• Journal of Multimedia Information System
• /
• v.6 no.1
• /
• pp.15-22
• /
• 2019

There are many ways to perform face recognition. The first step of face recognition is the face detection step. If the face is not found in the first step, the face recognition fails. Face detection research has many difficulties because it can be varied according to face size change, left and right rotation and up and down rotation, side face and front face, facial expression, and light condition. In this study, facial features are extracted and the extracted features are geometrically reconstructed in order to improve face recognition rate in extracted face region. Also, it is aimed to adjust face angle using reconstructed facial feature vector, and to improve recognition rate for each face angle. In the recognition attempt using the result after the geometric reconstruction, both the up and down and the left and right facial angles have improved recognition performance.

• 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.

• Applied Microscopy
• /
• v.36 no.2
• /
• pp.73-82
• /
• 2006

Major contributions has been made in cellular ultrastructure studies with the use of high voltage electron microscopy (HVEM) and tomography. Applications of HVEM, accompanied by appropriate image processing, have provided great improvements in the analysis of three-dimensional cellular structures. In the present study, structural patterns of the crystalline bodies that are distinguished in mesophyll plastids of CAM-performing Sedum rotundifolium L., have been investigated using HVEM and tomography. Tilting, and diffraction pattern analysis were performed during the investigation. The titlting was performed at ${\pm}60^{\circ}\;with\;2^{\circ}$ increments while examining serial sections ranging from 0.125 to $1{\mu}m$ in thickness. The young plastids exhibited crystalline inclusion bodies that revealed a peculiar structural pattern. They were irregular in shape and also variable in size. Their structural attributes affected the plastid morphology. The body consisted of a large number of tubular elements, often reaching up to several thousand in number. The tubular elements typically aggregated to form a fluster The elements demonstrated either a parallel or lattice arrangement depending on the sectioning angle. The distance between the elements was approximately 20nm as demonstrated by the diffraction analysis. HVEM examination of the serial sections revealed an occasional fusion or branching of elements within the inclusion bodies. Finally, a three-dimensional reconstruction of the plastid crystalline bodies has been attempted using two different image processing methods.

• Applied Microscopy
• /
• v.39 no.2
• /
• pp.73-80
• /
• 2009

The plastid inclusion has long been known to exist in leaves of numerous plant species, especially in those of flowering plants. Among the inclusions, crystalline bodies are the most frequently distinguished structures of the foliar plastids, however, microtubules and phytoferritins are also reported occasionally. The crystalline inclusions vary in shape, and are located either in the stroma or within intrathylakoidal spaces, whereas microtubules and phytoferritins are more uniform in shape and are formed in the stroma. In crystalline structures, the composing elements exhibit a lattice pattern and/or paralleled tubules that are either bounded by membranes or exist without membrane enclosing. Other types of inclusions have not been shown to be enclosed by any membranous structures. According to the current survey, the plastid inclusion, with the exception of phytoferritins, has been shown to exhibit a crystalline or tubular pattern, and has been reported in more than 56 species of various families. Their occurrence is not restricted to any photosynthetic pathway, but is found to be randomly distributed among C-3, C-4 and CAM species, without phylogenetic relationships. The progress in plastid inclusion research reveals more information about the function and complexity, but the need for characterizing the 3-D structure of the crystalline inclusions also has been acknowledged in previous studies. A 3-D characterization would utilize tilting and tomography of serial sections with appropriate image processing that would provide valuable information on the sub-structures of the crystalline inclusions. In fact, recent studies performed on 3-D reconstruction of the plastid inclusions revealed important information about their comprising elements. In this article, the crystals and microtubules that have been reported in various types of plastids have been reviewed, with special consideration given to their possible sub-cellular function within the plastids.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.224-232
• /
• 2016

The methodology to visualize the shape of blood vessel and its blood flow have been attracting as a very interesting problem to forecast and examinate a disease in thrombus precursor protein. May previous visualization researches have been appeared for designing the blood vessel and also modeling the blood flow using a doppler imaging technique which is one of nondestructive testing techniques. General visualization methods are to depict the blood flow obtained from doppler effects with fragmentary stream lines and also visualize the blood flow model using volume rendering. However, these visualizeation techniques have the disadvantage which a set of small line segments does not give the overall observation of blood flows. Therefore, we propose a visualization system which reconstruct the continuity of the blood flow obtained from doppler effects and also visualize the blood flow with the vector field of blood particles. This system will use doppler phase difference from medical equipments such as OCT with low penetration and reconstruct the blood flow by the curvature estimation from vector field of each blood particle.

• Korean Journal of Bronchoesophagology
• /
• v.16 no.2
• /
• pp.138-144
• /
• 2010

Background: Tracheal deviations are encountered frequently in head and neck tumors especially in thyroid cancer. Dyspnea and stridor are symptom calling for surgery. The method of evaluation in tracheal deviation is not well established yet. This paper is aimed to suggest objective tools to evaluate tracheal deviation in relation to cervical vertebra. Material and Method: Ten cases of thyroid cancers were recruited retrospectively. Tracheal inner shadow and shape of cervical vertebra were reconstructed three dimensionally using 3D-doctor to compare position of trachea in relation to vertebral body. Extent of deviation was scored in relation to both lateral borders of vertebral body. Angles between trachea and spinous process were measured in axial CT and compared between study group and control group. Results: Deviation scores were statistically significant between study group (mean=1.1) and control group (mean=0) (p=0.0008). Deviation angles at maximal tumor size in study group (mean=160.3 Degrees) and deviation angles of control group (mean=177.1 Degrees) were statistically significant (p=0.0007). Angles at maximal deviation of three dimensional images ages in study group (mean=162.6 Degrees) and deviation angles of control group (mean=177.1 Degrees) were statistically significant (p=0.0089). Conclusion: Tracheal deviation can be evaluated using scoring of three dimensional images and measuring angle between trachea and vertebral spine.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.1
• /
• pp.145-149
• /
• 2014

In this study, using X-ray cargo container scanning device and to differentiate the concept of three-dimensional information extraction applied for X-ray scanning device as an ingredient in the rotation of the X-Ray Linear Pushbroom Stereo System by introducing the geometric How to model was introduced. Three-dimensional information obtained through the matching of a single voxel space filled with a random vector operations for each voxel in the three dimensional shape reconstruction algorithm using the definition, and in time, the time required for each step were analyzed. Using OpenCV in each step by applying parallelization techniques approximately 1.8 times improvement in the processing time of the check, but do not meet the target within one minute levels. The other hand, X-ray images by the primary process to convert the point View the results of real-time stereo through a three-dimensional could feel the comfort level.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.247-256
• /
• 2005

One of the classic research problems in computer vision is that of stereo, i.e., the reconstruction of three dimensional shape from two or more images. This paper deals with the problem of extracting depth information of non-rigid dynamic 3D scenes from general 2D video sequences taken by monocular camera, such as movies, documentaries, and dramas. Depth of the blocks are extracted from the resultant block motions throughout following two steps: (i) calculation of global parameters concerned with camera translations and focal length using the locations of blocks and their motions, (ii) calculation of each block depth relative to average image depth using the global parameters and the location of the block and its motion, Both singular and non-singular cases are experimented with various video sequences. The resultant relative depths and ego-motion object shapes are virtually identical to human vision.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.5
• /
• pp.442-450
• /
• 2011

A measurement system using stereo pattern recognition (SPR) method was configured to measure the rotor blade deformations and motions. An SPR-based measurement system was prepared using six stereo cameras. Through a series of experiments to evaluate the system measurement uncertainty, it was verified that the SPR system had less than 0.2mm standard uncertainty. The combined standard uncertainties for the lead-lag, flapping, and pitching motions were estimated as 0.296mm, 0.209mm, and $0.238^{\circ}$, respectively. The SPR system was installed at a general small-scaled rotor test system at Korea Aerospace Research Institute. The blade motions and elastic deformation were successfully measured under the conditions with rotating speeds of 360rpm or 589rpm, and collective pitch angles of $0^{\circ}$, $4^{\circ}$, or $6^{\circ}$. The advantages of the SPR system was analyzed in comparison with the measurement system used in Higher Harmonic Control Aeroacoustic Rotor Test -II.

• Korean Journal of Optics and Photonics
• /
• v.20 no.2
• /
• pp.94-101
• /
• 2009

A novel method for the reconstruction of 3D shape and texture from elemental images has been proposed. Using this method, we can estimate a full 3D polygonal model of objects with seamless triangulation. But in the triangulation process, all the objects are stitched. This generates phantom surfaces that bridge depth discontinuities between different objects. To solve this problem we need to connect points only within a single object. We adopt a segmentation process to this end. The entire process of the proposed method is as follows. First, the central pixel of each elemental image is computed to extract spatial position of objects by correspondence analysis. Second, the object points of central pixels from neighboring elemental images are projected onto a specific elemental image. Then, the center sub-image is segmented and each object is labeled. We used the normalized cut algorithm for segmentation of the center sub-image. To enhance the speed of segmentation we applied the watershed algorithm before the normalized cut. Using the segmentation results, the subdivision process is applied to pixels only within the same objects. The refined grid is filtered with median and Gaussian filters to improve reconstruction quality. Finally, each vertex is connected and an object-based triangular mesh is formed. We conducted experiments using real objects and verified our proposed method.