• 한국멀티미디어학회논문지
• /
• 제10권6호
• /
• pp.699-706
• /
• 2007

This article is an approach to improving the clustering of Web images by using high-level semantic features from text information relevant to Web images as well as low-level visual features of image itself. These high-level text features can be obtained from image URLs and file names, page titles, hyperlinks, and surrounding text. As a clustering algorithm, a self-organizing map (SOM) proposed by Kohonen is used. To evaluate the clustering efficiencies of SOMs, we propose a simple but effective measure indicating the accumulativeness of same class images and the perplexities of class distributions. Our approach is to advance the existing measures through defining and using new measures accumulativeness on the most superior clustering node and concentricity to evaluate clustering efficiencies of SOMs. The experimental results show that the high-level text features are more useful in SOM-based Web image clustering.

• 정보처리학회논문지B
• /
• 제13B권2호
• /
• pp.121-126
• /
• 2006

본 논문에서는 웹 이미지의 분류 효과를 높이기 위해 이미지 자체에서 추출된 저수준의 비주얼 특징뿐만 아니라 이미지와 관련된 텍스트 정보로부터 나온 고수준 시맨틱 특징들을 이용하는 분류 방법을 제안한다. 이 고수준의 텍스트 특징들은 이미지 URL, 파일명, 페이지 타이틀, 하이퍼링크 및 이미지 주변 텍스트로부터 얻어진다. 분류 엔진으로는 Kohonen의 SOM(Self Organizing Map)을 사용한다. 고수준의 텍스트 특징들과 저수준의 비주얼 특징들을 동시에 사용하는 SOM 기반의 이미지 분류에서는 10개의 카테고리로부터 수집된 200개의 테스트 이미지들이 사용되었다. 분류 성능을 평가하기 위해 간단하면서도 새로운 두 가지 척도, 즉 동일 카테고리 이미지들의 산포 정도와 집적 정도를 나타내는 각각의 척도를 정의하고 사용하였다. 실험결과, SOM기반의 웹 이미지 분류에서는 고수준의 텍스트 특징들이 보다 유용한 것임이 밝혀졌다.

• 정보처리학회논문지B
• /
• 제9B권6호
• /
• pp.759-764
• /
• 2002

HTML 페이지로 대표되는 웹 문서에서 이미지는 매우 큰 비중을 차지하고 있지만 이에 대한 분석 및 이해에 관한 연구는 활발하게 진행되지 못하고 있다. 여러 가지 웹 이미지들은 중요한 정보를 전달하기도 하지만 그렇지 않은 것들도 있다. 본 논문에서는 현재 서비스중인 인터넷 사이트의 웹 이미지들을 수집하여 기계학습(machine learning)에 기반한 분류(classification)론 통해 제거 가능한 이미지와 제거 불가능한 이미지의 두가지 클래스로 분석해 본다. 이를 위해 16개의 독특하고 풍부한 웹 이미지 특징들을 발굴하고 베이지안 기법과 결정 트리 기법을 사용하여 실험하였다. 그 결과 각각의 기법에서 87.09%, 82.72%의 F-measure 값을 얻었으며 특히, 특징 그룹의 비교 실험을 통해 본 연구에서 추가한 특징들이 매우 유용한 것임을 입증하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.885-889
• /
• 2003

The e-catalog system consists of e-catalog database. e-catalog manager. and a web server, and provides e-catalog web service by displaying e-catalog documents that contain web 3D images. product specifications and manuals. Various web contents such as the 3D images of products, which offer basic viewpoints/movement handles and function simulations, product specifications, product manuals and product features, can be integrated into e-catalog documents in XML format through image manipulation and database connection by using the e-catalog manager tool. By reducing time and cost for publication and management of an e-catalog web service, the competitiveness of companies is expected to be intensified in the perspective of e-business activities.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.213-231
• /
• 2014

Existing image search systems allow users to search images by keywords, or by example images through content-based image retrieval (CBIR). On the other hand, users might learn more relevant textual information about an image from its text captions or surrounding contexts within documents or Web pages. Without such contexts, it's difficult to extract semantic description directly from the image content. In this paper, we propose an annotation watermarking system for users to embed text descriptions, and retrieve more relevant textual information from similar images. First, tags associated with an image are converted by two-dimensional code and embedded into the image by discrete wavelet transform (DWT). Next, for images without annotations, similar images can be obtained by CBIR techniques and embedded annotations can be extracted. Specifically, we use global features such as color ratios and dominant sub-image colors for preliminary filtering. Then, local features such as Scale-Invariant Feature Transform (SIFT) descriptors are extracted for similarity matching. This design can achieve good effectiveness with reasonable processing time in practical systems. Our experimental results showed good accuracy in retrieving similar images and extracting relevant tags from similar images.

• 한국정보처리학회논문지
• /
• 제4권9호
• /
• pp.2315-2332
• /
• 1997

In this paper, we implement a content based image retrieval system for image searching by visual features from the image databases on WWW (world wide web). The image retrieval system finds the images that contain the most similar color regions after the system automatically extracts color features from the input image. We can select one of two query methods which use a full image of $4{\times}4$ 16 sketched color region. The image similarity is calculated on the histogram intersection distance and the histogram Euclidean distance. As the experimental results show that the two different query types provide the precision/recall 0.84/0.92 and 0.85/0.93 respectively, this retrieval system has been able to obtain high performance and validity.

• 정보교육학회논문지
• /
• 제15권2호
• /
• pp.219-226
• /
• 2011

웹 상에서 사용자가 원하는 정보를 효율적으로 검색하는데 도움을 주기 위하여 웹 개인화는 사용자에게 흥미있는 웹 문서들을 추출해내는데 초점을 두고 있다. 이를 실현하기 위한 주요 방법들 중 하나는 문서에 포함된 질의어, 링크 및 사용자의 선호어를 이용하는 것이다. 본 연구에서는 이들 요소 외에 사용자들이 웹문서를 선택할 때 중요하게 생각하는 문서 특성들을 설문을 통하여 조사하였다. 설문 결과 문서의 내용이 가장 중요한 특성이었으나, 일부 사용자들에게는 문서에 포함된 이미지와 가독성도 내용과 마찬가지로 중요하게 간주되었다. 이를 바탕으로 각 사용자를 위한 문서의 주요 특성들의 상대적 가중치를 프로필에 유지 관리하고, 검색 결과의 개인화에 반영하는 방안을 제시한다. 제안한 개인화 방법의 성능을 분석한 결과, 일반 검색 엔진에 비해 최대 약 2.3배의 성능 향상을 보였고, 사용자 질의어와 선호어를 모두 이용하여 검색 결과를 산출하는 방법보다 약 1.5배의 성능 향상을 나타내어 그 우수성을 입증하였다.

• Journal of Information Processing Systems
• /
• 제14권5호
• /
• pp.1195-1214
• /
• 2018

Typical search engines may not be the most efficient means of returning images in accordance with user requirements. With the help of semantic web technology, it is possible to search through images more precisely in any required domain, because the images are annotated according to a custom-built ontology. With appropriate annotations, a search can then, return images according to the context. This paper reports on the design of a tourism ontology relevant to touristic images. In particular, the image features and the meaning of the images are described using various properties, along with other types of information relevant to tourist attractions using the OWL language. The methodology used is described, commencing with building an image and tourism corpus, creating the ontology, and developing the search engine. The system was tested through a case study involving the western region of Thailand. The user can search specifying the specific class of image or they can use text-based searches. The results are ranked using weighted scores based on kinds of properties. The precision and recall of the prototype system was measured to show its efficiency. User satisfaction was also evaluated, was also performed and was found to be high.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 추계학술발표대회
• /
• pp.1468-1471
• /
• 2012

It is always a dream to recreate the experience of a particular place, the Panorama Virtual Reality has been interpreted as a kind of technology to create virtual environments and the ability to maneuver angle for and select the path of view in a dynamic scene. In this paper we examined an efficient algorithm for Image registration and stitching of captured imaged from a video stream. Two approaches are studied in this paper. First, dynamic programming is used to spot the ideal key points, match these points to merge adjacent images together, later image blending is use for smooth color transitions. In second approach, FAST and SURF detection are used to find distinct features in the images and a nearest neighbor algorithm is used to match corresponding features, estimate homography with matched key points using RANSAC. The paper also covers the automatically choosing (recognizing, comparing) images to stitching method.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제65차 동계학술대회논문집 30권1호
• /
• pp.211-213
• /
• 2022

Images in the textbooks influence the learning process. Students often see pictures before reading the text and these pictures can enhance the power of imagination of the students. The findings of some researches show that the images in textbooks can increase students' creativity. However, when learning major subjects, reading a textbook or looking at a picture alone may not be enough to understand the topics and completely realize the concepts. Studies show that viewers remember 95% of a message when watching a video than reading a text. If we can combine textbooks and videos, this teaching method is fantastic. The "TEXT + IMAGE + VIDEO (Animation)" concept could be more beneficial than ordinary ones. We tried to give our solution by using machine learning Image Classification. This paper covers the features, approaches and detailed objectives of our project. For now, we have developed the prototype of this project as a web app and it only works when accessed via smartphone. Once you have accessed the web app through your smartphone, the web app asks for access to use the camera. Suppose you bring your smartphone's camera closer to the picture in the textbook. It will then display the video related to the photo below.