• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.5
• /
• pp.698-704
• /
• 2010

The machine vision system has been widely applied at automatic inspection field of the industries. Especially, the machine vision system shows good performance at difficult inspection field by contact method. In this paper, the automatic system of a slant method to inspect screw/bolt shape using machine vision is developed. The inspection system uses pattern matching method that search similar degree of the lucidity, the average lucidity, length and angle of inspection set up area using a circular scan and a line scan method. Also the feeding method for inspection product is the slant method, and feed rate is controlled by the ramp angle adjustment. This inspection system is composed of a feeding device, a transfer device, vision systems, a lighting device and computer, and is composed the sorting discharge system of the inferior product. The performance test carried out the feeding speed, the shape correct degree and the sorting discharge speed according to the type of screw/bolt. This sorting inspection system showed a satisfied test results in whole inspection items. Presently, this sorting inspection system is being used in the manufacturing process of screw/bolt usefully.

• Journal of the Korea Computer Graphics Society
• /
• v.18 no.4
• /
• pp.35-40
• /
• 2012

Simulation of deformation and fracture is one of the most important physics-based techniques in film production and real-time applications such as computer games. This paper proposes a practical approach to real-time deformation and fracturing. We adopt solid simulation with oriented particles [1] to simulate large deformation robustly, and develop a fracturing scheme to accommodate material failure when excessively stretched or compressed. The proposed method decomposes linear deformation into optimal rotation and pure stretching precisely in shape matching with oriented particles so that fracturing criteria can be easily formulated in terms of stretching. Experimental results show that the proposed method runs in real-time even for large meshes and it can simulate large deformation and fracturing.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.4
• /
• pp.696-706
• /
• 1992

In sheet metal fabrication using NCT(numerically controlled turret), the automatic tool selection for the NCT operation is the major problem to be solved first to improve its production performance. However, the punching tool selection has been done by human experts either manually or semi-automatically. In this paper, we have introduced the shape-index-set to handle the shape of sheet metal parts and developed an algorithm through which one can find easily the successive matching curves between two curve lists, one from the punching tool and the other from the boundaries of the sheet metal part. Based on this algorithm, we have also devised the method that can select automatically the tools to punch out the boundaries of sheet metal parts. The result of several computational experiments shows the successful tool selection without any fail.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.3
• /
• pp.555-561
• /
• 2024

This paper derives material properties of steel bars that simulate the distribution of stress and strain of prestressed tendons used in Prestressed concrete(PSC) girders and presents an optimal material model. ABAQUS software was used to establish the 3D solid model of the PSC girder and strand wire rope for a PS(Prestressed) tendon. Then the model of steel wire rope was imported into the Isight interface plugin directly through the ABAQUS and the Data Matching. In ABAQUS, the contact pairs were established, the models were meshed, the constraints were applied to solve the finite element model and an axial tension of 0.5m/s was loaded to analyze the stress and deformation distributions in the normal working range of the PS strand wire rope. In Data Matching, classical experimental data is fitted to the optimal material properties through finite element analysis and multi-objective optimization. The results show that the steel bar with optimal material properties presents a similar linear area and stress distribution with the PS tendon.

• Journal of Korea Game Society
• /
• v.21 no.6
• /
• pp.31-40
• /
• 2021

Go has a history of more than 2,500 years, and the life-and-death problems in Go is a fundamental problem domain that must be solved when implementing a computer Go. We attempted to determine the numbers of prototypical eye shapes with 3, 4, 5, and 6 eyes that are directly related to the life-and-death problems, and to classify the prototypical eye shapes represented in 4-tuple forms. Experiment was conducted by Monte-Carlo method and point pattern matching. According to the experimental results, the numbers of prototypical eye shapes were 2 for 3-eye, 5 for 4-eye, 12 for 5-eye, and 35 for 6-eye shapes. Further, using a 4-tuple form, we classified prototypical eye shapes into 1 for 3-eye, 3 for 4-eye, 4 for 5-eye, and 8 for 6-eye shapes.

• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1531-1539
• /
• 2004

In this paper, we propose an efficient method for locating human lips. Based on Point Distribution Model and Principle Component Analysis, a lip shape model is built. Lip boundary model is represented based on the concatenated gray level distribution model. We calculate the distribution of shape parameters using Gaussian mixture. The problem to locate lip is simplified as the minimization problem of matching object function. The Down Hill Simplex Algorithm is used for the minimization with Gaussian Mixture for setting initial condition and refining estimate of lip shape parameter, which can refrain iteration from converging to local minima. The experiments have been performed for many images, and show very encouraging result.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.11
• /
• pp.112-119
• /
• 2002

Generally, it is very difficult to inspect geometric shape of large 2D objects after machining. To maintain the accuracy for inspection, a robot vision is used to divide overall shape into several enlarged images, and image processing technique is applied to acquire one minute geometric contour. The inspection is to compare the NC data with the measured contour data by the vision system, and the algorithm is to rotate to minimize the maximum deviation after coinciding two geometric centers. This paper experimentally shows that the proposed algorithm is very useful for inspection of large machined objects.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.7A
• /
• pp.1076-1083
• /
• 2000

Vehicle license plate recognition identifies vehicle as a unique, and have many applications in traffic monitoring field. In this paper, a vertical edge based algorithm to extract license plate within input gray-scale image is proposed. A size-and-shape filter based on seed-filling algorithm is applied to remove the edges that are impossible to be the vertical edges of license plate. Then the remaining edges are matched with each other according to some restricted conditions so as to locate license plate in input image. After license plate is extracted. normalized and segmented, the characters on it are recognized by template matching method. Experimental results show that the proposed algorithm can deal with license plates in normal shape effectively, as well as the license plates that are out of shape due to the angle of view.

• Journal of Ocean Engineering and Technology
• /
• v.23 no.4
• /
• pp.32-37
• /
• 2009

An analytic similarity shape solution was studied for a two-dimensional floating and fluid-filled membrane structure. The static shape of a membrane structure can be expressed as a set of nonlinear ordinary differential equations. The integration of curvature leads to an analytic solution for the shape, which contains unknown boundary values. Matching the upper and lower shapes at the free surface incorporated with their buoyancy allowed the unknowns to be determined. Some characteristic values of similarity shapes were evaluated and shapes are illustrated for various density ratios and volume efficiency ratios.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3950-3964
• /
• 2017

With the increasing popularity of 3D technology such as 3D printing, 3D modeling, etc., there is a growing need to search for similar models on the internet. Matching non-rigid shapes has become an active research field in computer graphics. In this paper, we present an efficient and effective non-rigid model retrieval method based on topological structure and local volume. The integral geodesic distances are first calculated for each vertex on a mesh to construct the topological structure. Next, each node on the topological structure is assigned a local volume that is calculated using the shape diameter function (SDF). Finally, we utilize the Hungarian algorithm to measure similarity between two non-rigid models. Experimental results on the latest benchmark (SHREC' 15 Non-rigid 3D Shape Retrieval) demonstrate that our method works well compared to the state-of-the-art.