• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권9호
• /
• pp.676-683
• /
• 2002

XML(extensible Markup Language)문서가 웹 문서의 표준으로 자리 매김 할 수 있는 가장 큰 성공요인은 사용자가 문서 타입을 기술할 수 있는 유연성(flexibility)이다. 그러나 XML의 유연성으로 야기되는 문제점은 동일한 의미를 표현하기 위해 XML문서 작성자마다 서로 다른 태그명과 구조를 사용한다는 점이다. 즉 서로 다른 태그 집합, 요소(element), 속성(attribute)에 대한 서로 다른 이름 또는 다른 문서 구조로 인해 다른 태그로 표현된 문서는 서로 다른 부류의 문서로 간주되기 쉽다. 따라서 본 논문은 XML태그에 내재된 의미 정보(semantic information)와 구조 정보(structured information)를 추출하여 의미적으로 최대한 유사한 동의어로 확장하고, XML문서의 확장된 태그간의 의미적 유사도를 비교 분석할 수 있는 개념 기반의 태그 패턴 매처(Tag Pattern Matcher)를 설계 구현하였다. 두 XML문서의 태그간의 의미적 유사도에 가중치를 부여하여 기존의 비구조적인(semi-structured) 문서를 위한 벡터 스페이스 모델(vector space model)을 확장함으로써 두 XML문서가 유사한지를 파악할 수 있다.

• 정보관리학회지
• /
• 제22권3호
• /
• pp.261-287
• /
• 2005

이 논문의 목적은 SVM(지지벡터기계) 분류기의 성능을 문헌간 유사도를 이용해서 향상시키는 것이다. SVM은 효과적인 기계학습 시스템으로서 최고 수준의 문헌자동분류 기술로 인정받고 있다. 이 연구에서는 문헌 벡터 자질 표현에 기반한 SVM 문헌자동분류를 제안하였다. 제안한 방식은 분류 자질로 색인어 대신 문헌 벡터를, 자질 값으로 가중치 대신 벡터유사도를 사용한다. 제안한 방식에 대한 실험 결과, SVM 분류기의 성능을 향상시킬 수 있었다. 실행 효율 향상을 위해서 문헌 벡터 자질 선정 방안과 범주 센트로이드 벡터를 사용하는 방안을 제안하였다. 실험 결과 소규모의 벡터 자질 집합만으로도 색인어 자질을 사용하는 기존 방식보다 나은 성능을 얻을 수 있었다.

• Journal of Microbiology
• /
• 제44권5호
• /
• pp.515-522
• /
• 2006

A cDNA library of Ganoderma lucidum has been constructed using a Zap Express cloning vector. A glyceraldehyde-3-phosphate dehydrogenase gene (gpd) was isolated from this library by hybridization of the recombinant phage clones with a gpd-specific gene probe generated by PCR. By comparison of the cDNA and the genomic DNA sequences, it was found that the complete nucleotide sequence encodes a putative polypeptide chain of 338 amino acids interrupted by 6 introns. The predicted amino acid sequence of this gene shows a high degree of sequence similarity to the GPD proteins from yeast and filamentous fungi. The promoter region contains a CT-rich stretch, two CAAT boxes, and a consensus TATA box. The possibility of using the gpd promoter in the construction of new transformation vectors is discussed.

• 한국멀티미디어학회논문지
• /
• 제17권8호
• /
• pp.937-945
• /
• 2014

Multi-modal biometric system can use another biometric trait in the case of having deficiency at a biometric trait. It also has an advantage of improving the performance of personal identification by using multiple biometric traits, so studies on new biometric traits have continuously been performed. The inner face of finger is a relatively new biometric trait. It has two major features of knuckle lines and wrinkles, which can be used as discriminative features. This paper proposes a finger identification method based on displacement vector to effectively process some variation appeared in contactless hand image. At first, the proposed method produces displacement vectors, which are made by connecting corresponding points acquired by matching each pair of local block. It then recognize finger by measuring the similarity among all the detected displacement vectors. The experimental results using pubic CASIA hand image database show that the proposed method may be effectively applied to personal identification.

• Journal of information and communication convergence engineering
• /
• 제9권6호
• /
• pp.637-640
• /
• 2011

The hybrid neural networks have characteristics such as fast learning times, generality, and simplicity, and are mainly used to classify learning data and to model non-linear systems. The middle layer of a hybrid neural network clusters the learning vectors by grouping homogenous vectors in the same cluster. In the clustering procedure, the homogeneity between learning vectors is represented as the distance between the vectors. Therefore, if the distances between a learning vector and all vectors in a cluster are smaller than a given constant radius, the learning vector is added to the cluster. However, the usage of a constant radius in clustering is the primary source of errors and therefore decreases the recognition success rate. To improve the recognition success rate, we proposed the enhanced hybrid network that organizes the middle layer effectively by using the enhanced ART1 network adjusting the vigilance parameter dynamically according to the similarity between patterns. The results of experiments on a large number of calling card images showed that the proposed algorithm greatly improves the character extraction and recognition compared with conventional recognition algorithms.

• 전자공학회논문지B
• /
• 제29B권4호
• /
• pp.48-57
• /
• 1992

This paper addresses the estimation of the shift vector from aerial image sequences. The conventional feature-based and area-based matching methods are simulated for determining the suitable image registration scheme. Computer simulations show that the feature-based matching schemes based on the co-occurrence matrix, autoregressive model, and edge information do not give a reliable matching for aerial image sequences which do not have a suitable statistical model or significant features. In area-based matching methods we try various similarity functions for a matching measure and discuss the factors determining the matching accuracy. To reduce the estimation error of the shift vector we propose the reference window selection scheme. We also discuss the performance of the proposed algorithm based on the simulation results.

• 전자공학회논문지B
• /
• 제31B권3호
• /
• pp.91-102
• /
• 1994

For the analysis of textured image, it requires large storage space and computation time to calculate the matrix features such as SGLDM(Spatial Gray Level Dependence Matrix). NGLDM(Neighboring Gray Level Dependence Matrix). NSGLDM(Neighboring Spatial Gray Level Dependence Matrix) and GLRLM(Gray Level Run Length Matrix). In spite of a large amount of information that each matrix contains, a set of several correlated scalar features calculated from the matrix is not sufficient to approximate it. In this paper, we propose a new classifier for textured images based on these matrices in which the projected vectors of each matrix on the meaningful directions are used as features. In the proposed method, an unknown image is classified to the class of a known image that gives the maximum similarity between the projected model vector from the known image and the vector from the unknown image. In the experiment to classify images of agricultural products, the proposed method shows good performance as much as 85-95% of correct classification ratio.

• 통합자연과학논문집
• /
• 제12권4호
• /
• pp.122-126
• /
• 2019

In this paper, we propose a simple and efficient retrieval technique using the feature value of the corner region, which is one of the shape information attributes of images. The proposed algorithm extracts the edges and corner points of the image and rearranges the feature values of the corner regions doubly, and then measures the similarity with the image in the database using the correlation of these feature values as the feature vector. The proposed algorithm is confirmed to be more robust to rotation and size change than the conventional image retrieval method using the corner point.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.401-403
• /
• 2019

In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.

• 대한전자공학회논문지
• /
• 제24권1호
• /
• pp.35-45
• /
• 1987

For the registration problem in which the matching of two images is made, a new algorithm using an 1-D LPC model was proposed. The proposed algorithm employed LPC coefficients as feature vector of an image. The similarity of two images was measured using an LPC distance, proposed by Itakura, between each image's feature vector. The comparision of performance with normalized correlation method and template matching method was made by a computer simulation with several real images. The results of simulation showed that the proposed algorithm was more robust to image intensity variation and computationall efficient.