• Journal of the Korea Society of Computer and Information
• /
• v.6 no.2
• /
• pp.41-47
• /
• 2001

In this paper, I propose a detection algorithm that can reliably separate moving objects from noisy background in the image sequence received from a camera at the fixed position. The proposed algorithm consists of four processes: generation of the difference image between the input image and the reference image. multilevel quantization of the difference image, and multistage merging in the quantized image, detection of the moving object using a back propagation in a neural network. The test results show that the proposed algorithm can detect moving objects very effectively in noisy environment.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.7 s.262
• /
• pp.739-746
• /
• 2007

Recently, models in STL files are widely used in reverse engineering processes, CAD systems and analysis systems. However the models have poor geometric quality and include only triangles, so the models are not suitable for the finite element analysis. This paper presents a general method that generates finite element mesh from STL file models. Given triangular meshes, the method estimates triangles and makes clusters which consist of triangles. The clusters are merged by some geometric indices. After merging clusters, the method applies plane meshing algorithm, based on domain decomposition method, to each cluster and then the result plane mesh is projected into the original triangular set. Because the algorithm uses general methods to generate plane mesh, we can obtain both tri and quad meshes unlike previous researches. Some mechanical part models are used to show the validity of the proposed method.

• Journal of Mechanical Science and Technology
• /
• v.15 no.5
• /
• pp.623-629
• /
• 2001

The PSC (Propagation of Surfaces under Curvature) algorithm is adapted to the simulation of a flame propagation in a premixed medium including the effect of volume expansion across the flame front due to exothermicity. The algorithm is further developed to incorporate the flame anchoring scheme. This methodology is successfully applied to numerically simulate the response of an anchored V-flame to two strong free stream vortices, in accord with experimental observations of a passage of Karman vortex street through a flame. The simulation predicts flame cusping when a strong vortex pair interacts with flame front. In other words, this algorithm handles merging and breaking of the flame front and provides an accurate calculation of the flame curvature which is needed for flame propagation computation and estimation of curvature-dependent flame speeds.

• Journal of Industrial Technology
• /
• v.28 no.B
• /
• pp.209-214
• /
• 2008

Set-valued attributes appear in many applications to model complex objects occurring in the real world. One of the most important operations on set-valued attributes is the set join, because it provides a various method to express complex queries. Currently proposed set join algorithms are based on block nested loop join in which inverted files are partitioned horizontally into blocks. Evaluating these joins are expensive because they generate intermediate partial results severely and finally obtain the final results after merging partial results. In this paper, we present an efficient processing of set join algorithm. We propose a new set join algorithm that vertically partitions inverted files into blocks, where each block fits in memory, and performs block nested loop join without producing intermediate results. Our experiments show that the vertical bitmap nested set join algorithm outperforms previously proposed set join algorithms.

• 한국데이터정보과학회:학술대회논문집
• /
• 2004.04a
• /
• pp.39-50
• /
• 2004

The decision tree approach is most useful in classification problems and to divide the search space into rectangular regions. Decision tree algorithms are used extensively for data mining in many domains such as retail target marketing, fraud dection, data reduction and variable screening, category merging, etc. CHAID(Chi-square Automatic Interaction Detector) uses the chi-squired statistic to determine splitting and is an exploratory method used to study the relationship between a dependent variable and a series of predictor variables. In this paper we propose CHAID algorithm by cube-based proportional sampling and explore CHAID algorithm in view of accuracy and speed by the number of variables.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.803-816
• /
• 2004

The decision tree approach is most useful in classification problems and to divide the search space into rectangular regions. Decision tree algorithms are used extensively for data mining in many domains such as retail target marketing, fraud dection, data reduction and variable screening, category merging, etc. CHAID uses the chi-squired statistic to determine splitting and is an exploratory method used to study the relationship between a dependent variable and a series of predictor variables. In this paper we propose CHAID algorithm by cube-based proportional sampling and explore CHAID algorithm in view of accuracy and speed by the number of variables.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.5
• /
• pp.444-452
• /
• 2008

This paper presents an overall image processing approach of defect inspection of patterned TFT-LCD panels for the real manufacturing process. A prototype of AOI(Automatic Optical Inspection) system which is composed of air floating stage and multi line scan cameras is developed. Adjacent pattern comparison algorithm is enhanced and used for pattern elimination to extract defects in the patterned image of TFT-LCD panels. New region merging algorithm which is based on border expansion is proposed to identify defects from the pattern eliminated defect image. Experimental results show that a developed AOI system has acceptable performance and the proposed algorithm reduces environmental effects and processing time effectively for applying to the real manufacturing process.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.363-363
• /
• 2000

The conventional algorithms which identify and follow a moving target using a camera located at a fixed position are not appropriate for applying to the cases o( using mobile robots, due to their long processing time. This paper proposes a new tracking algorithm based on the sensing system which uses a line light with a single camera. The algorithm categirizes the motion patterns of a pair of mobile objects into parallel, branching, and merging motion, to decide of which objects the trajectories should be calculated to follow the reference object. Kalman Filter is used to estimate the trajectories of selected objects. The proposed algorithm has shown in the experiments that the mobile robot does not miss the target in most cases.

• Journal of Korean Institute of Industrial Engineers
• /
• v.29 no.1
• /
• pp.90-99
• /
• 2003

Object clustering, which makes classification for a set of objects into a number of groups such that objects included in a group have similar characteristic and objects in different groups have dissimilar characteristic each other, has been exploited in diverse area such as information retrieval, data mining, group technology, etc. In this study, an object-clustering problem with similarity coefficients between objects is considered. At first, an evaluation function for the optimization problem is defined. Then, a genetic algorithm and local optimization technique based on heuristic method are proposed and used in order to obtain near optimal solutions. Solutions from the genetic algorithm are improved by local optimization techniques based on object relocation and cluster merging. Throughout extensive experiments, the validity and effectiveness of the proposed algorithms are tested.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.695-700
• /
• 2021

The Faster RCNN-based shellfish recognition algorithm is introduced for shellfish recognition studies that currently do not have any deep learning-based algorithms in a practical setting. The original feature extraction module is replaced by DenseNet, which fuses multi-level feature data and optimises the NMS algorithm, network depth and merging method; overcoming the omission of shellfish overlap, multiple shellfish and insufficient light, effectively solving the problem of low shellfish classification accuracy. In the complexifier test environment, the test accuracy was improved by nearly 4%. Higher testing accuracy was achieved compared to the original testing algorithm. This provides favourable technical support for future applications of the improved Faster RCNN approach to seafood quality classification.