• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.160-168
• /
• 2022

In this paper, we propose a 3D mesh reconstruction method from a single image using deep learning and a sphere shape transformation method. The proposed method has the following originality that is different from the existing method. First, the position of the vertex of the sphere is modified to be very similar to the 3D point cloud of an object through a deep learning network, unlike the existing method of building edges or faces by connecting nearby points. Because 3D point cloud is used, less memory is required and faster operation is possible because only addition operation is performed between offset value at the vertices of the sphere. Second, the 3D mesh is reconstructed by covering the surface information of the sphere on the modified vertices. Even when the distance between the points of the 3D point cloud created by correcting the position of the vertices of the sphere is not constant, it already has the face information of the sphere called face information of the sphere, which indicates whether the points are connected or not, thereby preventing simplification or loss of expression. can do. In order to evaluate the objective reliability of the proposed method, the experiment was conducted in the same way as in the comparative papers using the ShapeNet dataset, which is an open standard dataset. As a result, the IoU value of the method proposed in this paper was 0.581, and the chamfer distance value was It was calculated as 0.212. The higher the IoU value and the lower the chamfer distance value, the better the results. Therefore, the efficiency of the 3D mesh reconstruction was demonstrated compared to the methods published in other papers.

• Transactions of Materials Processing
• /
• v.14 no.2 s.74
• /
• pp.139-144
• /
• 2005

It was investigated that curved aluminum products with 'ㄷ' section or with 'h' section could be bended during extrusion by the extru-bending process. In order to make bending at the exit section of die, the flow of billet inside die cavity was controlled by the shape of billet. As results of the analysis of $DEFORM^{™}-3D$, it was known that the bending phenomenon at the die exit can be happened by the asymmetric section of billet. And it was known by the experiment with plasticine or aluminum material that an symmetric product with 'c' channel section and the product with flanged 'h' section could be bended because of asymmetric shape of billet.

• Proceedings of the KSME Conference
• /
• 2008.11a
• /
• pp.1255-1258
• /
• 2008

Roll to roll (R2R) system, known as 'web processing', is the process of producing these electronic devices on a roll of flexible plastic. With the need of improved performance and productivity in R2R industry, effective control and on-line supervision for web quality is essential. In this report, we present a system for on-line measurement of wrinkles, one of defects incurring due to compressive stresses developed in the web. This system is able to capture an image generated when a well defined line shape laser beam passes through a transparent web. The system calculates 3D shape information, including the height of the wrinkle on the web, and displays the images for the shape information of the web in real time. By using area scan camera and machine vision laser, this system takes more advantages of setting up as a simple and low cost system compared to the line scan camera systems that widely used in web manufacturing. Specific calibration method and analysis on the achievable accuracy will be discussed.

• Journal of the Microelectronics and Packaging Society
• /
• v.24 no.2
• /
• pp.55-59
• /
• 2017

An optical method to inspect the 3-D shape of surface of Micro BGA is proposed, where spatially arranged LED light sources and specular reflection are considered. The reflected image captured by a vision system was analyzed to calculate the relative displacements of LED's in the image. Also, the statistics for all BGA's contained in a captured image are used together to find out the criteria for the detection of existing defects, and the usefulness of the proposed method is shown via experiments.

• The KIPS Transactions:PartA
• /
• v.16A no.2
• /
• pp.61-68
• /
• 2009

We present a fast 3D shape deformation method that achieves smoothly deformed result by approximating a rigid transformation based on moving least squares (MLS). Our modified MLS formulation reduces the computation cost for computing the optimal transformation of each point and still keeps the rigidity of the deformed results. Even complex geometric shapes are easily, intuitively, and interactively deformed by manipulating point and ellipsoidal handles.

• Journal of radiological science and technology
• /
• v.40 no.1
• /
• pp.121-126
• /
• 2017

A technique for producing the ear shell for a hearing aid using DICOM (Digital Imaging and Communication in Medicine) image and a 3D printing was studied. It is a new application method, and is an application technique that can improve the safety and infection of hearing aid users and can reduce the production time and process stages. In this study, the effects on the shape surface were examined before and after the printing of the ear shell using a 3D printer based on the values obtained from the raw data of the DICOM images at the volumes of 0.5 mm, 1.0 mm, and 2.0 mm, respectively. Before the printing, relative relationship was compared with respect to the STL (STereoLithography) file structure; and after the printing, the intervals of the layered structure of the ear shell shape surface were compared by magnifying them using a microscope. For the STL file structure, the numbers of triangular vertices, more than five intersecting points, and maximum intersecting points were large in the order of 0.5 mm, 1.0 mm, and 2.0 mm, respectively; and the triangular structure was densely distributed in the order of the bending, angle, and crest regions depending on the sinuosity of the external auditory meatus shape. As for the ear shell shape surface examined by the digital microscope, the interval of the layered structure was thick in the order of 2.0 mm, 1.0 mm, and 0.5 mm. For the STL surface structure mentioned above, the intersecting STL triangular structure was denser as the sinuosity of the 3D ear shell shape became more irregular and the volume of the raw data decreased.

• The korean journal of orthodontics
• /
• v.13 no.1
• /
• pp.105-114
• /
• 1983

the author studied the corelativity between the head and face and the maxillary arch in Korean. This study was undertaker in 336 persons at age from 9 to 19 years who had normal occlusion by means of angle's classification. The following results were obtained. 1. The corelative coefficient between the Height of Head and Face (H.H.F.) and the Arch Length (A.L.) was 0.203-0.543, 2. The corelative coefficient between the Bizygomatic width (Z.W.) and the Bicanine width (C-C) was 0.203-0.543. 3. The corelative coefficient between the Bizygomatic width (Z.W.) and the Bimolar width (M-M) was 0.206-0.600. 4. The corelative coefficient between the Face shape (Index a) and Maxillaxy arch shape (In-dex c) was 0.232-0.404. 5. The corelative coefficient between the Face shape (Index a) and Maxillary arch shape (Index d) was 0.221-0.401. 6. There was no corelativity between the Anterior-posterior width of head (A.P.W.) and Arch Length A.L.), Head shape (Index b) and Maxillary arch shape (Index c, Index d).

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1634-1642
• /
• 2022

Numerous studies have attempted to present converting 2D drawings to 3D. However, converting 3D shapes to exactly how a person thinks is challenging because 2D drawings include numerous variables and possibilities. This study focuses on visualizing 2D to 3D in a commonly used 3D animation software required in animation education or the 3D industry. We implemented our SketchTo3D tool to add the editing and automatic texture assigning method from the imported 2D image into the 3D software that previously had to be done manually. As a result, the SketchTo3D tool saves time to immediately visualize the composition, shape, and volume to express the 3D character, providing an opportunity to break down the barrier between 2D and 3D.

• Journal of Korean Society of Disaster and Security
• /
• v.13 no.3
• /
• pp.45-58
• /
• 2020

Due to a high portion of mountainous terrains in Korea, debris flow and its disasters have been increased. In addition, recently localized flash-floods caused by climate change should add frequencies and potential risks. Grasping and understanding the behaviors of debris flow would allow us to prevent the consequent disasters caused by its occurrence. In this study, we developed a number of cases by changing the bottom slopes and their curvatures and investigated their effects on potential damage caused by the debris flow using FLO-2D. As simulating each bed slopes we analyzed for velocity, depth, impact, reach distance, and reach shape. As a result the lower the average slope, the greater the influence of its curvature and the numerical results were analyzed with showed a well-marked difference in impact stress and flow velocity. The result from this study could be referred for protecting from the debris flows when design countermeasure structures in mountainous regions.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.421-427
• /
• 2001

In this paper, a method for selection of the optimal feature vectors is proposed for the classification of closed 2D shapes using the bispectrum of a contour sequence. The bispectrum based on third order cumulants is applied to the contour sequences of the images to extract feature vectors for each planar image. These bispectral feature vectors, which are invariant to shape translation, rotation and scale transformation, can be used to represent two-dimensional planar images, but there is no certain criterion on the selection of the feature vectors for optimal classification of closed 2D images. In this paper, a new method for selecting the optimal bispectral feature vectors based on the variances of the feature vectors. The experimental results are presented using eight different shapes of aircraft images, the feature vectors of the bispectrum from five to fifteen and an weighted mean fuzzy classifier.