• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.149-154
• /
• 2023

This paper presents a novel approach to multi-focus image fusion using light field cameras. The proposed neural network, LFFCNN (Light Field Focus Convolutional Neural Network), is composed of three main modules: feature extraction, feature fusion, and feature reconstruction. Specifically, the feature extraction module incorporates SPP (Spatial Pyramid Pooling) to effectively handle images of various scales. Experimental results demonstrate that the proposed model not only effectively fuses a single All-in-Focus image from images with multi focus images but also offers more efficient and robust focus fusion compared to existing methods.

• Korean Journal of English Language and Linguistics
• /
• v.4 no.2
• /
• pp.195-227
• /
• 2004

This paper concerns the issue related to the focus phenomena with a particular reference to the two alternating orders (continuous vs. discontinuous orders) in particle constructions in English. To explain the alternation of word order in particle constructions, I will argue that the choice of word order is closely related to the focus property of the object DPs. Following Drubig (2003), I will assume that focus-feature is taken to be a syntactic feature assigned freely to a lexical head in the process of the mapping into Lexical Array (LA) from the lexicon (LEX). I argue that the focus-marked object DP cannot move out of its focus domain and thus the continuous order is derived. In the case of non-focus-marked object DP, however, the object DP moves out of VP in order to receive an appropriate interpretation. As a result, the discontinuous order is derived.

• Journal of Digital Convergence
• /
• v.10 no.3
• /
• pp.173-178
• /
• 2012

In this paper, a new saliency map generation method is discussed which extracts objects effectively using extracted Salient Region. Feature map is constructed first using four features of edge, hue of HSV color model, focus and entropy and then conspicuity map is generated from Center Surround Differences using the feature map. Final saliency map is constructed by the combination of conspicuity maps. Saliency map generated using this procedure is compared to the conventional technique and confirmed that new technique has better results.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.2
• /
• pp.131-139
• /
• 2008

This paper presents a new saliency map which is constructed by providing dynamic weights on individual features in an input image to search ROI(Region Of Interest) or FOA(Focus Of Attention). To construct a saliency map on there is no a priori information, three feature-maps are constructed first which emphasize orientation, color, and intensity of individual pixels, respectively. From feature-maps, conspicuity maps are generated by using the It's algorithm and their information quantities are measured in terms of entropy. Final saliency map is constructed by summing the conspicuity maps weighted with their individual entropies. The prominency of the proposed algorithm has been proved by showing that the ROIs detected by the proposed algorithm in ten different images are similar with those selected by one-hundred person's naked eyes.

• ETRI Journal
• /
• v.24 no.6
• /
• pp.469-472
• /
• 2002

Speaker adaptation techniques are generally used to reduce speaker differences in speech recognition. In this work, we focus on the features fitted to a linear regression-based speaker adaptation. These are obtained by feature transformation based on independent component analysis (ICA), and the feature transformation matrices are estimated from the training data and adaptation data. Since the adaptation data is not sufficient to reliably estimate the ICA-based feature transformation matrix, it is necessary to adjust the ICA-based feature transformation matrix estimated from a new speaker utterance. To cope with this problem, we propose a smoothing method through a linear interpolation between the speaker-independent (SI) feature transformation matrix and the speaker-dependent (SD) feature transformation matrix. From our experiments, we observed that the proposed method is more effective in the mismatched case. In the mismatched case, the adaptation performance is improved because the smoothed feature transformation matrix makes speaker adaptation using noisy speech more robust.

• ETRI Journal
• /
• v.38 no.3
• /
• pp.502-509
• /
• 2016

Feature detection and description are key ingredients of common image processing and computer vision applications. Most existing algorithms focus on robust feature matching under challenging conditions, such as inplane rotations and scale changes. Consequently, they usually fail when the scene is blurred by camera shake or an object's motion. To solve this problem, we propose a new feature description algorithm that is robust to image blur and significantly improves the feature matching performance. The proposed algorithm builds a feature descriptor by considering the integral projection along four angular directions ($0^{\circ}$, $45^{\circ}$, $90^{\circ}$, and $135^{\circ}$) and by combining four projection vectors into a single highdimensional vector. Intensive experiment shows that the proposed descriptor outperforms existing descriptors for different types of blur caused by linear motion, nonlinear motion, and defocus. Furthermore, the proposed descriptor is robust to intensity changes and image rotation.

• Journal of the Semiconductor & Display Technology
• /
• v.11 no.3
• /
• pp.19-25
• /
• 2012

The accuracy of Shape From Focus (SFF) technique depends on the quality of the focus measurements which are computed through a focus measure operator. In this paper, we introduce a new approach to estimate 3D shape of an object based on Gaussian process regression. First, initial depth is estimated by applying a conventional focus measure on image sequence and maximizing it in the optical direction. In second step, input feature vectors consisting of eginvalues are computed from 3D neighborhood around the initial depth. Finally, by utilizing these features, a latent function is developed through Gaussian process regression to estimate accurate depth. The proposed approach takes advantages of the multivariate statistical features and covariance function. The proposed method is tested by using image sequences of various objects. Experimental results demonstrate the efficacy of the proposed scheme.

• Proceedings of the Korean Society of Environment and Ecology Conference
• /
• 2001.04a
• /
• pp.101-105
• /
• 2001

• Korean Journal of Computational Design and Engineering
• /
• v.3 no.1
• /
• pp.68-85
• /
• 1998

Solid modeling refers to techniques for unambiguous representations of three-dimensional objects. Feature recognition is a sub-discipline focusing on the design and implementation of algorithms for detecting manufacturing information such as holes, slots, etc. in a solid model. Automated feature recognition has been an active research area in stolid modeling for many years, and is considered to be a critical component for CAD/CAM integration. This paper gives a technical overview of the state of the art in feature recognition research. Rather than giving an exhaustive survey, I focus on the three currently dominant feature recognition technologies: graph-based algorithms, volumetric decomposition techniques, and hint-based geometric reasoning. For each approach, I present a detailed description of the algorithms being employed along with some assessments of the technology. I conclude by outlining important open research and development issues.

• Journal of Information Technology Applications and Management
• /
• v.13 no.1
• /
• pp.77-94
• /
• 2006

Case-based Reasoning (CBR) is widely used in business and industry prediction. It is suitable to solve complex and unstructured business problems. Recently, the prediction accuracy of CBR has been enhanced by not only various machine learning algorithms such as genetic algorithms, relative weighting of Artificial Neural Network (ANN) input variable but also data mining technique such as feature selection, feature weighting, feature transformation, and instance selection As a result, CBR is even more widely used today in business area. In this study, we investigated the usefulness of the CBR method in forecasting success in implementing ERP systems. We used a CBR method based on the feature weighting technique to compare the performance of three different models : MDA (Multiple Discriminant Analysis), GECBR (GEneral CBR), FWCBR (CBR with Feature Weighting supported by Analytic Hierarchy Process). The study suggests that the FWCBR approach is a promising method for forecasting of successful ERP implementation in Small and Medium sized Enterprises.