• International Journal of CAD/CAM
• /
• 제3권1_2호
• /
• pp.67-75
• /
• 2003

Viewpoint-dependent feature-based modelling in computer-aided design is developed for the purposes of supporting engineering design representation and automation. The approach of this paper uses a combination of a multi-level modelling approach. This has two stages of mapping between models, and the multi-level model approach is implemented in three-level architecture. Top of this level is a feature-based description for each viewpoint, comprising a combination of form features and other features such as loads and constraints for analysis. The middle level is an executable representation of the feature model. The bottom of this multi-level modelling is a evaluation of a feature-based CAD model obtained by executable feature representations defined in the middle level. The mappings involved in the system comprise firstly, mapping between the top level feature representations associated with different viewpoints, for example for the geometric simplification and addition of boundary conditions associated with moving from a design model to an analysis model, and secondly mapping between the top level and the middle level representations in which the feature model is transformed into the executable representation. Because an executable representation is used as the intermediate layer, the low level evaluation can be active. The example will be implemented with an analysis model which is evaluated and for which results are output. This multi-level modelling approach will be investigated within the framework aimed for the design automation with a feature-based model.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1999년도 가을 학술발표논문집 Vol.26 No.2 (1)
• /
• pp.12-14
• /
• 1999

오늘날 멀티미디어 및 인터넷 서비스가 눈에 띄게 증가하면서 다양한 응용분야에서의 동영상 데이터 활용을 급증하였고 이에 사용자가 원하는 동영상 데이터를 빠르고 정확하게 검색하기 위한 내용기반 검색기법이 필수적이다. 본 논문은 high-level features와 더불어 동영상의 고유 내용 속성에 속하는 low-level features를 자동 일반화(generalization)하여 다단계 관리하고 features에 대한 가중치 적용질의를 제공함으로써 기존 내용기반 검색 연구와는 뚜렷한 차별성을 갖는다. 또한 low-level features와 high-level features간의 자동변환(translation)을 가능하게 함으로써 동영상 데이터베이스의 사용자 접근 효율을 한단계 높이고 보다 의미구조화된 동영상 관리 및 내용기반 검색을 지원한다.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1293-1308
• /
• 2020

In fine-tuning-based transfer learning, the size of the dataset may affect learning accuracy. When a dataset scale is small, fine-tuning-based transfer-learning methods use high computing costs, similar to a large-scale dataset. We propose a mid-level feature extractor that retrains only the mid-level convolutional layers, resulting in increased efficiency and reduced computing costs. This mid-level feature extractor is likely to provide an effective alternative in training a small-scale medical image dataset. The performance of the mid-level feature extractor is compared with the performance of low- and high-level feature extractors, as well as the fine-tuning method. First, the mid-level feature extractor takes a shorter time to converge than other methods do. Second, it shows good accuracy in validation loss evaluation. Third, it obtains an area under the ROC curve (AUC) of 0.87 in an untrained test dataset that is very different from the training dataset. Fourth, it extracts more clear feature maps about shape and part of the chest in the X-ray than fine-tuning method.

• Interaction and multiscale mechanics
• /
• 제3권4호
• /
• pp.373-387
• /
• 2010

This study is intended to assess low frequency sound radiated from a viaduct under normal traffic. The bridge comprises steel box girders and wide cantilever decks on which vehicles pass. The low frequency sound and the acceleration response of the bridge under normal traffic are measured to investigate how bridge vibrations affect the low frequency sound observed near the bridge. Observations demonstrate that strong relationships exist between frequency characteristic of bridge's acceleration response and the sound pressure level of low frequency sound. A noteworthy point is that the dynamic feature of the sound pressure level is mostly affected by dynamic feature of the span locating near the observation point.

• 한국정보과학회논문지:데이타베이스
• /
• 제33권4호
• /
• pp.372-383
• /
• 2006

이미지 데이타베이스 분야에 대한 다양한 기법들 가운데, 내용 기반 영상 검색 기법 (Content Based Image Retrieval)은 대용량의 영상을 효율적으로 검색하고 탐색할 수 있도록 한다. 기존의 내용 기반 영상 검색 시스템은 사용자가 입력한 질의 이미지에서 낮은 레벨의 특성 (low-level feature)을 추출하고 그에 기반하여 데이타베이스로부터 유사한 영상을 검색한다. 하지만 컴퓨터에서 사용하는 낮은 레벨의 특성은 실제 인간이 영상을 인식하는 방법과 다르게 영상을 인식한다는 단점이 있다. 이러한 단점을 보완하기 위하여 각 특성에 대한 가중치를 적합성 피드백 (relevance feedback)을 통하여 재조정하는 기법이 개발되었다. 기존의 특성 가중치 조정 (feature re-weighting) 기법은 모든 영상에 대하여 특성은 항상 고정된 길이의 벡터 데이타로 표현된다고 가정한다, 이러한 가정을 전제로 하여 기존의 기법은 특성 표현 (feature representation)의 각 부분을 n 차원 공간의 각 축에 할당한다. 하지만 특성 표현 기법의 발전에 따라 가변적인 길이의 벡터로 표현되는 특성이 출현하였으며 이로 인하여 기존의 제한된 길이의 벡터로 표현되는 특성 표현에 기반한 특성 가중치 조정 기법의 유효성은 감소하게 되었다. 본 논문에서는 가변적인 크기의 벡터로 표현되는 특성에 대해서도 특성 가중치를 효과적으로 조정할 수 있는 기법을 제안한다. 본 기법은 특성에 기반하여 계산된 질의 영상과 데이타베이스 내부의 영상간의 거리와 양방향 신뢰구간을 이용하여 특성 가중치를 조정한다. 이 때 각 특성의 거리 계산 방법에 대해서는 제한을 두지 않는다. 또한 각 특성의 표현에 있어서도 고정적인 크기뿐만이 아니라 가변적인 크기의 데이타 역시 사용할 수 있도록 한다. 본 논문에서는 실험을 통하여 제안한 기법의 유효성을 입증하였으며, 다른 연구 결과와의 비교를 통하여 제안한 기법의 성능이 보다 우수함을 보였다.

• ETRI Journal
• /
• 제20권3호
• /
• pp.272-283
• /
• 1998

In this paper, we propose efficient content-based image retrieval methods using the automatic extraction of the low-level visual features as image content. Two new feature extraction methods are presented. The first one os an advanced color feature extraction derived from the modification of Stricker's method. The second one is a texture feature extraction using some DCT coefficients which represent some dominant directions and gray level variations of the image. In the experiment with an image database of 200 natural images, the proposed methods show higher performance than other methods. They can be combined into an efficient hierarchical retrieval method.

• 한국ITS학회 논문지
• /
• 제19권3호
• /
• pp.129-136
• /
• 2020

본 논문에서는 저조도 야간 감시 시스템을 위한 열영상 기반의 객체 검출 알고리즘을 제안한다. 기존 Adaboost를 이용한 Haar 특징점 선택 알고리즘은 학습 샘플에 대한 유사하거나 중복되는 특징점의 선택 문제와 잡음에 취약한 경우가 많았다. 또한 저조도 야간 환경의 감시 영상에서 얻어지는 잡음을 특징점 세트에서 제거하고 빠르고 효율적인 실시간 특징점 선택이 이루어질 수 있게 가벼운 확장형 Haar 특징점과 Adaboost 학습 알고리즘을 사용하여 구현하였다. 야간 저조도 환경에서 움직임이 있는 비예측 객체를 인식하기 위하여 열영상으로 촬영된 이미지에 확장 Haar 특징점을 사용하여 객체를 인식한다. 비디오 프레임 800*600 크기의 열영상 이미지를 입력으로 하는 Adaboost 학습 알고리즘을 CUDA 9.0 플랫폼으로 구현하여 시뮬레이션을 시행한다. 그 결과 객체 검출 결과는 성공률이 약 90% 이상임을 확인하였고, 이는 일반영상에 히스토그램 이퀄라이징 연산을 거쳐 얻어진 연산 결과보다 약 30% 더 빠른 처리 속도를 얻을 수 있었다.

• 한국CDE학회논문집
• /
• 제7권2호
• /
• pp.121-130
• /
• 2002

The concept of Level Of Detail (LOD) was introduced and has been used to enhance display performance and to carry out certain engineering analysis effectively. We would like to use an adequate complexity level for each geometric model depending on specific engineering needs and purposes. Solid modeling systems are widely used in industry, and are applied to advanced applications such as virtual assembly. In addition, as the demand to share these engineering tasks through networks is emerging, the problem of building a solid model of an appropriate resolution to a given application becomes a matter of great necessity. However, current researches are mostly focused on triangular mesh models and various operators to reduce the number of triangles. So we are working on the multi-resolution of the solid model itself, rather than that of the triangular mesh model. In this paper, we propose multi-resolution representation of B-rep model by reordering and converting design features into an enclosing volume and subtractive features.

• Journal of Computing Science and Engineering
• /
• 제9권4호
• /
• pp.204-213
• /
• 2015

Under the conditional independence assumption among local features, the Naive Bayes Nearest Neighbor (NBNN) classifier has been recently proposed and performs classification without any training or quantization phases. While the original NBNN shows high classification accuracy without adopting an explicit training phase, the conditional independence among local features is against the compositionality of objects indicating that different, but related parts of an object appear together. As a result, the assumption of the conditional independence weakens the accuracy of classification techniques based on NBNN. In this work, we look into this issue, and propose a novel Bayesian network for an NBNN based classification to consider the conditional dependence among features. To achieve our goal, we extract a high-level feature and its corresponding, multiple low-level features for each image patch. We then represent them based on a simple, two-level layered Bayesian network, and design its classification function considering our Bayesian network. To achieve low memory requirement and fast query-time performance, we further optimize our representation and classification function, named relation-based Bayesian network, by considering and representing the relationship between a high-level feature and its low-level features into a compact relation vector, whose dimensionality is the same as the number of low-level features, e.g., four elements in our tests. We have demonstrated the benefits of our method over the original NBNN and its recent improvement, and local NBNN in two different benchmarks. Our method shows improved accuracy, up to 27% against the tested methods. This high accuracy is mainly due to consideration of the conditional dependences between high-level and its corresponding low-level features.

• 무역학회지
• /
• 제46권5호
• /
• pp.99-113
• /
• 2021

This study aims to analyze the effect of product information quality and source credibility on product arousal in fresh food website. Despite fresh food websites are selling products with various feature, prior studies have focused on consumer behavior for fresh food website characteristics or specific products without considering the feature of the products. Consumers' attitudes, beliefs, and behaviors vary depending on the feature of the product. In other words, depending on the category of product, the decision making process that consumers purchase products can be differ. So, we classify products considering the feature of these products to examine the effect of information quality and source credibility on product arousal into experience goods and search goods. We surveyed 288 consumers having experience of purchase in fresh food website and verified the hypothesis through One-way ANOVA by classifying the information quality and the source credibility as high level and low level. As a result, there was a difference in product arousal according to the product information quality level and the source credibility level for each product category exposed to the fresh food website. In experience goods, source credibility have a more important effect on product arousal than product information quality, and in search goods, product information quality have a more important effect on product arousal than source credibility.