• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.2
• /
• pp.28-33
• /
• 2017

Recently, the operation of precision pocket machining has been studied for the high speed and accuracy in industry to increase production and quality. Moreover, the demand for products with complex 3D free-curved surface shapes has increasing rapidly in the development of computer systems, CNC machining, and CAM software in various manufacturing fields, especially in automotive engineering. The type of aluminum (Al6061) that is widely used in aerospace fields was used in this study, and end-mill down cutting was conducted in fillet cutting at a corner with end-mill tools for various process conditions. The experimental results may demonstrate that the end mill cutter with four blades is more advantageous than that of the two blades on shape forming in the same condition precise machining conditions. It was also found that cutting forces and tool deformation increased as the cutting speed increased. When the tool was located at $45^{\circ}$ (four locations), the corner was found to conduct the maximum cutting force rather than the start point of the workpiece. The experimental research is expected to increase efficiency when the economical precision machining methods are required for various cutting conditions in industry.

• Journal of the Korean Academy of Esthetic Dentistry
• /
• v.25 no.2
• /
• pp.68-78
• /
• 2016

Recently, digital technology has become increasingly prevalent in the dental clinic. Using a milling machine for clinic, it is possible to produce provisional restoration inside the clinic. This can promote large clinical cases such as full mouth rehabilitation with the help of a tabletop scanner, which is capable of semi-adjustable articulator equipment, and a powerful dental CAD software with excellent user convenience. In this case report, a full-mouth rehabilitation was done with digital technology to a 55 year-old female patient, who has lost vertical dimension through the attrition, and has got inclined occlusal plane with unplanned and repeated dental reconstruction. Through the design and milling of the provisional restoration in the clinic and the duplication of these provisionals by double scanning technique, a good functional and esthetic result could be achieved.

• Journal of the Korean Academy of Esthetic Dentistry
• /
• v.25 no.2
• /
• pp.88-97
• /
• 2016

Aesthetics can be affected by the interest and the trend of the time. There are the limits of the equipment and materials required for the times, aesthetic case is also considered necessary to overcome them and will introduce the following case in accordance with the patients demands and circumstances. I hope the further development of CAD/CAM by taking over the things have done in the analogue by utilizing the latest technology that is thought to challenge the current limit itself is important. Digital has the advantages in various perspectives. Especially, I am very interested in as related to "digital communication." In particular, when utilizing the data using intra oral scanner can easily direct converse about prosthesis between the dentist and the dental technician through a software program Now, as the digital communication affects the integrity of the prosthesis directly, I had a expectation of a new era for the prosthetic and aesthetics. In this case report, I would like to introduce direct and real digital communication through the following 2 parts.

• The Journal of Advanced Prosthodontics
• /
• v.10 no.4
• /
• pp.328-334
• /
• 2018

PURPOSE. To evaluate the reproducibility of scan-based abutments using a blue light model scanner. MATERIALS AND METHODS. A wax cast abutment die was fabricated, and a silicone impression was prepared using a silicone material. Nine study dies were constructed using the prepared duplicable silicone, and the first was used as a reference. These dies were classified into three groups and scanned using a blue light model scanner. The first three-dimensional (3D) data set was obtained by scanning eight dies separately in the first group. The second 3D data set was acquired when four dies were placed together in the scanner and scanned twice in the second group. Finally, the third 3D data set was obtained when eight dies were placed together in the scanner and scanned once. These data were then used to define the data value using third-dimension software. All the data were then analyzed using the non-parametric Kruskal-Wallis H test (${\alpha}=.05$) and the post-hoc Mann-Whitney U-test with Bonferroni's correction (${\alpha}=.017$). RESULTS. The means and standard deviations of the eight dies together were larger than those of the four dies together and of the individual die. Moreover, significant differences were observed among the three groups (P<.05). CONCLUSION. With larger numbers of abutments scanned together, the scan becomes more inaccurate and loses reproducibility. Therefore, scans of smaller numbers of abutments are recommended to ensure better results.

• Journal of Technologic Dentistry
• /
• v.40 no.3
• /
• pp.115-123
• /
• 2018

Purpose: The purpose of this study was establishing process of manufacturing dental prosthesis by using eZIS system(DDS Inc.,Korea). Methods: To evaluate accuracy verification, the test was practiced two ways. First, Comparison of 3D printing models and stone models was practiced by using 3D superimposing software. #36 prepared master model was scanned by eZIS system and three 'Veltz3D' 3D printing models and three 'Bio3D' 3D printing models were manufactured. three stone models were manufactured by conventional impression technique. Second, Fitness test was practiced. the 3D printing models and the stone models was compared by manufacturing same resin crown. #36 prepared master model was scanned 9 times and manufactured (milled) 9 resin crowns by eZIS system. These crowns were cemented three 'Veltz3D' 3D printing models, three 'Bio3D' 3D printing models and three stone models. These crowns were sliced mesiodistal axis and gaps were measured by digital microscope. Results: The average accuracy of Bio3D models were 65.75%. Veltz3D(Hebsiba) models were 60.11% Stone models were 41.00%. Conclusion : This study results showed 3D printing model is similar with stone model. So it was under clinical allow, didn't affect final dental prothesis. There were no significant differences in the appearance of the three types of milling crowns.

• International Journal of CAD/CAM
• /
• v.6 no.1
• /
• pp.9-17
• /
• 2006

Performing inspections for Hull Condition Monitoring and Assessment as stipulated in IACS unified requirements and IMO's Condition Assessment Scheme (CAS) IMO Resolution MEPC.94(46), 2001, Condition Assessment Scheme, IMO Resolution MEPC.111(50), 2003, Amendments to regulation 13G, addition of new regulation 13H involves a huge amount of measurement data to be collected, processed, analysed and maintained. Information to be recorded consists of thickness measurements and visual assessment of coating and cracks. The amount of data and increasing requirements with respect to condition assessment demand efficient computer support. Currently, due to the lack of standardization for this kind of data, the thickness measurements are recorded manually on ship drawings or tables. In this form, handling of the measurements is tedious and error-prone and assessment is difficult. Data reporting and analysis takes a long time, leading to some repairs being performed only at the next docking of the ship or making an additional docking necessary. The recently started ED funded project CAS addresses this topic and develops-as a first step-a data model for Hull Condition Monitoring and Assessment (HCMA) based on XML-technology. The model includes simple geometry representation to facilitate a graphically supported data collection as well as an easy visualisation of the measurement results. In order to ensure compatibility with the current way of working, the content of the data model is strictly confined to the requirements of the measurement process. Appropriate data interfaces to classification software will enable rapid assessment by the classification societies, thus improving the process in terms of time and cost savings. In particular, decision-making can be done while the ship is still in the dock for maintenance.

• The Journal of Advanced Prosthodontics
• /
• v.9 no.4
• /
• pp.239-243
• /
• 2017

PURPOSE. The purpose of this study is to compare single and three-unit metal frameworks that are produced by micro-stereolithography. MATERIALS AND METHODS. Silicone impressions of a selected molar and a premolar were used to make master abutments that were scanned into a stereolithography file. The file was processed with computer aided design software to create single and three-unit designs from which resin frameworks were created using micro-stereolithography. These resin frameworks were subjected to investment, burnout, and casting to fabricate single and three-unit metal ones that were measured under a digital microscope by using the silicone replica technique. The measurements were verified by means of the Mann-Whitney U test (${\alpha}=.05$). RESULTS. The marginal gap was $101.9{\pm}53.4{\mu}m$ for SM group and $104.3{\pm}62.9{\mu}m$ for TUM group. The measurement of non-pontics in a single metal framework was $93.6{\pm}43.9{\mu}m$, and that of non-pontics in a three-unit metal framework was $64.9{\pm}46.5{\mu}m$. The dimension of pontics in a single metal framework was $110.2{\pm}61.4{\mu}m$, and that of pontics in a three-unit metal framework was $143.7{\pm}51.8{\mu}m$. CONCLUSION. The marginal gap was smaller for the single metal framework than for the three-unit one, which requires further improvement before it can be used for clinical purposes.

• The Journal of Advanced Prosthodontics
• /
• v.9 no.4
• /
• pp.252-256
• /
• 2017

PURPOSE. This in vitro study aimed to analyze and compare the reproducibility of zirconia and lithium disilicate crowns manufactured by digital workflow. MATERIALS AND METHODS. A typodont model with a prepped upper first molar was set in a phantom head, and a digital impression was obtained with a video intraoral scanner (CEREC Omnicam; Sirona GmbH), from which a single crown was designed and manufactured with CAD/CAM into a zirconia crown and lithium disilicate crown (n=12). Reproducibility of each crown was quantitatively retrieved by superimposing the digitized data of the crown in 3D inspection software, and differences were graphically mapped in color. Areas with large differences were analyzed with digital microscopy. Mean quadratic deviations (RMS) quantitatively obtained from each ceramic group were statistically analyzed with Student's t-test (${\alpha}=.05$). RESULTS. The RMS value of lithium disilicate crown was $29.2\;(4.1){\mu}m$ and $17.6\;(5.5){\mu}m$ on the outer and inner surfaces, respectively, whereas these values were $18.6\;(2.0){\mu}m$ and $20.6\;(5.1){\mu}m$ for the zirconia crown. Reproducibility of zirconia and lithium disilicate crowns had a statistically significant difference only on the outer surface (P<.001). The outer surface of lithium disilicate crown showed over-contouring on the buccal surface and under-contouring on the inner occlusal surface. The outer surface of zirconia crown showed both over- and under-contouring on the buccal surface, and the inner surface showed under-contouring in the marginal areas. CONCLUSION. Restoration manufacturing by digital workflow will enhance the reproducibility of zirconia single crowns more than that of lithium disilicate single crowns.

• The Journal of Advanced Prosthodontics
• /
• v.10 no.5
• /
• pp.354-360
• /
• 2018

PURPOSE. To compare and analyze trueness and precision of provisional crowns made using stereolithography apparatus and subtractive technology. MATERIALS AND METHODS. Digital impressions were made using a master model and an intraoral scanner and the crowns were designed with CAD software; in total, 22 crowns were produced. After superimposing CAD design data and scan data using a 3D program, quantitative and qualitative data were obtained for analysis of trueness and precision. Statistical analysis was performed using normality test combined with Levene test for equal variance analysis and independent sample t-test. Type 1 error was set at 0.05. RESULTS. Trueness for the outer and inner surfaces of the SLA crown (SLAC) were $49.6{\pm}9.3{\mu}m$ and $22.5{\pm}5.1{\mu}m$, respectively, and those of the subtractive crown (SUBC) were $31.8{\pm}7.5{\mu}m$ and $14.6{\pm}1.2{\mu}m$, respectively. Precision values for the outer and inner surfaces of the SLAC were $18.7{\pm}6.2{\mu}m$ and $26.9{\pm}8.5{\mu}m$, and those of the SUBC were $25.4{\pm}3.1{\mu}m$ and $13.8{\pm}0.6{\mu}m$, respectively. Trueness values for the outer and inner surfaces of the SLAC and SUBC showed statistically significant differences (P<.001). Precision for the inner surface showed significance (P<.03), whereas that for the outer surface showed no significance (P<.58). CONCLUSION. The study demonstrates that provisional crowns produced by subtractive technology are superior to crowns fabricated by stereolithography in terms of accuracy.