• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.28-35
• /
• 2006

Statistical models of shape variability based on active shape models (ASMs) have been successfully utilized to perform segmentation and recognition tasks in two-dimensional (2D) images. Three-dimensional (3D) model-based approaches are more promising than 2D approaches since they can bring in more realistic shape constraints for recognizing and delineating the object boundary. For 3D model-based approaches, however, building the 3D shape model from a training set of segmented instances of an object is a major challenge and currently it remains an open problem in building the 3D shape model, one essential step is to generate a point distribution model (PDM). Corresponding landmarks must be selected in all1 training shapes for generating PDM, and manual determination of landmark correspondences is very time-consuming, tedious, and error-prone. In this paper, we propose a novel automatic method for generating 3D statistical shape models. Given a set of training 3D shapes, we generate a 3D model by 1) building the mean shape fro]n the distance transform of the training shapes, 2) utilizing a tetrahedron method for automatically selecting landmarks on the mean shape, and 3) subsequently propagating these landmarks to each training shape via a distance labeling method. In this paper, we investigate the accuracy and compactness of the 3D model for the human liver built from 50 segmented individual CT data sets. The proposed method is very general without such assumptions and can be applied to other data sets.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.1
• /
• pp.32-40
• /
• 2022

The trade-off between morphology and physical function may vary according to ecological traits. Taking a quantitative approach, we attempted to analyze the differences in the skeletal shape of the lower body and limbs in relation to the ecological traits of four anuran species (Dryophytes japonicus, Glandirana rugosa, Pelophylax nigromaculatus, and Lithobates catesbeianus) occurring in South Korea. Body size, locomotor mode, microhabitat, trophic positions, and predator defense mechanisms were selected for the ecological traits of the anurans. The pelvis, ilium, and urostyle, which are associated with locomotor performance, were selected for the skeletal shape of the lower body. The ratio of limbs, which is related to locomotor mode and microhabitat, was confirmed by analyzing the skeletons of the forelimbs (radio-ulnar and humerus) and hindlimbs (femur and tibiofibular). Both landmark-based geometric morphometrics and traditional methods were used for skeletal shape comparison. The skeletal shape of the lower body was completely different among the four species, whereas the ratio of the limbs was only different in D. japonicus. The skeletal shape of the lower body may be related to body mass and predator defense mechanisms, whereas the ratio of the limbs was related to the locomotor mode and microhabitat. Quantifying these morphological differences among various species can help elucidate the mechanisms of behavioral and morphological changes in response to ecological effects.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.1-21
• /
• 2012

In recent years, mobile phone has experienced an extremely fast evolution. It is equipped with high-quality color displays, high resolution cameras, and real-time accelerated 3D graphics. In addition, some other features are includes GPS sensor and Digital Compass, etc. This evolution advent significantly helps the application developers to use the power of smart-phones, to create a rich environment that offers a wide range of services and exciting possibilities. To date mobile AR in outdoor research there are many popular location-based AR services, such Layar and Wikitude. These systems have big limitation the AR contents hardly overlaid on the real target. Another research is context-based AR services using image recognition and tracking. The AR contents are precisely overlaid on the real target. But the real-time performance is restricted by the retrieval time and hardly implement in large scale area. In our work, we exploit to combine advantages of location-based AR with context-based AR. The system can easily find out surrounding landmarks first and then do the recognition and tracking with them. The proposed system mainly consists of two major parts-landmark browsing module and annotation module. In landmark browsing module, user can view an augmented virtual information (information media), such as text, picture and video on their smart-phone viewfinder, when they pointing out their smart-phone to a certain building or landmark. For this, landmark recognition technique is applied in this work. SURF point-based features are used in the matching process due to their robustness. To ensure the image retrieval and matching processes is fast enough for real time tracking, we exploit the contextual device (GPS and digital compass) information. This is necessary to select the nearest and pointed orientation landmarks from the database. The queried image is only matched with this selected data. Therefore, the speed for matching will be significantly increased. Secondly is the annotation module. Instead of viewing only the augmented information media, user can create virtual annotation based on linked data. Having to know a full knowledge about the landmark, are not necessary required. They can simply look for the appropriate topic by searching it with a keyword in linked data. With this, it helps the system to find out target URI in order to generate correct AR contents. On the other hand, in order to recognize target landmarks, images of selected building or landmark are captured from different angle and distance. This procedure looks like a similar processing of building a connection between the real building and the virtual information existed in the Linked Open Data. In our experiments, search range in the database is reduced by clustering images into groups according to their coordinates. A Grid-base clustering method and user location information are used to restrict the retrieval range. Comparing the existed research using cluster and GPS information the retrieval time is around 70~80ms. Experiment results show our approach the retrieval time reduces to around 18~20ms in average. Therefore the totally processing time is reduced from 490~540ms to 438~480ms. The performance improvement will be more obvious when the database growing. It demonstrates the proposed system is efficient and robust in many cases.

• Genomics & Informatics
• /
• v.4 no.1
• /
• pp.1-10
• /
• 2006

Epigenetic alterations are common features of human solid tumors, though global DNA methylation has been difficult to assess. Restriction Landmark Genomic Scanning (RLGS) is one of technology to examine epigenetic alterations at several thousand Notl sites of promoter regions in tumor genome. To assess sequence information for Notl sequences in RLGS gel, we cloned 1,161 unique Notl-linked clones, compromising about 60% of the spots in the soluble region of RLGS profile, and performed BLAT searches on the UCSC genome server, May 2004 Freeze. 1,023 (88%) unique sequences were matched to the CpG islands of human genome showing a large bias of RLGS toward identifying potential genes or CpG islands. The cloned Notl-loci had a high frequency (71%) of occurrence within CpG islands near the 5' ends of known genes rather than within CpG islands near the 3' ends or intragenic regions, making RLGS a potent tool for the identification of gene-associated methylation events. By mixing RLGS gels with all Notl-linked clones, we addressed 151 Notl sequences onto a standard RLGS gel and compared them with previous reports from several types of tumors. We hope our sequence information will be useful to identify novel epigenetic targets in any types of tumor genome.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.1
• /
• pp.40-47
• /
• 2010

This paper presents a simultaneous localization and mapping (SLAM) of an indoor hallway environment using Rao-Blackwellized particle filter (RBPF) along with a line segment as a landmark. Based on the fact that fluent line features can be extracted around the ceiling and side walls of hallway using vision sensor, a horizontal line segment is extracted from an edge image using Hough transform and is also tracked continuously by an optical flow method. A successive observation of a line segment gives initial state of the line in 3D space. For data association, registered feature and observed feature are matched in image space through a degree of overlap, an orientation of line, and a distance between two lines. Experiments show that a compact environmental map can be constructed with small number of horizontal line features in real-time.

• The korean journal of orthodontics
• /
• v.50 no.1
• /
• pp.3-12
• /
• 2020

Objective: This study compared three prominent midsagittal planes (MSPs) to identify the MSP that best approximates the true symmetrical MSP. Methods: Forty-three patients (mean age, 23.0 ± 8.20 years) were grouped as follows: group 1 consisted of 10 patients with skeletal Class I and a menton (Me) deviation of < 2 mm; group 2, 11 patients with skeletal Class III and a Me deviation < 2 mm; group 3, nine patients with skeletal Class III and a Me deviation of 2 to less than 4 mm; and group 4, 13 patients with skeletal Class III and an Me deviation ≥ 4 mm. The candidate MSPs were established by three-dimensional (3D) cone beam computed tomography (CBCT) reorientation methods (RMs): (1) the MSP perpendicular to the Frankfort horizontal (FH) plane while passing through the crista galli and basion; (2) the MSP including the nasion, incisive foramen, and basion; (3) the MSP including the nasion, anterior nasal spine, and posterior nasal spine. The mean absolute distances (MADs) to the MSPs were calculated from the coordinates of 1,548 points on 129 CBCT images. The differences in the values of the 3D coordinates among RMs were compared. Results: The MADs of the three RMs showed significant differences (p < 0.05). Most of the differences in values of the coordinates were not significant among RMs. Conclusions: Although the differences in distance among the three MSPs were minor, the MSP perpendicular to the FH plane while passing through the crista galli and basion best approximated the true symmetrical MSP.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.10
• /
• pp.1139-1145
• /
• 2014

Creation of a human skeleton model and characterization of the variation in the bone shape are fundamentally important in many applications of biomechanics. In this paper, we present a parametric shape modeling method for femurs that is based on extracting the main parameter of variations of the femur shape from a 3D model database by using statistical shape analysis. For this shape analysis, principal component analysis (PCA) is used. Application of the PCA to 3D data requires bringing all the models in correspondence to each other. For this reason, anatomical landmarks are used for guiding the deformation of the template model to fit the 3D model data. After subsequent application of PCA to a set of femur models, we calculate the correlation between the dominant components of shape variability for a target population and the anatomical parameters of the femur shape. Finally, we provide tools for visualizing and creating the femur shape using the main parameter of femur shape variation.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• Journal of Korean Dental Science
• /
• v.14 no.2
• /
• pp.101-109
• /
• 2021

Purpose: For minimally invasive procedures, three-dimensional (3D) anatomical knowledge of the structures of the face is essential. This study aimed to describe the thickness of the skin and subcutaneous tissue and depths of the facial muscles located in the infraorbital region using a 3D scanner to provide critical clinical anatomical guidelines for improving minimally invasive cosmetic procedures. Materials and Methods: The 3D scanning images of 38 Korean cadavers (22 males and 16 females; age range: 51~94 years at the time of death) were analyzed. Eight facial landmarks (P1~P8) were marked on the cadaveric faces. The images were scanned in three steps-undissected face, hemiface after skinning, and revealing the facial muscles. Student's t-test was used to identify significant differences. Result: The skin and subcutaneous tissue tended to become thicker from the upper to lower and medial to lateral aspects, and the muscles followed the same pattern as that of the most superficial located muscle and the deepest located muscles. No significant sex-related differences were found in the skin at any landmark. However, the muscles tended to be deeper in the female participants. Conclusion: The study data can serve as a basis for creating or enhancing clinical anatomy-based guidelines or improving procedures in the infraorbital region.

• Journal of the Korean Arthroscopy Society
• /
• v.12 no.1
• /
• pp.40-44
• /
• 2008

Purpose: The purpose of this study was to report the real geometry of Resident's ridge doing in anterior cruciate ligament reconstruction Materials and Methods: From Jan 2007 to Aug 2007, 48 cases which had normal distal femoral condyle analyzed with Multidetector-Row Computed Tomography. Resident's ridge was defined as change of height above 1 mm in lateral wall of intercondylar notch. Anterior-posterior length of intercondylar notch, length and height of Resident's ridge, distance of Resident's ridge from posterior cortex were estimated with 3-D reconstruction using $Lucion^{(R)}$ program. Results: Cases were $59{\pm}16$ years olds and male was 16 cases, female was 32 cases. 9 cases had no Resident's ridge, anterior-posterior length of intercondylar notch was $25.4{\pm}3.5$ mm, average of length and height of the Resident's ridge was $8.2{\pm}2.6,\;3.5{\pm}1.5$ mm. Distance of the Resident's ridge from posterior cortex was $7.6{\pm}2.6$ mm. Conclusion: Resident's ridge was used as landmark in anterior cruciate ligament reconstruction, which presented in many cases and which had distinct length and height.