• Imaging Science in Dentistry
• /
• v.51 no.3
• /
• pp.299-306
• /
• 2021

Purpose: This study aimed to propose a fully automatic landmark identification model based on a deep learning algorithm using real clinical data and to verify its accuracy considering inter-examiner variability. Materials and Methods: In total, 950 lateral cephalometric images from Yonsei Dental Hospital were used. Two calibrated examiners manually identified the 13 most important landmarks to set as references. The proposed deep learning model has a 2-step structure-a region of interest machine and a detection machine-each consisting of 8 convolution layers, 5 pooling layers, and 2 fully connected layers. The distance errors of detection between 2 examiners were used as a clinically acceptable range for performance evaluation. Results: The 13 landmarks were automatically detected using the proposed model. Inter-examiner agreement for all landmarks indicated excellent reliability based on the 95% confidence interval. The average clinically acceptable range for all 13 landmarks was 1.24 mm. The mean radial error between the reference values assigned by 1 expert and the proposed model was 1.84 mm, exhibiting a successful detection rate of 36.1%. The A-point, the incisal tip of the maxillary and mandibular incisors, and ANS showed lower mean radial error than the calibrated expert variability. Conclusion: This experiment demonstrated that the proposed deep learning model can perform fully automatic identification of cephalometric landmarks and achieve better results than examiners for some landmarks. It is meaningful to consider between-examiner variability for clinical applicability when evaluating the performance of deep learning methods in cephalometric landmark identification.

• The korean journal of orthodontics
• /
• v.54 no.1
• /
• pp.48-58
• /
• 2024

Objective: To quantify the effects of midline-related landmark identification on midline deviation measurements in posteroanterior (PA) cephalograms using a cascaded convolutional neural network (CNN). Methods: A total of 2,903 PA cephalogram images obtained from 9 university hospitals were divided into training, internal validation, and test sets (n = 2,150, 376, and 377). As the gold standard, 2 orthodontic professors marked the bilateral landmarks, including the frontozygomatic suture point and latero-orbitale (LO), and the midline landmarks, including the crista galli, anterior nasal spine (ANS), upper dental midpoint (UDM), lower dental midpoint (LDM), and menton (Me). For the test, Examiner-1 and Examiner-2 (3-year and 1-year orthodontic residents) and the Cascaded-CNN models marked the landmarks. After point-to-point errors of landmark identification, the successful detection rate (SDR) and distance and direction of the midline landmark deviation from the midsagittal line (ANS-mid, UDM-mid, LDM-mid, and Me-mid) were measured, and statistical analysis was performed. Results: The cascaded-CNN algorithm showed a clinically acceptable level of point-to-point error (1.26 mm vs. 1.57 mm in Examiner-1 and 1.75 mm in Examiner-2). The average SDR within the 2 mm range was 83.2%, with high accuracy at the LO (right, 96.9%; left, 97.1%), and UDM (96.9%). The absolute measurement errors were less than 1 mm for ANS-mid, UDM-mid, and LDM-mid compared with the gold standard. Conclusions: The cascaded-CNN model may be considered an effective tool for the auto-identification of midline landmarks and quantification of midline deviation in PA cephalograms of adult patients, regardless of variations in the image acquisition method.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.23 no.3
• /
• pp.197-203
• /
• 2007

Statement of problem: It is very important to establish the suitable position for artificial maxillary anterior teeth and the orientation of occlusal plane in fabrication of the complete dentures. Incisive papilla has been considered the most useful anatomic landmark in the arranging of a maxillary anterior artificial teeth. Purpose: To determine correct position of upper anterior artificial teeth in complete denture patients, relationship of incisive papilla, intercanine line, occlusal plane were evaluated in Korean adults. Materials and Method: Maxillary casts were made in 60 Korean dentate subjects. Each cast was mounted in Hanau modular articulator using Hanau spring bow. Then, anatomic landmarks were determined in each cast. Distance from central incisor to incisive papilla, distance from incisive papilla to intercanine line and discrepancies between frankfurt plane and occlusal plane were measured and analysed. Results: 1. The mean distance between the posterior point of incisive papilla and the incisal edge of central incisor was 11.20 mm (in male 11.77 mm, in female 10.55 mm) and there was no significant difference in measured values between male and female 2. The mean distance between the posterior point of incisive papilla and intercanine line was 2.52 mm (Male 2.57 mm, Female 2.35 mm) and there were no significant differencies in measured values between male and female 3. The mean discripancy between the Frankfurt plane and the occlusal plane were 9. 75 degree (Male 9.81 degree, Female 9.55 degree), and there was no significant difference in measured values between left and right sides.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.1
• /
• pp.35-45
• /
• 2007

The log data collected from mobile devices contains diverse meaningful and practical personal information. However, this information is usually ignored because of its limitation of memory capacity, computation power and analysis. We propose a novel method that detects landmarks of meaningful information for users by analyzing the log data in distributed modules to overcome the problems of mobile environment. The proposed method adopts Bayesian probabilistic approach to enhance the inference accuracy under the uncertain environments. The new cooperative modularization technique divides Bayesian network into modules to compute efficiently with limited resources. Experiments with artificial data and real data indicate that the result with artificial data is amount to about 84% precision rate and about 76% recall rate, and that including partial matching with real data is about 89% hitting rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1279-1292
• /
• 2022

This study proposes a non-contact input method based on face recognition and Pyautogui mouse control as a system that can help users who have difficulty using input devices such as conventional mouse due to physical discomfort. This study includes features that help web surfing more conveniently, especially screen zoom, scroll function, and also solves the problem of eye fatigue, which has been suggested as a limitation in existing non-contact input systems. In addition, various set values can be adjusted in consideration of individual physical differences and Internet usage habits. Furthermore, no high-performance CPU or GPU environment is required, and no separate tracker devices or high-performance cameras are required. Through these studies, we intended to contribute to the realization of barrier-free access by increasing the web accessibility of the disabled and the elderly who find it difficult to use web content.

• Korean Institute of Interior Design Journal
• /
• v.22 no.2
• /
• pp.157-166
• /
• 2013

The underground space of urban entertainment center can do various roles for urban development. Especially, the design of underground space using natural elements is necessary to sustainable development of facilities. The purpose of this study is to propose the elements, characteristics and application around interior environmental design using natural elements in underground space of urban entertainment center. The research methods of this study are research references, survey and field-study. This study can be concluded as follows; First, the factors of interior environmental design using natural elements in underground space of urban entertainment center are 'landmarks expression of natural elements', 'introduction and planning of daylighting', 'planning of materials using natural images', 'planning of ecological footpath' and 'planning of energy recycling'. Second, pedestrian space and openspace considering regional context are necessary. Third, introduction of daylight and design of artificial lighting in underground space are needed to making eco-friendly environment. Fourth, landmark design using various natural elements in underground space is needed to provide eco-friendly amenity. Fifth, the interior environmental design using natural elements is needed to community space in underground space. Sixth, eco-friendly pedestrian space in underground space is necessary. Seventh, interior environmental design using natural elements is needed to the entrance of underground space of urban entertainment center.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.688-693
• /
• 2010

Vision based object recognition in mobile robots has many issues for image analysis problems with neighboring elements in dynamic environments. SURF(Speeded Up Robust Features) is the local feature extraction method of the image and its performance is constant even if disturbances, such as lighting, scale change and rotation, exist. However, it has a difficulty of real-time processing caused by representation of high dimensional vectors. To solve th problem, execution of SURF in GPU(Graphics Processing Unit) is proposed and implemented using CUDA of NVIDIA. Comparisons of recognition rates and processing time for SURF between CPU and GPU by variation of robot velocity and image sizes is experimented.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.9 s.252
• /
• pp.1124-1133
• /
• 2006

This paper addresses the localization and navigation problem using invisible two dimensional barcodes on the floor. Compared with other methods using natural/artificial landmark, the proposed localization method has great advantages in cost and appearance, since the location of the robot is perfectly known using the barcode information after the mapping is finished. We also propose a navigation algorithm which uses the topological structure. For the topological information, we define nodes and edges which are suitable for indoor navigation, especially for large area having multiple rooms, many walls and many static obstacles. The proposed algorithm also has an advantage that errors occurred in each node are mutually independent and can be compensated exactly after some navigation using barcode. Simulation and experimental results. were performed to verify the algorithm in the barcode environment, and the result showed an excellent performance. After mapping, it is also possible to solve the kidnapped case and generate paths using topological information.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.560-566
• /
• 2005

In this paper, a practical technique for correction of a distorted image for vision-based localization of ubiquitous mobile robot. The localization of mobile robot is essential and is realized by using camera vision system. In order to wide the view angle of camera, the vision system includes a fish-eye lens, which distorts the image. Because a mobile robot moves rapidly, the image processing should he fast to recognize the localization. Thus, we propose the practical correction technique for a distorted image, verify the Performance by experimental test.

• Land and Housing Review
• /
• v.6 no.4
• /
• pp.221-229
• /
• 2015

Large trees in the apartment complex are playing an important role to decide the quality of external environment. They are planted with the object of utilizing themselves as a landmark of the complex and enhancing space symbolism. Since planting large trees would require high maintenance costs and generate defect, it would cause decline in quality of external environment. This study researches on large trees in artificial ground of the apartment complex. This study analyzes actual condition of planting and tries to provide improvement direction of planting. In order to conduct this research, three target areas (over R30) and 265 trees are selected. Based on the drawings and specifications this study researches on the plan of landscape design, changes of field design, actual condition of completion, present condition of planting, minimum soil depth of growth and development and types of extra action for soil depth. The result shows that 85% of drawings and specifications for large trees in the apartment complex are deep-rooted tree species. On average large trees with R 35 are planted in artificial ground and there is lack of on average 65cm minimum soil depth of growth and development. Reviewing changes of field design is conducted in such limited size as mainly R30 and R40 and there is no extra plan for lack of soil depth. The plan for securing additional soil depth is done by 85% of mounding. However, since there is only 10% of satisfaction, the inappropriateness in securing additional soil is pointed out. This research also points out that the size of large trees, root characteristics and location-allocation for planting are pivotal factors for securing minimum soil depth of growth and development. This research also provides improvement direction in case of planning planting.