• 한국정보과학회논문지:소프트웨어및응용
• /
• 제26권10호
• /
• pp.1204-1218
• /
• 1999

문서영상 검색을 위한 디지털도서관의 대부분은 논문제목과/또는 논문요약으로부터 만들어진 색인에 근거한 제한적인 검색기능을 제공하고 있다. 본 논문에서는 영문 문서영상전체에 대한 검색을 위한 단어 영상 형태 특징기반의 단어검색시스템을 제안한다. 본 논문에서는 검색의 효율성과 정확도를 높이기 위해 1) 기존의 단어검색시스템에서 사용된 특징들을 조합하여 사용하며, 2) 특징의 개수 및 위치뿐만 아니라 특징들의 순서를 포함하여 매칭하는 방법을 사용하며, 3) 특징비교에 의해 검색결과를 얻은 후에 여과목적으로 문자인식을 부분적으로 적용하는 2단계의 검색방법을 사용한다. 제안된 시스템의 동작은 다음과 같다. 문서 영상이 주어지면, 문서 영상 구조가 분석되고 단어 영역들의 조합으로 분할된다. 단어 영상의 특징들이 추출되어 저장된다. 사용자의 텍스트 질의가 주어지면 이에 대응되는 단어 영상이 만들어지며 이로부터 영상특징이 추출된다. 이 참조 특징과 저장된 특징들과 비교하여 유사한 단어를 검색하게 된다. 제안된 시스템은 IBM-PC를 이용한 웹 환경에서 구축되었으며, 영문 문서영상을 이용하여 실험이 수행되었다. 실험결과는 본 논문에서 제안하는 방법들의 유효성을 보여주고 있다. Abstract Most existing digital libraries for document image retrieval provide a limited retrieval service due to their indexing from document titles and/or the content of document abstracts. This paper proposes a word spotting system for full English document image retrieval based on word image shape features. In order to improve not only the efficiency but also the precision of a retrieval system, we develop the system by 1) using a combination of the holistic features which have been used in the existing word spotting systems, 2) performing image matching by comparing the order of features in a word in addition to the number of features and their positions, and 3) adopting 2 stage retrieval strategies by obtaining retrieval results by image feature matching and applying OCR(Optical Charater Recognition) partly to the results for filtering purpose. The proposed system operates as follows: given a document image, its structure is analyzed and is segmented into a set of word regions. Then, word shape features are extracted and stored. Given a user's query with text, features are extracted after its corresponding word image is generated. This reference model is compared with the stored features to find out similar words. The proposed system is implemented with IBM-PC in a web environment and its experiments are performed with English document images. Experimental results show the effectiveness of the proposed methods.

• 한국컴퓨터정보학회논문지
• /
• 제11권5호
• /
• pp.69-74
• /
• 2006

최근 멀티미디어 내용기반 검색 기술의 발달로 음악 정보 검색 기술 중 하나인 오디오 특징을 이용한 뮤지션 검색에 대한 관심이 증대되고 있다. 그러나 이와 관련한 음악 데이타베이스의 인덱싱 기법에 대한 연구는 부족한 실정이다. 본 논문에서는 시계열 패턴 인덱스 화일의 공간 분할 방법을 이용하여 오디오 특징 데이터를 사용한 뮤지션 검색 기법을 제시한다. 뮤지션 탐색을 위하여 오디오의 특징을 사용하며, 유사한 후보 뮤지션의 곡을 탐색하기 위한 인덱싱 기법으로 시계열 패턴 인덱스 화일을 사용한다. 실험 결과, 윤번 공간 분할 방법을 사용한 시계열 패턴 인덱스 화일이 뮤지션 검색에 있어서 효율적임을 보였다.

• 한국통신학회논문지
• /
• 제27권3A호
• /
• pp.258-267
• /
• 2002

본 논문에서는 저자 등이 질감특징으로 제안한 바 있는 BDIP(block difference of inverse probabilities) 모멘트 특징과 새로이 질감특징으로 제안하는 BVLC(block variation of local correlation coefficient) 모멘트 특징을 기존의 웨이브렛 모멘트 질감특징과 융합하여 칼라영상을 대상으로 검색하는 내용기반 검색법을 제시하였다. 효율적인 융합을 위해 각 특징벡터들에 대한 가중치는 전체 DB에서 각 특징벡터의 성분이 가지는 표준편차와 각 특징벡터가 가지는 차원과의 곱의 역수로 하였다. 시험영상으로는 Corel Draw Photo DB와 Vistex 질감영상 DB를 사용하였다. 실험결과, 제안한 검색기법은 일반영상뿐만 아니라 질감영상에서도 웨이브렛 모멘트 특징보다 7%정도 성능이 향상됨을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.763-765
• /
• 2005

In the area of remote sensing, an immense number of images are continuously generated by various remote sensing systems. These images must then be managed by a database system efficient storage and retrieval. There are many types of image database systems, among which the content-based image retrieval (CBIR) system is the most advanced. CBIR utilizes the metadata of images including the feature data for indexing and searching images. Therefore, the performance of image retrieval is significantly affected by the storage method of the image metadata. There are many features of images such as color, texture, and shape. We mainly consider the shape feature because shape can be identified in any remote sensing while color does not always necessarily appear in some remote sensing. In this paper, we propose a metadata representation and storage method for image search based on shape features. First, we extend MPEG-7 to describe the shape features which are not defined in the MPEG-7 standard. Second, we design a storage schema for storing images and their metadata in a relational database system. Then, we propose an efficient storage method for managing the shape feature data using a Wavelet technique. Finally, we provide the performance results of our proposed storage method.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제8권3호
• /
• pp.303-317
• /
• 2002

In this paper, we design and implement E-COIRS enabling users to query with concepts and image features used for further refining the concepts. For example, E-COIRS supports the query "retrieve images containing black home appliance to north of reception set. "The query includes two types of concepts: IS-A and composite. "home appliance"is an IS-A concept, and "reception set" is a composite concept. For evaluating such a query. E-COIRS includes three important components: a visual image indexer, thesauri and a query processor. Each pair of objects in an mage captured by the visual image indexer is converted into a triple. The triple consists of the two object identifiers (oids) and their spatial relationship. All the features of an object is referenced by its old. A composite concept is detected by the triple thesaurus and IS-A concept is recolonized by the fuzzy term thesaurus. The query processor obtains an image set by matching each triple in a user with an inverted file and CS-Tree. To support efficient storage use and fast retrieval on high-dimensional feature vectors, E-COIRS uses Cell-based Signature tree(CS-Tree). E-COIRS is a more advanced content-based image retrieval system than other systems which support only concepts or image features.

• Journal of Information Processing Systems
• /
• 제16권3호
• /
• pp.663-676
• /
• 2020

Plant leaf classification is a significant application of image processing techniques in modern agriculture. In this paper, a multi-granular angle description method is proposed for plant leaf classification and retrieval. The proposed method can describe leaf information from coarse to fine using multi-granular angle features. In the proposed method, each leaf contour is partitioned first with equal arc length under different granularities. And then three kinds of angle features are derived under each granular partition of leaf contour: angle value, angle histogram, and angular ternary pattern. These multi-granular angle features can capture both local and globe information of the leaf contour, and make a comprehensive description. In leaf matching stage, the simple city block metric is used to compute the dissimilarity of each pair of leaf under different granularities. And the matching scores at different granularities are fused based on quotient space theory to obtain the final leaf similarity measurement. Plant leaf classification and retrieval experiments are conducted on two challenging leaf image databases: Swedish leaf database and Flavia leaf database. The experimental results and the comparison with state-of-the-art methods indicate that proposed method has promising classification and retrieval performance.

• ETRI Journal
• /
• 제29권2호
• /
• pp.246-248
• /
• 2007

Query-by-example (QBE) is a well-known method for image retrieval. In reality, however, an example image to be used for the query is rarely available. Therefore, it is often necessary to find a good example image to be used for the query before applying the QBE method. Query-by-layout (QBL) is our proposal for that purpose. In particular, we make use of the visual descriptors such as the edge histogram descriptor (EHD) and the color layout descriptor (CLD) in MPEG-7. Since image features of the CLD and the EHD can be localized in terms of a$4{\times}4$ sub-image, we can specify image features such as color and edge distribution on each sub-image separately for image retrieval without a query image. Experimental results show that the proposed query method can be used to retrieve a good image as a starting point for further QBE-based image retrieval.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.183-186
• /
• 2001

In this paper, we first propose new texture features, BVLC (block variation of local correlation coefficients) moments, for content-based image retrieval (CBIR) and then present an image retrieval method based on the fusion of BDIP and BVLC moments. BDIP uses the local probabilities in image blocks to extract valley and edges well. BVLC uses the variations of local correlation coefficients in images blocks to measure texture smoothness well. In order not to be affected with the movement, rotation, and size of an object, the first and second moments of BDIP and BVLC are used for CBIR. Corel DB and Vistex DB are used to evaluate the performance of the proposed retrieval method. Experimental results show that the presented retrieval method yields average 12% better performance than the method using only BDIP or BVLC moments and average 13% better performance than the method using wavelet moments.

• 대한전자공학회논문지SP
• /
• 제40권1호
• /
• pp.20-27
• /
• 2003

본 논문에서는 사용자가 질의를 원하는 물체 영역을 선택하면 유사 물체를 영상 데이터베이스 내에서 검색할 수 있는 내용기반 영상검색 시스템을 구현하였다. 질의영상은 색상성분과 그레이성분으로 나누어져 웨블릿 변환되고 색상성분에서는 컬러 오토코릴로그램과 분산으로 색상특성을 추출한다. 그리고 그레이성분에서는 오토코릴로그램과 GLCM을 통해 질감특성을 추출한다. 이렇게 구한 2개 성분에서의 특성들을 이용하여 데이터베이스내의 영상들과 각각 유사도를 비교하여 검색하게 된다. 이때 각 유사도에 가중치를 적용하였다. 한 가지 성분보다 두 가지 성분에서 특성을 구하여 각각의 단점을 보완하였고 실험 결과에서도 소환성(recall) 및 정확성(precision)이 향상됨을 볼 수 있었다 또한 가중치를 적용함으로써 검색 효율이 개선되었다. 그리고 데이터베이스내 영상들의 여러 특성을 특성 라이브러리내에 자동 색인화 시킴으로써 고속의 영상 검색이 가능하였다.