• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.1
• /
• pp.228-246
• /
• 2011

A 3D model based approach for a face representation and recognition algorithm has been investigated as a robust solution for pose and illumination variation. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time and complexity. In this paper, we propose a novel 3D face representation algorithm based on a pixel to vertex map (PVM) to optimize the number of vertices. We explore shape and texture coefficient vectors of the 3D model by fitting it to an input face using inverse compositional image alignment (ICIA) to evaluate face recognition performance. Experimental results show that the proposed face representation and recognition algorithm is efficient in computation time while maintaining reasonable accuracy.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.47-54
• /
• 2009

Automatic object recognition in 3D measuring data is of great interest in many application fields e.g. computer vision, reverse engineering and digital factory. In this paper we present a software tool for a fully automatic object detection and parameter estimation in unordered and noisy point clouds with a large number of data points. The software consists of three interactive modules each for model selection, point segmentation and model fitting, in which the orthogonal distance fitting (ODF) plays an important role. The ODF algorithms estimate model parameters by minimizing the square sum of the shortest distances between model feature and measurement points. The local quadric surface fitted through ODF to a randomly touched small initial patch of the point cloud provides the necessary initial information for the overall procedures of model selection, point segmentation and model fitting. The performance of the presented software tool will be demonstrated by applying to point clouds.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.135-144
• /
• 2015

Fingerprint pores have proven to be useful features for fingerprint recognition and several pore-based fingerprint recognition systems have been reported recently. In order to recognize fingerprints using pore information, it is very important to extract pores reliably and accurately. Existing pore extraction methods utilize 2D model fitting to detect pore centers. This paper proposes a pore extraction method using 1D Gaussian model which is much simpler than 2D model. During model fitting process, 1D model requires less computational cost than 2D model. The proposed method first calculates local ridge orientation; then, ridge mask is generated. Since pore center is brighter than its neighboring pixels, pore candidates are extracted using a $3{\times}3$ filter and a $5{\times}5$ filter successively. Pore centers are extracted by fitting 1D Gaussian model on the pore candidates. Extensive experiments show that the proposed pore extraction method can extract pores more effectively and accurately than other existing methods, and pore matching results show the proposed pore extraction method could be used in fingerprint recognition.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.212-214
• /
• 2021

In a society with Covid-19 as part of our daily lives, we had to adapt ourselves to a new reality to maintain our lifestyles as normal as possible. An example of this is teleworking and online classes. However, several issues appeared on the go as we started the new way of living. One of them is the doubt of knowing if real people are in front of the camera or if someone is paying attention during a lecture. Therefore, we encountered this issue by creating a 3D reconstruction tool to identify human faces and expressions actively. We use a web camera, a lightweight 3D face model, and use the 2D facial landmark to fit expression coefficients to drive the 3D model. With this Model, it is possible to represent our faces with an Avatar and fully control its bones with rotation and translation parameters. Therefore, in order to reconstruct facial expressions during online meetings, we proposed the above methods as our solution to solve the main issue.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.768-776
• /
• 2011

This paper considers a data fitting problem for rational function models using the LM (Levenberg-Marquardt) optimization method. Rational function models have various merits on representing a wide range of shapes and modeling complicated structures by polynomials of low degrees in both the numerator and denominator. However, rational functions are nonlinear in the parameter vector, thereby requiring nonlinear optimization methods to solve the fitting problem. In this paper, we propose a data fitting method for rational function models based on the LM algorithm which is renowned as an effective nonlinear optimization technique. Simulations show that the fitting results are robust against the measurement noises and uncertainties. The effectiveness of the proposed method is further demonstrated by the real application to a 3D depth camera calibration problem.

• Journal of Fashion Business
• /
• v.8 no.4
• /
• pp.94-103
• /
• 2004

The purpose of this study was to make activated electronic business transaction of clothes. The subject used for this study was 19 - 24 aged 149 college women who most likely buying products through internet. By compare the 149 women's body shape with 3D model, 149 women could be judged their body shape objectively. We showed the average 3D model by the measurement of 19 - 24aged women's body shape. 19 - 24aged women are big customer of internet shopping mall. By understanding of the difference between real somatotype and perceptual somatotype, we can reduce the disadvantage such as returning clothes. Also, imaginary fitting model can be used for internet shopping mall, animation work, fashion show, and advertisement work. Therefore, we can expect the worth of this study to do.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.51-61
• /
• 2004

In the dental field, the 3D tooth model in which each tooth can be manipulated individually is an essential component for the simulation of orthodontic surgery and treatment. To reconstruct such a tooth model from CT slices, we need to define the accurate boundary of each tooth from CT slices. However, the global threshold method, which is commonly used in most existing 3D reconstruction systems, is not effective for the tooth segmentation in the CT image. In tooth CT slices, some teeth touch with other teeth and some are located inside of alveolar bone whose intensity is similar to that of teeth. In this paper, we propose an image segmentation algorithm based on B-spline curve fitting to produce smooth tooth regions from such CT slices. The proposed algorithm prevents the malfitting problem of the B-spline algorithm by providing accurate initial tooth boundary for the fitting process. This paper proposes an optimal threshold scheme using the intensity and shape information passed by previous slice for the initial boundary generation and an efficient B-spline fitting method based on genetic algorithm. The test result shows that the proposed method detects contour of the individual tooth successfully and can produce a smooth and accurate 3D tooth model for the simulation of orthodontic surgery and treatment.

• Journal of Mechanical Science and Technology
• /
• v.20 no.12
• /
• pp.2034-2042
• /
• 2006

In this study, a complete 3D surface reconstruction method is proposed based on the concept that the vertices, of surface model can be completely matched to the unstructured point cloud. In order to generate the initial mesh model from the point cloud, the mesh subdivision of bounding box and shrink-wrapping algorithm are introduced. The control mesh model for well representing the topology of point cloud is derived from the initial mesh model by using the mesh simplification technique based on the original QEM algorithm, and the parametric surface model for approximately representing the geometry of point cloud is derived by applying the local subdivision surface fitting scheme on the control mesh model. And, to reconstruct the complete matching surface model, the insertion of isolated points on the parametric surface model and the mesh optimization are carried out. Especially, the fast 3D surface reconstruction is realized by introducing the voxel-based nearest-point search algorithm, and the simulation results reveal the availability of the proposed surface reconstruction method.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.161-162
• /
• 1997

It is very useful to perform the surgery simulation before implanting TAH(Total Artificial Heart} in a patient. The space of chest and the shape of vessels are different from patient to patient. So, It is desirable to customize a TAH design to the anatomy structure of a patient. Several studies are performed to visualize and explain the 3D structure of heart. These studies are performed using 2-dimensional ref or mated images and simple measurement. Anatomy structure of a human heart is not so simple. It is 4dimensional structure ; 3-dimensional plus time, heart beating. 3-dimensional reconstruction schemes of medical images developed for about 10 years are usually categorized into two types of rendering technique ; surface rendering and volume rendering. Volume rendering is preferable in medical image processing field because this technique can be applied without considering the complexity of geometry and change of field of interest. The usable space in the chest of patient can be measured by 3D volume matching of patient trunk and TAH model. This space changes with time. In this research we have developed the 4-dimensional volume match program of patient and TAH model. 3-dimensional rendered set of volumes along time were used to simulate TAH fitting trial. The quantitative measurement from this simulation could be applied to customize TAH design.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2782-2805
• /
• 2018

We present a legorization framework that produces a LEGO model from user-specified 3D mesh model. Our framework is composed of two stages: voxelization and legorization. In the voxelization, input 3D mesh is converted to a voxel model. To preserve the shape of the 3D mesh, we devise a silhouette fitting process for the initial voxel model. For legorization, we propose three objectives: stability, aesthetics and efficiency. These objectives are expressed in a tiling equation, which builds a LEGO model using layer-by-layer approach. We legorize five models including characters and buildings to prove the excellence of our framework.