• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2000년도 춘계공동학술대회 논문집
• /
• pp.397-400
• /
• 2000

This paper provides a product data representation, a data schema and related operations, for the management of engineering changes. The computer Interpretable format of the representation enables itself to be realized through databases and their applications to a component of a product data management system. Supporting general operations for the engineering changes, it resolves problems of the existing information systems in the nested engineering changes and the simultaneous change application to multiple products. To show the feasibility, a prototype system is implemented based on the representation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.212-217
• /
• 1992

In this paper, a two ports machine(TPM) model for discrete event dynamic systems(DEDS) is proposed. The proposed model is a finite state machine which has two inputs and two outputs. Inputs and outputs have two components, events and informations. TPM is different from other state machine models, since TPM has symmetric input and output. This symmetry enables the block diagram representation of the DEDS with TPM blocks, summing points, multiplying points, branch points, and connections. The graphical representation of DEDS is analogous to that of control system theory. TPM has a matrix representation of its transition and information map. This matrix representation simplifies the analysis of the DEDS.

• Journal of Computing Science and Engineering
• /
• 제12권1호
• /
• pp.1-11
• /
• 2018

Human activities recognition is a challenging task due to its complexity of human movements and the variety performed by different subjects for the same action. This paper presents a recognition algorithm by using skeleton information generated from depth maps. Concatenating motion features and temporal constraint feature produces feature vector. Reducing dictionary scale proposes an improved fast classifier based on sparse representation. The developed method is shown to be effective by recognizing different activities on the UTD-MHAD dataset. Comparison results indicate superior performance of our method over some existing methods.

• Journal of applied mathematics & informatics
• /
• 제11권1_2호
• /
• pp.1-57
• /
• 2003

Vector fields in three-space admit bundles of internal variables such as a Heisenberg algebra bundle. Information transmission along field lines of vector fields is described by a wave linked to the Schrodinger representation in the realm of time-frequency analysis. The preservation of local information causes geometric optics and a quantization scheme. A natural circle bundle models quantum information visualized by holographic methods. Features of this setting are applied to magnetic resonance imaging.

• 한국정보전자통신기술학회논문지
• /
• 제10권2호
• /
• pp.147-153
• /
• 2017

텍스쳐를 효과적으로 표현하는 것은 컴퓨터 비전 분야에서 매우 중요한 과정이다. 효과적인 텍스쳐 표현을 통해 텍스쳐 분류나 텍스쳐 분할 등의 처리 성능을 향상시킬 수 있다. 가버 필터는 텍스쳐 표현을 위해 오랫동안 사용된 다해상도 스케일 기반의 방법이다. 가버 필터는 텍스쳐 분류나 분할에 높은 성능을 제공한다. 그러나 처리 과정의 연산량으로 인해 처리 시간이 매우 많이 소요되어 실제 응용에서는 사용하기 어려운 문제가 있다. 본 논문에서는 가버 필터와 유사하게 다해상도 스케일 기반으로 텍스쳐를 표현할 수 있는 새로운 특징 표현 방법을 제안한다. 제안한 방법은 주파수 공간에서 방향과 스케일을 기반으로 다해상도 스케일 기반으로 텍스쳐를 표현한다. 2가지 실험 영상 집합에 대해 분류 실험을 수행하여 제안한 특징의 유용성을 확인하였다. 가버 필터와 유사한 분류 성능을 제공하면서 처리 속도는 가버 필터의 5%이하로 줄일 수 있는 것을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2390-2406
• /
• 2022

Scene text recognition has important application value and attracted the interest of plenty of researchers. At present, many methods have achieved good results, but most of the existing approaches attempt to improve the performance of scene text recognition from the image level. They have a good effect on reading regular scene texts. However, there are still many obstacles to recognizing text on low-quality images such as curved, occlusion, and blur. This exacerbates the difficulty of feature extraction because the image quality is uneven. In addition, the results of model testing are highly dependent on training data, so there is still room for improvement in scene text recognition methods. In this work, we present a natural scene text recognizer to improve the recognition performance from the feature level, which contains feature representation and feature enhancement. In terms of feature representation, we propose an efficient feature extractor combined with Representative Batch Normalization and ResNet. It reduces the dependence of the model on training data and improves the feature representation ability of different instances. In terms of feature enhancement, we use a feature enhancement network to expand the receptive field of feature maps, so that feature maps contain rich feature information. Enhanced feature representation capability helps to improve the recognition performance of the model. We conducted experiments on 7 benchmarks, which shows that this method is highly competitive in recognizing both regular and irregular texts. The method achieved top1 recognition accuracy on four benchmarks of IC03, IC13, IC15, and SVTP.

• 영어어문교육
• /
• 제9권spc호
• /
• pp.149-165
• /
• 2003

This paper is aimed at the investigation of pragmatic contributions to the identification of explicatures. An explicature is the result of fleshing out the semantic representation of an utterance. The basic assumption of the paper is that the process of the developing the semantic representation into an explicature depends heavily on contextual information. Therefore, we are concerned with the way in which hearers use contextual information to flesh rut or develop the semantic representation of an utterance. The identification of explicatures includes both the recovery of the proposition expressed and the recovery of what we called higher-level explicatures. There are three subtasks involved in the recovery of the proposition expressed: reference assignment disambiguation and enrichment On the other hand, there are two subtasks involved in the recovery of higher-level explicatures: attitudes and speech acts.

• 한국정보전자통신기술학회논문지
• /
• 제3권3호
• /
• pp.39-44
• /
• 2010

본 연구에서는 벡터 변환 기법을 이용하여 연령변화에 따른 얼굴변환 기법을 제안 하였다. 제안한 기법은 주관성을 배제하고 일관성과 신뢰성을 높이기 위하여 모핑과 벡터 모델을 적용하였다. 또한, 형태에 따른 질감변화 요인을 정의하고 내부 외부 환경 변화에 대한 형태 변환 요소를 고려하였다. 제안한 방법의 타당성을 확인하기 위하여 실험결과를 정성적인 방법으로 유사성 평가를 수행하였는 바, 14세부터 60세까지의 얼굴 변환 결과가 매우 유사하게 평가 되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2109-2123
• /
• 2017

This paper presents a super-resolution reconstruction method based on sparse representation for two-dimensional bar code images. Considering the features of two-dimensional bar code images, Kirsch and LBP (local binary pattern) operators are used to extract the edge gradient and texture features. Feature extraction is constituted based on these two features and additional two second-order derivatives. By joint dictionary learning of the low-resolution and high-resolution image patch pairs, the sparse representation of corresponding patches is the same. In addition, the global constraint is exerted on the initial estimation of high-resolution image which makes the reconstructed result closer to the real one. The experimental results demonstrate the effectiveness of the proposed algorithm for two-dimensional bar code images by comparing with other reconstruction algorithms.

• 한국언어정보학회지:언어와정보
• /
• 제8권2호
• /
• pp.1-25
• /
• 2004

This paper examines two different approaches to resolving a theoretical problem which the bottom-up approach version of Discourse Representation Theory of Kamp et al. (2003) faces in dealing with anaphoric relations between pronouns and their potential antecedents in conditional sentences where consequent clauses precede their corresponding conditional clauses. In one of the approaches, every element is processed in the order of occurrence and conditional operators in a non-sentence-initial position cause the ongoing DR to split in two with the same index. The definition of accessibility is accordingly modified so that the right DR can be accessible from the left DR. In the other approach, a different type of discourse representation structure, K ${\Leftarrow}$ K, is introduced, which allows us to resolve the target problem without modifying accessibility proposed in Kamp et al. (2003). Compatibility of these two approaches with the bottom-up version of DRT is evaluated by examining their applicability to the analysis of quantified sentences where pronominal expressions precede generalized quantifiers.