• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.177-180
• /
• 2000

Recently, a feature extraction method based on decision boundary has been proposed for neural networks. The method is based on the fact that all the features necessary to achieve the same classification accuracy as in the original space can be obtained from the vectors normal to decision boundaries. However, the normal vector was estimated numerically. resulting in inaccurate estimation and a long computational time. In this paper. we propose a new method to calculate the normal vector analytically. Experiments show that the proposed method provides a better performance.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6D
• /
• pp.923-929
• /
• 2008

Due to the increasing need for 3D spatial data, modeling of topography and artificial structures plays an important role in three-dimensional Urban Analysis. This study suggests a methodology for solving the problem of calculation for the extraction of building boundary, minimizing the user's intervention, and automatically extracting building boundary, using the LIDAR data. The methodology suggested in this study is characterized by combining the merits of the point-based process and the image-based process. The procedures for extracting building boundary are three steps: 1) LIDAR point data are interpolated to extract approximately building region. 2) LIDAR point data are triangulated in each individual building area. 3) Extracted boundary of each building is then simplified in consideration of its area, minimum length of building.The performance of the developed methodology is evaluated using real LIDAR data. Through the experiment, the extracted building boundaries are compared with digital map.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.44-52
• /
• 2002

In this paper, we present an analytical method for decision boundary feature extraction for neural networks. It has been shown that all the features necessary to achieve the same classification accuracy xxxas in the original space can be obtained from the vectors normal to decision boundaries. However, the vector normal to the decision boundary of a neural network has been calculated numerically using a gradient approximation. This process is time-consuming and the normal vector may be inaccurately estimated. In this paper, we propose a method to improve the performance of the previous decision boundary feature extraction for neural networks by accurately calculating the normal vector When the normal vectors are computed analytically, it is possible to reduce the processing time significantly and improve the performance of the previous implementation that employs numerical approximation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.1-8
• /
• 2000

This paper describes an algorithm for semantic video object tracking using semi automatic method. In the semi automatic method, a user specifies an object of interest at the first frame and then the specified object is to be tracked in the remaining frames. The proposed algorithm consists of three steps: object boundary projection, uncertain area extraction, and boundary refinement. The object boundary is projected from the previous frame to the current frame using the motion estimation. And uncertain areas are extracted via two modules: Me error-test and color similarity test. Then, from extracted uncertain areas, the exact object boundary is obtained by boundary refinement. The simulation results show that the proposed video object extraction method provides efficient tracking results for various video sequences compared to the previous methods.

• Spatial Information Research
• /
• v.15 no.1
• /
• pp.53-65
• /
• 2007

Terrestrial laser scanner provides highly accurate, 3D images and by sweeping a laser beam over a scene or object, the laser scanner is able to record millions of 3D points' coordinates in a short period, so becoming distinguished in various application fields as one of the representative surveying instruments. This study deals with 3D building boundary extraction using Terrestrial Laser Scanner. The results shows that high accuracy 3D coordinates for building boundaries are possibly acquired fast, but terrestrial laser scanner is a ground-based system, so "no roofs", and "no lower part of building" due to trees and electric-poles, etc. It is expected that the combination of total station, terrestrial laser scanner, airborne laser scanner with aerial photogrammetry will contribute to the acquisition of an effective 3D spatial information.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.1
• /
• pp.49-60
• /
• 2002

We propose an algorithm for extracting the boundary of a desired object with shape information obtained from sample images. Considering global shape obtained from sample images and edge orientation as well as edge magnitude, the Proposed method composed of two steps finds the boundary of an object. The first step is the approximate segmentation that extracts a rough boundary with a probability map and an edge map. And the second step is the detailed segmentation for finding more accurate boundary based on the SEEL (seed-point extraction and edge linking) algorithm. The experiment results using IR images show robustness to low-quality image and better performance than conventional segmentation methods.

• Fire Science and Engineering
• /
• v.19 no.4 s.60
• /
• pp.64-68
• /
• 2005

In this paper, we studied fire position recognition and alarm system when we acquired CCDcamera image of fire region and position. We proposed effectively extraction system of boundary of fire region using RED Filtering, and applied 2-graylevel image method to fire boundary extraction. Finally we can make system of fire position and region using mask extraction and matching for fire recognition. For the purpose of experiment result, we effectively recognized that the tire occurrence position and region have steadily spread.

• Journal of Ocean Engineering and Technology
• /
• v.28 no.5
• /
• pp.474-483
• /
• 2014

The majority of existing WECs (wave energy converters) are designed to achieve maximum power at a resonance condition. In the case of a single WEC, its size must be large enough for tuning, and it has high efficiency only within a limited frequency band. Recently, wave power extraction by deploying many small buoys in a compact array has been studied under the assumption that the buoy's size and separation distance are much smaller than the water depth, wave length, and size of the array. A boundary value problem involving the macro-scale boundary condition on the mean surface covered by an infinite strip of buoys is solved using the eigenfunction expansion method. The energy extraction efficiency (${\varepsilon}=1-R^2_f-T^2_r$), where $R_f$ and $T_r$ are the reflection and transmission coefficients for a strip array of buoys, is assessed for various combinations of packing ratio, strip width, and PTO damping coefficient.

• Journal of Korean Medical classics
• /
• v.32 no.3
• /
• pp.47-57
• /
• 2019

Objectives : We aim to assist in choosing an appropriate method for word extraction when analyzing East Asian Traditional Medical texts based on unsupervised learning. Methods : In order to assign ranks to substrings, we conducted a test using one method(BE:Branching Entropy) for exterior boundary value, three methods(CS:cohesion score, TS:t-score, SL:simple-ll) for interior boundary value, and six methods(BExSL, BExTS, BExCS, CSxTS, CSxSL, TSxSL) from combining them. Results : When Miss Rate(MR) was used as the criterion, the error was minimal when the TS and SL were used together, while the error was maximum when CS was used alone. When number of segmented texts was applied as weight value, the results were the best in the case of SL, and the worst in the case of BE alone. Conclusions : Unsupervised-Learning-Based Word Extraction is a method that can be used to analyze texts without a prepared set of vocabulary data. When using this method, SL or the combination of SL and TS could be considered primarily.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1067-1087
• /
• 2018

In a study for LiDAR data based building boundary extraction, usually dense point cloud was used to cluster building rooftop area and extract building outline. However, when we used DSM generated from stereo image matching to extract building boundary, it is not trivial to cluster building roof top area automatically due to outliers and large holes of point cloud. Thus, we propose a technique to extract building boundary semi-automatically from the DSM created from stereo images. The technique consists of watershed segmentation for using user input as markers and recursive MBR algorithm. Since the proposed method only inputs simple marker information that represents building areas within the DSM, it can create building boundary efficiently by minimizing user input.