• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.432-435
• /
• 2019

Convolutional Neural Networks (CNNs) have recently been gaining popularity in the medical image analysis field because of their image segmentation capabilities. In this paper, we present a CNN that performs automated brain tumor segmentations of sparsely annotated 3D Magnetic Resonance Imaging (MRI) scans. Our CNN is based on 3D U-net architecture, and it includes separate Dilated and Depth-wise Convolutions. It is fully-trained on the BraTS 2018 data set, and it produces more accurate results even when compared to the winners of the BraTS 2017 competition despite having a significantly smaller amount of parameters.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.1
• /
• pp.24-34
• /
• 2008

Three dimensional body scan technology is being targeted for utilization in the apparel industry. The purpose of this study was to test reliability of the body scan data targeting from 20 to 24 year old men by comparing 3DM, 3D body-scanning semi-auto measurement extraction method, Scanworx, 3D body-scanning auto measurement extraction method, and traditional anthropometric method. We found significant differences in 9 out of 25 items in upper body measurements using 3DM and 16 out of 25 items using Scanworx. In the range of difference value of scan measures, it showed 1 item in the absolute value of more than 40mm between two measuring methods, 3 items in 20 up to 40mm, and less than 20mm in other items. Overall, in height items, the numerical value of traditional measure was higher and in girth, width, depth items, 3D scan measure was higher. We found out that reliability of 3D measurements taken from whole body scans was different according to scanners, scanning softwares, programs, and subjects.

• Journal of KIBIM
• /
• v.14 no.2
• /
• pp.1-12
• /
• 2024

The paper proposes a methodology that combines the Random Sample Consensus (RANSAC) algorithm and the Point Cloud Encoder-Decoder Network (PCEDNet) algorithm to automatically extract the length of infrastructure elements from point cloud data acquired through 3D LiDAR scans of retaining walls. This methodology is expected to significantly improve time and cost efficiency compared to traditional manual measurement techniques, which are crucial for the data-driven analysis required in the precision-demanding construction sector. Additionally, the extracted positional and dimensional data can contribute to enhanced accuracy and reliability in Scan-to-BIM processes. The results of this study are anticipated to provide important insights that could accelerate the digital transformation of the construction industry. This paper provides empirical data on how the integration of digital technologies can enhance efficiency and accuracy in the construction industry, and offers directions for future research and application.

• Journal of Korean society of Dental Hygiene
• /
• v.19 no.6
• /
• pp.1067-1075
• /
• 2019

Objectives: The present study aimed to compare the accuracy of removable partial denture (RPD) frameworks fabricated by selective laser sintering (SLS) before and after electropolishing. Methods: A partially edentulous mandibular model was used as the working model. Scanning of the model was performed using a dental scanner. The framework was designed using CAD software. The metal framework was formed using an SLS 3D printer. 3D scans of the two fabricated prototypes produced before and after electropolishing were overlapped with reference data. The fit was calculated based on Root Mean Square (RMS). Fabrication accuracy was verified using the paired t-test to compare the discrepancy before and after electropolishing. Results: The mean (SD) values of RMS before and after electropolishing were 126.6 (34.19) and 75.86 (21.36), respectively. There was a statistically significant difference before and after electropolishing (p<0.05). Conclusions: Metal frameworks made with SLS 3D printers showed clinically acceptable fit after electropolishing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1209-1214
• /
• 2020

With the recent aging age, people's interest in healthy life is increasing. People are causing adult diseases or an increasing number of obese populations due to poor lifestyles, eating habits, and poor physical activity. Accordingly, skin beauty research is being conducted using medical information in the information and communication field. Existing systems have not been able to provide smooth information because they are not expressed in combination with various related measurement items. The system proposed in this paper scans the user's body shape using a 3D scanner and a skin care device, calculates the BMI (Body Mass Index) index using 3D image data, and allows you to view the collected data at a glance. Provide a service system. This will provide the user with the content managed by comparing and providing the continuous body change data. It is expected to be widely used in various U-health and beauty fields.

• International Journal of Human Ecology
• /
• v.12 no.1
• /
• pp.87-99
• /
• 2011

Purpose- The purpose of this study was to compare the fit of two prototype liquid cooled vests using a 3D body scanner and accompanying software. The objectives of this study were to obtain quantitative measurements of ease values, and to use these data to evaluate the fit of two cooling vests in active positions and to develop methodological protocol to resolve alignment issues between the scans using software designed for the alignment of 3D objects. Design/methodology/approach- Garment treatments and body positions were two independent variables with three levels each. Quantitative dataset were dependent variables, and were manipulated in 3x3 factorial designs with repeated measures. Scan images from eight subjects were used and ease values were obtained to compare the fit. Two different types of analyses were conducted in order to compare the fit using t-test; those were radial mean distance value analysis and radial distance distribution rate analysis. Findings- Overall prototype II achieved a closer fit than prototype I with both analyses. These were consistent results with findings from a previous study that used a different approach for evaluation. Research limitations/implications- The main findings can be used as practical feedback for prototype modification/selection in the design process, making use of 3D body scanner as an evaluation tool. Originality/value- Methodological protocols that were devised to eliminate potential sources of errors can contribute to application of data from 3D body scanners.

• The Journal of Advanced Prosthodontics
• /
• v.9 no.6
• /
• pp.409-415
• /
• 2017

PURPOSE. Accurate information is essential in dentistry. The image information of missing teeth is used in optically based medical equipment in prosthodontic treatment. To evaluate oral scanners, the standardized model was examined from cases of image recognition errors of linear discriminant analysis (LDA), and a model that combines the variables with reference to ISO 12836:2015 was designed. MATERIALS AND METHODS. The basic model was fabricated by applying 4 factors to the tooth profile (chamfer, groove, curve, and square) and the bottom surface. Photo-type and video-type scanners were used to analyze 3D images after image capture. The scans were performed several times according to the prescribed sequence to distinguish the model from the one that did not form, and the results confirmed it to be the best. RESULTS. In the case of the initial basic model, a 3D shape could not be obtained by scanning even if several shots were taken. Subsequently, the recognition rate of the image was improved with every variable factor, and the difference depends on the tooth profile and the pattern of the floor surface. CONCLUSION. Based on the recognition error of the LDA, the recognition rate decreases when the model has a similar pattern. Therefore, to obtain the accurate 3D data, the difference of each class needs to be provided when developing a standardized model.

• Fashion & Textile Research Journal
• /
• v.19 no.6
• /
• pp.786-794
• /
• 2017

The purpose of this study is to analyze and classify breast shape of women aged 11~15 using 3D body scan data. In this study, 250 women's body scans were selected from the 6th Size Korea dataset, and 30 items from each of the scan were measured using RapidForm XOR 3 program. The principal component analysis and cluster analysis were conducted using statistical program SPSS 17.0. The five principal components were identified; breast drooping and breast capacity, size from chest to under bust area, breast protrusion, breast height, and under breast angle & outer distance of breast. As the results of cluster analysis, woman's breast types were classified into four types. The breast type 1 was protrusion type (25.1%) which is considered as the breast maturity stage. The breast type 2 had the most drooped breast covering a large area (20.2%). The breast type 3 had the least prominent breast with a highest nipple point, which was considered as the early breast development stage (38.9%). The breast type 4 had the obesity of the chest and breast circumferences with the slightly prominent and the least drooped breast (15.8%). This study can provide fundamental information to develop sizing system and brassiere pattern for junior girls.

• ETRI Journal
• /
• v.37 no.3
• /
• pp.606-616
• /
• 2015

In this paper, we propose a novel method for road recognition using 3D point clouds based on a Markov random field (MRF) framework in unstructured and complex road environments. The proposed method is focused on finding a solution for an analysis of traversable regions in challenging environments without considering an assumption that has been applied in many past studies; that is, that the surface of a road is ideally flat. The main contributions of this research are as follows: (a) guidelines for the best selection of the gradient value, the average height, the normal vectors, and the intensity value and (b) how to mathematically transform a road recognition problem into a classification problem that is based on MRF modeling in spatial and visual contexts. In our experiments, we used numerous scans acquired by an HDL-64E sensor mounted on an experimental vehicle. The results show that the proposed method is more robust and reliable than a conventional approach based on a quantity evaluation with ground truth data for a variety of challenging environments.

• The Journal of Advanced Prosthodontics
• /
• v.10 no.5
• /
• pp.335-339
• /
• 2018

PURPOSE. The purpose of the present study was to compare scanning trueness and precision between an abutment impression and a stone model according to dental computer-aided design/computer-aided manufacturing (CAD/CAM) evaluation standards. MATERIALS AND METHODS. To evaluate trueness, the abutment impression and stone model were scanned to obtain the first 3-dimensional (3-D) stereolithography (STL) file. Next, the abutment impression or stone model was removed from the scanner and re-fixed on the table; scanning was then repeated so that 11 files were obtained for each scan type. To evaluate precision, the abutment impression or stone model was scanned to obtain the first 3-D STL file. Without moving it, scanning was performed 10 more times, so that 11 files were obtained for each scan type. By superimposing the first scanned STL file onto the other STL files one by one, 10 color-difference maps and reports were obtained; i.e., 10 experimental scans per type. The independent t-test was used to compare root mean square (RMS) data between the groups (${\alpha}=.05$). RESULTS. The $RMS{\pm}SD$ values of scanning trueness of the abutment impression and stone model were $22.4{\pm}4.4$ and $17.4{\pm}3.5{\mu}m$, respectively (P<.012). The $RMS{\pm}SD$ values of scanning precision of the abutment impression and stone model were $16.4{\pm}2.9$ and $14.6{\pm}1.6{\mu}m$, respectively (P=.108). CONCLUSION. There was a significant difference in scanning trueness between the abutment impression and stone model, as evaluated according to dental CAD/CAM standards. However, all scans showed high trueness and precision.