• The Journal of the Korea Contents Association
• /
• v.1 no.1
• /
• pp.8-14
• /
• 2001

In this paper, we suggests a algorithms of recognizing the disease region by extracting particular organ from medical image. This method can extract liver region in spite of input image including many organs and charged format by using multi-threshold of feed-back-structure for segmentation liver region, and suggest the recognition of disease region in extracted liver, using multi-neural network structured by RBF and BP, overcoming the defect of single-neural network. The algorithm in this paper is proficient in adaptation for a multi form change of input medical image. This algorithm can be used at tole-medicine through automatic recognition after recognizing of the disease region by real-tire medical Image.

• Journal of Biomedical Engineering Research
• /
• v.28 no.3
• /
• pp.332-337
• /
• 2007

In the early twenty-first century, minimally invasive surgery is the mainstay of various kinds of surgical fields. Surgeons gave percutaneously surgical treatment of the screw directly using a fluoroscopic view in the past. The latest date, they began to operate the fractured carpal bone surgery using Computerized Tomography (CT). Carpal bones composed of wrist joint consist of eight small bones which have hexahedron and sponge shape. Because of these shape, it is difficult to grasp the shape of carpal bones using only CT image data. Although several image segmentation studies have been conducted with carpal bone CT image data, more studies about carpal bone using CT data are still required. Especially, to apply the software implemented from the studies to clinical fIeld, the outcomes should be user friendly and very accurate. To satisfy those conditions, we propose modified multi-seed region growing segmentation method which uses simple threshold and the canny edge detector for finding edge information more accurately. This method is able to use very easily and gives us high accuracy and high speed for extracting the edge information of carpal bones. Especially, using multi-seed points, multi-bone objects of the carpal bone are extracted simultaneously.

• The korean journal of orthodontics
• /
• v.29 no.6 s.77
• /
• pp.673-688
• /
• 1999

This study was conducted in order to analyze the mechanical characteristics of multiloop edgewise archwire (MEAW). The purposes were 1) to compare load deflection rate (LDR) of MEAW with that of various other arch wires in the individual interbracket span, 2) to compare the wire stiffness in the interbracket span with that in the multi-L-loop region (the span from distal border of the bracket of the lateral incisor to the mesial border of the buccal tube of the second molar), and 3) to verify the experimental results with theoretically derived formula. The single L-loops of five different horizontal lengths and multi-L-loops for the upper and lower arches were made out of .$016\times.022$ permachrome stainless steel wire. Straight segment of plain stainless steel, TMA and NiTi wire of the same dimension were prepared. The LDR was measured using Instron model 4466 with the load cell of 50N capacity at cross head speed of 1.0mm/min, and maximum deflection of 1.0mm. Five specimens were tested under each experimental condition. The wire stiffness number for each interbracket region and multi-L-loop region was calculated from the LDR and the interbracket spans. By dividing the theoretical model of multi-L-loop into 35 linear segments, the energy stored in each segment was obtained. Then the LDR and wire stiffness of single L-loop and multi-L-loop were calculated and compared. The findings were as follows : 1) The average LDR of MEAW in the individual interbracket region was 1/1.53 of that of the NiTi,1/2.47 of TMA and 1/5.16 of the plain stainless steel wire. 2) The wire stiffness of MEAW in the multi-L-loop region was 1.53 times larger than that in the interbracket region, and the LDR was almost twice as large as that of NiTi in that region. 3) According to the theoretically derived equation, the wire stiffness of the single L-loop was lower than that of multi-L-loop. The results of this study suggest that MEAW has the unique mechanical Property which could allow individual tooth movement and transmit elastic force effectively through the entire arch wire.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.185-189
• /
• 2004

For face recognition system, a face detector which can find exact face region from complex image is needed. Many face detection algorithms have been developed under the assumption that background of the source image is quite simple . this means that face region occupy more than a quarter of the area of the source image or the background is one-colored. Color-based face detection is fast but can't be applicable to the images of which the background color is similar to face color. And the algorithm using neural network needs so many non-face data for training and doesn't guarantee general performance. In this paper, A multi-scale, multi-face detection algorithm using PCA is suggested. This algorithm can find most multi-scaled faces contained in static images with small number of training data in reasonable time.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.33 no.5
• /
• pp.373-380
• /
• 2009

The evaporation process of multi-component fuel is different from one of a single component, because the properties of each component affects among the components. In actual engine, the spatial distribution of fuel vapor concentration dominates auto-ignition and initial combustion, and depends on the volatility and diffusivity of each component fuel contained in the multi-component fuel. Then, this study proposes a simplified numerical scheme for analysis of evaporation process of multi-component fuel sprays. Evaporation process is calculated by KIVA-II code based on the simple two-phases region that is approximated by modified saturated liquid-vapor line, which was obtained by connecting the 50% distillation temperature for each component under several pressure fields. Consequently, it can be quantitatively simulated that vapor of low boiling fuel component mostly exists around nozzle and spray tip region, the high boiling duel component, on the other hand, mostly appears near the spray tip.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.10
• /
• pp.38-49
• /
• 1996

In this paper, we propose a fast hierarchical image segmentation using mathematical morphology. The proposed segmentation method is composed of five basic steps; multi-thresholding, open-close by reconstructing, mode operation, marker extraction, and region decision. In the multi-thresholding, an input image is simplified by Lloyd clustering algorithm. The multi-thresholded image then is more simplified by open-close by reconstruction and mode operating. In the region decision, to which region each uncertainty pixel belongs finally is decided by a watershed algorithm. Experimental results show that the quality of the segmentation results by the proposed method is not inferior to that by the conventional method and the average times elapsed by the proposed method can be reduced by one tghird of those elapsed by the conventional method.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.42 no.2
• /
• pp.78-85
• /
• 2000

The moment equations of the concentration distribution for the multi-region model are derived using the method of moment. The method originally devised by Aris is to obtain the concentration moments satisfying a given PDE (Partial Differential Equation. The method of moment is used to obtain the first five moments (0th to 4to) that satisfy the model PDE. Each moment of the concentration distribution for the model equation is plotted for the dimensionless time and gave similar results except the skewness and the kurtosis. The results of the analysis show the physical meaning of each moment. The comparisons with the number of regions or the global interaction coefficient give a possibility to determine the parameters of the multi-region model with the analytical concepts.

• Journal of Mechanical Science and Technology
• /
• v.17 no.5
• /
• pp.766-775
• /
• 2003

The intermittent spray characteristics of a multi-hole diesel nozzle with a 2-spring nozzle holder were investigated experimentally. Without changing the total orifice exit area, the hole number of the multi-hole nozzle varied from 3 (d$\_$n/=0.42 mm) to 5 (d$\_$n/=0.32 mm). The time-resolved droplet diameters of the spray including the SMD (Saute. mean diameter) and the AMD (arithmetic mean diameter), injected intormittently from the multi-hole nozzles into still ambient ai., were measured by using a 2-D PDPA (phase Doppler particle analyze.). The 5-hole nozzle spray shows the smaller spray cone angle, the decreased SMD distributions and the small difference between the SMD and the AMD, compared with that of the 3-hole nozzle spray. From the SMD distributions with the radial distance, the spray structure can be classified into the three regions : (a) the inner region showing the high SMD distribution , (b) the mixing flow region where the shea. flow structure would be constructed : and (c) the outer region formed through the disintegration processes of the spray inner region and composed of fine droplets. Through the SMD distributions along the spray centerline, it reveals that the SMD decreases rapidly after showing the maximum value in the vicinity of the nozzle tip. The SMD remains the constant value near the Z/d$\_$n/=166 and 156.3 for the 3-hole and 5-hole nozzles, which illustrate that the disintegration processes of the 5-hole nozzle spray proceed more rapidly than that of the 3-hole nozzle spray.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.5
• /
• pp.1158-1168
• /
• 1994

For BEM analyses of the impact problems of dissimilar materials, the connected multi-region method using perfect bonded conditions on the interface boundaries was added to two-dimensional Laplace transformed-domain BEM program for a single region analysis. It was confirmed that the BEM results of impact problems of a single-region and multi-regions for a homogeneous isotropic material are agreed well. The two-dimensional Laplace transformed-domain BEM program combined with connected multi-region method was applied to analyse several impact problems of dissimilar materials. Also the feasibility of BEM impact analyses was investigated for dissimilar materials by the analysis of the BEM results for impact problems of dissimilar materials in terms of physical aspects. As for an application, the two-dimensional Laplace transformed BEM concerning impact problems of cracks at the interface of dissimilar materials and the determinating process of the dynamic stress intensity factors by extrapolation method are presented in this paper.