selection factor recognition through multidimensional scaling method. The result is as following. First, as a result of analysis in the similarity in Image of the 6 touristy Spa places, each "Asan and Onyang" and "Suanbo and Ducksan" form different similar image groups. However, Yoosung does not share the similarity in Image that other Spa places own. Second, as a result of analysis of selection factors in the six touristy spa places, it is found out that there is no big difference in selection factors such as 'spa facility', 'a fee to use', and 'quality of service' in the six spa places. Yet, Onyang, Yoosung, Ducksan, and Suanbo spa reflect high selection factor as 'a recognized spa place' different from Asan and Dogo where the reflection of selection factor is low. Onyang, Yoosung, and Dogo regions reflect high selection factor as a 'Touristy destination' while Asan reflects low selection factor.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.591-598
• /
• 2021

It's possible to get the word-vector by the statistical SVD or deep-learning CBOW and LSTM methods and theses ones learn the contexts of forward/backward words or the sequence of following words. It's used to analyze the poems by Ki Hyung-do with similar words recommended by the word-vector showing the core images of the poetry. It seems at first sight that the words don't go well with the images but they express the similar style described by the reference words once you look close the contexts of the specific poems. The word-vector can analogize the words having the same relations with the ones between the representative words for the core images of the poems. Therefore you can analyze the poems in depth and in variety with the similarity and analogy operations by the word-vector estimated with the statistical SVD or deep-learning CBOW and LSTM methods.

• Journal of KIISE:Databases
• /
• v.30 no.2
• /
• pp.145-156
• /
• 2003

Most of the content-based image retrieval systems focuses on similarity-based retrieval of natural picture images by utilizing color. shape, and texture features. For the neuroscience image databases, we found that retrieving similar images based on global average features is meaningless to pathological researchers. To realize the practical content-based retrieval on images in neuroscience databases, it is essential to represent internal contents or semantics of images in detail. In this paper, we present how to represent image contents and their related concepts to support more useful retrieval on such images. We also describe the operational semantics to support these advanced retrievals by using object-oriented message path expressions. Our schemes are flexible and extensible, enabling users to incrementally add more semantics on image contents for more enhanced content searching.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.816-822
• /
• 2016

Content-Based image retrieval is a method to search by image features such as local color, texture, and other image content information, which is different from conventional tag or labeled text-based searching. In real life data, the number of images having tags or labels is relatively small, so it is hard to search the relevant images with text-based approach. Existing image search method only based on image feature similarity has limited performance and does not ensure that the results are what the user expected. In this study, we propose and validate a machine learning based approach to improve the performance of the image search engine. We note that when users search relevant images with a query image, they would expect the retrieved images belong to the same category as that of the query. Image classification method is combined with the traditional image feature similarity method. The proposed method is extensively validated on a public PASCAL VOC dataset consisting of 11,530 images from 20 categories.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.509-516
• /
• 2004

Semantic interpretation of image is incomplete without some mechanism for understanding semantic content that is not directly visible. For this reason, human assisted content-annotation through natural language is an attachment of textual description to image. However, keyword-based retrieval is in the level of syntactic pattern matching. In other words, dissimilarity computation among terms is usually done by using string matching not concept matching. In this paper, we propose a method for computerized semantic similarity calculation In WordNet space. We consider the edge, depth, link type and density as well as existence of common ancestors. Also, we have introduced method that applied similarity measurement on semantic image retrieval. To combine wi#h the low level features, we use the spatial color distribution model. When tested on a image set of Microsoft's 'Design Gallery Line', proposed method outperforms other approach.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.489-492
• /
• 2007

산업재산권중 하나인 상표에 대한 효율적인 이미지 검색은 상표도용 및 이로 인한 분쟁을 방지할 수 있다. 이를 위해서는 효율적인 내용기반 유사이미지 검색이 필요하다. 본 논문에서는 상표이미지검색에 있어 가시적인 특성(visual feature)을 그레이 히스토그램을 통해서 상표이미지의 특성값을 추출하여 이를 입력패턴으로 SOM(Self-Organizing Map)알고리즘을 적용한 내용기반 유사이미지 검색시스템을 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.454-456
• /
• 2002

압축 방법에는 크게 손실(lossy)압축과 무손실(lossless)압축으로 나눌 수 있다. 그 중 프랙탈 이미지 압축은 lossy 압축의 한가지 방법으로서 개별적인 화소들에 대한 자료를 저장하기보다는, 영상 생성을 위한 명령이나 방식을 저장하는 방법이다. 특히 이미지의 내에 자기유사성(self-similarity)과 중복성(Redundancy)을 이용하여 관련성을 발견하고 수학적인 공식으로 표현하려는 방식이다. 그러나 이미지를 Domain과 Range로 블록화 한 후 유사한 이미지를 찾아내는 데 걸리는 시간이 상당히 길다. 여기에서는 Domain과 Range의 외곽선의 기울기의 부호를 이용하여 블록을 16가지로 클래스화 하여서, 전체의 Domain 블록을 탐색하는 데 걸리는 시간을 줄이고자 하였다. 전체 탐색을 하는 경우보다 10배 이상의 속도향상을 보였고, 이미지에 따라서는 PSNR 값의 손실도 없음을 보였다.