• 반도체디스플레이기술학회지
• /
• 제15권4호
• /
• pp.97-102
• /
• 2016

Image stitching is a process of combining two or more images with overlapping area to create a panorama of input images, which is considered as an active research area in computer vision, especially in the field of augmented reality with 360 degree images. Image stitching techniques can be categorized into two general approaches: direct and feature based techniques. Direct techniques compare all the pixel intensities of the images with each other, while feature based approaches aim to determine a relationship between the images through distinct features extracted from the images. This paper proposes a novel image stitching method based on feature pixels with approximated clustering filter. When the features are extracted from input images, we calculate a meaning of the minutiae, and apply an effective feature extraction algorithm to improve the processing time. With the evaluation of the results, the proposed method is corresponding accurate and effective, compared to the previous approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5197-5218
• /
• 2019

Large-scale retrieval algorithm is problem for visual analyses applications, along its research track. In this paper, we propose a high-efficiency region division-based image retrieve approaches, which fuse low-level local color histogram feature and texture feature. A novel image region division is proposed to roughly mimic the location distribution of image color and deal with the color histogram failing to describe spatial information. Furthermore, for optimizing our region division retrieval method, an image descriptor combining local color histogram and Gabor texture features with reduced feature dimensions are developed. Moreover, we propose an extended Canberra distance method for images similarity measure to increase the fault-tolerant ability of the whole large-scale image retrieval. Extensive experimental results on several benchmark image retrieval databases validate the superiority of the proposed approaches over many recently proposed color-histogram-based and texture-feature-based algorithms.

• 한국정밀공학회지
• /
• 제20권3호
• /
• pp.105-111
• /
• 2003

This paper presents an approach to automate process planning of press dies for manufacturing of car bodies. Considering that the press-dies used at the same press operations regardless of the panels they produce or the car models of which they produce panels have similar shapes except for the forming part of the dies, general approaches to recognize manufacturing features from CAD models are not necessary. Therefore, a hybrid approach is proposed combining feature-based design and feature-extraction approaches. The proposed method recognizes features by parsing the parameters extracted from CAD models and finds proper operations by querying the database by the recognized features. An internet-based process planning system is developed to demonstrate the proposed approach and to suggest a new paradigm of process planning system that utilizes an internet access to the CAD system.

• 한국CDE학회논문집
• /
• 제1권3호
• /
• pp.242-256
• /
• 1996

Although feature-based design is a promising approach to fully integrating CAD/CAM, current feature-based design approaches seldom provide methodologies to easily define and design features. This paper proposes a new approach to integrating parametric design with feature-based design to overcome those limitations by globally decomposing a design into a set of features and locally defining and positioning each feature by geometric constraints. Each feature is defined as a parametric shape which consists of a feature section, attributes, and a set of constraints. The generalized sketching and sweeping techniques are used to simplify the process of designing features. The proposed approach is knowledge-based and its computational efficiency in geometric reasoning is improved greatly. Parametrically designed features not only have the advantage of allowing users to efficiently perform design changes, but also provide designers with a natural design environment in which they can do their work more naturally and creatively.

• Industrial Engineering and Management Systems
• /
• 제16권1호
• /
• pp.64-79
• /
• 2017

Identifying disease genes from human genome is a critical task in biomedical research. Important biological features to distinguish the disease genes from the non-disease genes have been mainly selected based on traditional feature selection approaches. However, the traditional feature selection approaches unnecessarily consider many unimportant biological features. As a result, although some of the existing classification techniques have been applied to disease gene identification, the prediction performance was not satisfactory. A small set of the most important biological features can enhance the accuracy of disease gene identification, as well as provide potentially useful knowledge for biologists or clinicians, who can further investigate the selected biological features as well as the potential disease genes. In this paper, we propose a new stepwise random forests (SRF) approach for biological feature selection and disease gene identification. The SRF approach consists of two stages. In the first stage, only important biological features are iteratively selected in a forward selection manner based on one-dimensional random forest regression, where the updated residual vector is considered as the current response vector. We can then determine a small set of important biological features. In the second stage, random forests classification with regard to the selected biological features is applied to identify disease genes. Our extensive experiments show that the proposed SRF approach outperforms the existing feature selection and classification techniques in terms of biological feature selection and disease gene identification.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권9호
• /
• pp.654-668
• /
• 2002

In this paper, we present an empirical study for improving the Korean text chunking based on machine learning and feature set selection approaches. We focus on two issues: the problem of selecting feature set for Korean chunking, and the problem of alleviating the data sparseness. To select a proper feature set, we use a heuristic method of searching through the space of feature sets using the estimated performance from a machine learning algorithm as a measure of "incremental usefulness" of a particular feature set. Besides, for smoothing the data sparseness, we suggest a method of using a general part-of-speech tag set and selective lexical information under the consideration of Korean language characteristics. Experimental results showed that chunk tags and lexical information within a given context window are important features and spacing unit information is less important than others, which are independent on the machine teaming techniques. Furthermore, using the selective lexical information gives not only a smoothing effect but also the reduction of the feature space than using all of lexical information. Korean text chunking based on the memory-based learning and the decision tree learning with the selected feature space showed the performance of precision/recall of 90.99%/92.52%, and 93.39%/93.41% respectively.

• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1315-1318
• /
• 2003

In this paper, a neural network based approach using a self-organizing feature map is proposed for the segmentation of X ray images. A number of algorithms based on such approaches as histogram analysis, region growing, edge detection and pixel classification have been proposed for segmentation of general images. However, few approaches have been applied to X ray image segmentation because of blur of the X ray image and vagueness of its edge, which are inherent properties of X ray images. To this end, we develop a new model based on the neural network to detect objects in a given X ray image. The new model utilizes Mumford-Shah functional incorporating with a modified adaptive SOFM. Although Mumford-Shah model is an active contour model not based on the gradient of the image for finding edges in image, it has some limitation to accurately represent object images. To avoid this criticism, we utilize an adaptive self organizing feature map developed earlier by the authors.[1] It's learning rule is derived from Mumford-Shah energy function and the boundary of blurred and vague X ray image. The evolution of the neural network is shown to well segment and represent. To demonstrate the performance of the proposed method, segmentation of an industrial part is solved and the experimental results are discussed in detail.

• Advances in Energy Research
• /
• 제6권2호
• /
• pp.91-101
• /
• 2019

This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.

• Journal of Information Processing Systems
• /
• 제8권2호
• /
• pp.301-314
• /
• 2012

In this paper, two new approaches to align English-Arabic sentences in bilingual parallel corpora based on the Multi-Class Support Vector Machine (MSVM) and the Hidden Markov Model (HMM) classifiers are presented. A feature vector is extracted from the text pair that is under consideration. This vector contains text features such as length, punctuation score, and cognate score values. A set of manually prepared training data was assigned to train the Multi-Class Support Vector Machine and Hidden Markov Model. Another set of data was used for testing. The results of the MSVM and HMM outperform the results of the length based approach. Moreover these new approaches are valid for any language pairs and are quite flexible since the feature vector may contain less, more, or different features, such as a lexical matching feature and Hanzi characters in Japanese-Chinese texts, than the ones used in the current research.