• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9C
• /
• pp.861-866
• /
• 2007

A clustering algorithm for Gaussian Probability Distribution Function (GPDF) data called Centroid Neural Network with a Bhattacharyya Kernel (BK-CNN) is proposed in this paper. The proposed BK-CNN is based on the unsupervised competitive Centroid Neural Network (CNN) and employs a kernel method for data projection. The kernel method adopted in the proposed BK-CNN is used to project data from the low dimensional input feature space into higher dimensional feature space so as the nonlinear problems associated with input space can be solved linearly in the feature space. In order to cluster the GPDF data, the Bhattacharyya kernel is used to measure the distance between two probability distributions for data projection. With the incorporation of the kernel method, the proposed BK-CNN is capable of dealing with nonlinear separation boundaries and can successfully allocate more code vector in the region that GPDF data are densely distributed. When applied to GPDF data in an image classification probleml, the experiment results show that the proposed BK-CNN algorithm gives 1.7%-4.3% improvements in average classification accuracy over other conventional algorithm such as k-means, Self-Organizing Map (SOM) and CNN algorithms with a Bhattacharyya distance, classed as Bk-Means, B-SOM, B-CNN algorithms.

• Korean Journal of Remote Sensing
• /
• v.18 no.6
• /
• pp.369-376
• /
• 2002

This paper presents a method to enhance the performance of supervised classification by separating the spectral signature of the training data sets for each class. Using clustering technique, a training data set is divided into several subsets which show a pattern of the normal distribution with small value of spectral variances. Then a supervised classification is applied with the divided training data set as training data for the temporary subclasses of the original class. The proposed method is applied to a Landsat TM image of Busan area for the applicability test. The result shows that the proposed method produces better classified results than the conventional statistical classification methods. It is expected that the proposed method will reduce the effort and expense for selecting the training data set for each class in an area which has spectrally homogeneous signature.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.3
• /
• pp.11-22
• /
• 2002

The design of optimal filter yielding optimal texture feature separation is a most effective technique in many torture analyzing areas, such as perception of surface, object, shape and depth. But, most optimal filter design approaches are restricted to the issue of computational complexity and supervised problems. In this paper, Our proposed method yields new insight into the design of optimal Gabor filters for segmenting multiple texture images. The optimal frequency of Gator filter is turned to the optimal frequency of the distinct texture in frequency domain. In order to show the performance of the designed filters, we have attempted to build a various texture images. Our experimental results show that the performance of the system is very successful.

• Journal of Plant Biotechnology
• /
• v.39 no.1
• /
• pp.81-92
• /
• 2012

Two-dimensional gel electrophoresis (2-DGE) is one of the most important technologies for high-resolution separation of proteins for proteomics. In this study, we present a detail 2-DGE protocol which allows detection and quantification of total plant proteins separated on gels to improve matching in image analysis. This protocol highlighted here may be useful for researchers, who like to first study for the development of protein biomarkers involved in development, biotic and abiotic stresses in plant.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.5
• /
• pp.1524-1533
• /
• 1996

Risidual stress of cylindrical glass rods are measured by photoelasticity to study the variation of stresses with respect to heat treatment temperatures. In order to measure the stresses accurately, fringe sharpening and multiplication techniques are applied to the determination of photoelastic fringe orders. Filon's separationmethod is used to resolve circumferential and redial stress ocmponents from isochromatic fringes which are the same as in-plane maximum shearing stresses. According to the photoelastic measurements, residual stress is increased as the heat treatment temperature of the rods is raised from $560^{\circ}C$ to $650^{\circ}C$ All the circumferential stress components are changed from tensile stresses to compressive ones at approximate $R_m$/$R_o$ = 0.6, where $R_o$/ is outer radius and $R_m$any measured radius. This analysis shows that residual stresses of the glass rods approach zero if the rods are heat-treated near the strain point.

• Wind and Structures
• /
• v.17 no.5
• /
• pp.515-535
• /
• 2013

The present study aims to investigate characteristics of the flow structures around the Ahmed body by using both experimental and numerical methods. Therefore, 1/4 scale Ahmed body having $25^{\circ}$ slant angle was employed. The Reynolds number based on the body height, H and the free stream velocity, U was $Re_H=1.48{\times}10^4$. Investigations were conducted in two parts. In the first part of the study, Large Eddy Simulation (LES) method was used to resolve the flow structures around the Ahmed body, numerically. In the second part of the study the particle image velocimetry (PIV) technique was used to measure instantaneous velocity fields around the Ahmed body. Time-averaged and instantaneous velocity vectors maps, streamline topology and vorticity contours of the flow fields were presented and discussed in details. Comparison of the mean and turbulent quantities of the LES results and the PIV results with the results of Lienhart et al. (2000) at different locations over the slanted surface and in the wake region of the Ahmed body were also given. Flow features such as critical points and recirculation zones in the wake region downstream of the Ahmed body were well captured. The spectra of numerically and experimentally obtained stream-wise and vertical velocity fluctuations were presented and they show good consistency with the numerical result of Minguez et al. (2008).

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.66 no.4
• /
• pp.452-458
• /
• 2021

Roots are the most important organs in plants that absorb nutrients and moisture from the soil. However, owing to difficulties in root data collection, root research is still poorly conducted as compared to shoot research. Recent advancements in crop phenotyping, through advanced imagery data, are rapidly increasing, and artificial intelligence has been applied in various crop root research. Depending on the purpose, different root analysis methods have been developed that measure roots directly in soil or after separation from the soil. Each method has its advantages and disadvantages; therefore, it can be used in accordance with the research interest. Therefore, this review introduces root analysis methods that use imagery systems to help domestic researchers precisely study plant roots or root architecture.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.241-250
• /
• 2019

Road signs are guide facilities for road users, and the Ministry of Land, Infrastructure and Transport has established and operated a system to enhance the convenience of managing these road signs. The role of road signs will decrease in the future autonomous driving, but they will continue to be needed. For the accurate mechanical recognition of texts on road signs, automatic road sign recognition equipment has been developed and it has applied image-based text recognition technology. Yet there are many cases of misrecognition due to irregular specifications and external environmental factors such as manual manufacturing, illumination, light reflection, and rainfall. The purpose of this study is to derive location-based destination names for finding misrecognition errors that cannot be overcome by image analysis, and to improve the automatic recognition of road signs destination names by using Levenshtein similarity verification method based on phoneme separation.

• Resources Recycling
• /
• v.15 no.6 s.74
• /
• pp.3-9
• /
• 2006

In this study, a machine vision system using a color recognition method has been designed and developed to automatically sort out specified materials from a mixture, especially Cu and other non-ferrous metal scraps from a mixture of iron scraps. The system consists of a CCD camera, light sources, a frame grabber, conveying devices and an air-nozzle ejector, and is program-controlled by a image processing algorithms. The ejectors designed to be operated by an I/O interface communication with a hardware controller. In the functional tests of the system, its efficiency in the separation of Cu scraps from its mixture with Fe ones reaches to 90% or more at a conveying speed of 15m/min, and thus the system is proven to be excellent in terms of the separating efficiency. Therefore, it is expected that the system can be commercialized in the industry of shredder makers if an automated sorting system of high speed is realized.

• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.383-392
• /
• 2017

This paper introduces a real-time 3D model generation system that can process in real time from multi-view image acquisition to image-based 3D model generation. This system describes how to collect, transmit, and manage the HD images input from 18 cameras and explain the background separation and smooth 3D volume model generation process. This paper proposes a new distributed data transmission and reception method for real-time processing of HD images input from 18 cameras. In addition, we describe a codebook-based background separating algorithm and a modified marching cube algorithm using perspective difference interpolation to generate smooth 3D models from multi-view images. The system is currently being built with a throughput rate of 30 frames per second.