• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.326-334
• /
• 2024

Extra-oral imaging techniques such as Panoramic X-rays (PXs) and Cone Beam Computed Tomography (CBCT) are the most preferred imaging modalities in dental clinics owing to its patient convenience during imaging as well as their ability to visualize entire teeth information. PXs are preferred for routine clinical treatments and CBCTs for complex surgeries and implant treatments. However, PXs are limited by the lack of third dimensional spatial information whereas CBCTs inflict high radiation exposure to patient. When a PX is already available, it is beneficial to reconstruct the 3D oral structure from the PX to avoid further expenses and radiation dose. In this paper, we propose 3DentAI - an U-Net based deep learning framework for 3D reconstruction of oral structure from a PX image. Our framework consists of three module - a reconstruction module based on attention U-Net for estimating depth from a PX image, a realignment module for aligning the predicted flattened volume to the shape of jaw using a predefined focal trough and ray data, and lastly a refinement module based on 3D U-Net for interpolating the missing information to obtain a smooth representation of oral cavity. Synthetic PXs obtained from CBCT by ray tracing and rendering were used to train the networks without the need of paired PX and CBCT datasets. Our method, trained and tested on a diverse datasets of 600 patients, achieved superior performance to GAN-based models even with low computational complexity.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.39-44
• /
• 2023

Renewable energy such as solar and wind power is a resource that is sensitive to weather conditions and environmental changes. Since the amount of power generated by a facility can vary depending on the installation location and structure, it is important to accurately predict the amount of power generation. Using meteorological data, a data preprocessing process based on principal component analysis was conducted to monitor the relationship between features that affect energy production prediction. In addition, in this study, the prediction was tested by reconstructing the dataset according to the sensitivity and applying it to the machine learning model. Using the proposed model, the performance of energy production prediction using random forest regression was confirmed by predicting energy production according to the meteorological environment for new and renewable energy, and comparing it with the actual production value at that time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.686-689
• /
• 2018

3D 손 포즈 추정(Hand Pose Estimation, HPE)은 스마트 인간 컴퓨터 인터페이스를 위해서 중요한 기술이다. 이 연구에서는 딥러닝 방법을 기반으로 하여 단일 RGB-Depth 카메라로 촬영한 양손의 3D 손 자세를 실시간으로 인식하는 손 포즈 추정 시스템을 제시한다. 손 포즈 추정 시스템은 4단계로 구성된다. 첫째, Skin Detection 및 Depth cutting 알고리즘을 사용하여 양손을 RGB와 깊이 영상에서 감지하고 추출한다. 둘째, Convolutional Neural Network(CNN) Classifier는 오른손과 왼손을 구별하는데 사용된다. CNN Classifier 는 3개의 convolution layer와 2개의 Fully-Connected Layer로 구성되어 있으며, 추출된 깊이 영상을 입력으로 사용한다. 셋째, 학습된 CNN regressor는 추출된 왼쪽 및 오른쪽 손의 깊이 영상에서 손 관절을 추정하기 위해 다수의 Convolutional Layers, Pooling Layers, Fully Connected Layers로 구성된다. CNN classifier와 regressor는 22,000개 깊이 영상 데이터셋으로 학습된다. 마지막으로, 각 손의 3D 손 자세는 추정된 손 관절 정보로부터 재구성된다. 테스트 결과, CNN classifier는 오른쪽 손과 왼쪽 손을 96.9%의 정확도로 구별할 수 있으며, CNN regressor는 형균 8.48mm의 오차 범위로 3D 손 관절 정보를 추정할 수 있다. 본 연구에서 제안하는 손 포즈 추정 시스템은 가상 현실(virtual reality, VR), 증강 현실(Augmented Reality, AR) 및 융합 현실 (Mixed Reality, MR) 응용 프로그램을 포함한 다양한 응용 분야에서 사용할 수 있다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.6
• /
• pp.1-10
• /
• 2005

This paper describes the implementation of HTML converter for wireless internet access in wireless application protocol environment. The implemented HTML converter consists of the contents conversion module, the conversion rule set, the WML file generation module, and the frame contents reformatting module. Plain text contents are converted to WML contents through one by one mapping, referring to the converting rule set in the contents converting module. For frame contents, the first frameset sources are parsed and the request messages are reconstructed with all the file names, reconnecting to web server as much as the number of files to receive each documents and append to the first document. Finally, after the process of reformatting in the frame contents reformatting module, frame contents are converted to WML's table contents. For image map contents, the image map related tags are parsed and the names of html documents which are linked to any sites are extracted to be replaced with WML contents data and linked to those contents. The proposed conversion method for frame contents provides a better interface for the users convenience and interactions compared to the existing converters. Conversion of image maps in our converter is one of the features not currently supported by other converters.

• KIISE Transactions on Computing Practices
• /
• v.21 no.11
• /
• pp.681-688
• /
• 2015

The k nearest neighbor (k-NN) graph construction is an important operation with many web-related applications, including collaborative filtering, similarity search, and many others in data mining and machine learning. Despite its many elegant properties, the brute force k-NN graph construction method has a computational complexity of $O(n^2)$, which is prohibitive for large scale data sets. Thus, (Key, Value)-based distributed framework, MapReduce, is gaining increasingly widespread use in Locality Sensitive Hashing which is efficient for high-dimension and sparse data. Based on the two-stage strategy, we engage the locality sensitive hashing technique to divide users into small subsets, and then calculate similarity between pairs in the small subsets using a brute force method on MapReduce. Specifically, generating a candidate group stage is important since brute-force calculation is performed in the following step. However, existing methods do not prevent large candidate groups. In this paper, we proposed an efficient algorithm for approximate k-NN graph construction by regrouping candidate groups. Experimental results show that our approach is more effective than existing methods in terms of graph accuracy and scan rate.

• Journal of Navigation and Port Research
• /
• v.38 no.4
• /
• pp.385-390
• /
• 2014

Simulator is composed of several devices that have a variety of forms and functions. These devices are connected to each other by a network intricately. For this reason, simulator development and maintenance process require a lot of time and money. In order to successfully develop the simulator, it is ideal that related professionals share the work and work together in parallel. However, development is carried out inefficiently, because task interdependence makes it difficult to work in parallel. In this paper, the developments of the simulator were classified into algorithm development and system development, and it was discussed how to lower the interdependence of these two tasks and support professionals. In particular, based on the requirements analysis of the domain experts responsible for the development of the algorithm, we designed the support tool for simulator development and proposed development process using this tool. We also introduced the concept of a DataSet in order to support algorithm development of domain experts and manage data flexibly. And we designed network architecture to enable flexible reconfiguration of simulator equipment. By using the tools to support the simulator development, domain experts are able to concentrate on algorithm development and it is expected to be effective collaboration. In addition, the development plan and management are expected to be easy because the development process is systematic and clearer.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.9-16
• /
• 2020

In the Image processing and computer vision, the problem of reconstructing from one image to another or generating a new image has been steadily drawing attention as hardware advances. However, the problem of computer-generated images also continues to emerge when viewed with human eyes because it is not natural. Due to the recent active research in deep learning, image generating and improvement problem using it are also actively being studied, and among them, the network called Generative Adversarial Network(GAN) is doing well in the image generating. Various models of GAN have been presented since the proposed GAN, allowing for the generation of more natural images compared to the results of research in the image generating. Among them, pix2pix is a conditional GAN model, which is a general-purpose network that shows good performance in various datasets. pix2pix is based on U-Net, but there are many networks that show better performance among U-Net based networks. Therefore, in this study, images are generated by applying various networks to U-Net of pix2pix, and the results are compared and evaluated. The images generated through each network confirm that the pix2pix model with Attention, R2, and Attention-R2 networks shows better performance than the existing pix2pix model using U-Net, and check the limitations of the most powerful network. It is suggested as a future study.

• Progress in Medical Physics
• /
• v.25 no.4
• /
• pp.233-241
• /
• 2014

The aim of this study is to develop a new software tool for 3D dose verification using $PRESAGE^{REU}$ Gel dosimeter. The tool included following functions: importing 3D doses from treatment planning systems (TPS), importing 3D optical density (OD), converting ODs to doses, 3D registration between two volumetric data by translational and rotational transformations, and evaluation with 3D gamma index. To acquire correlation between ODs and doses, CT images of a $PRESAGE^{REU}$ Gel with cylindrical shape was acquired, and a volumetric modulated arc therapy (VMAT) plan was designed to give radiation doses from 1 Gy to 6 Gy to six disk-shaped virtual targets along z-axis. After the VMAT plan was delivered to the targets, 3D OD data were reconstructed from 512 projection data from $Vista^{TM}$ optical CT scanner (Modus Medical Devices Inc, Canada) per every 2 hours after irradiation. A curve for converting ODs to doses was derived by comparing TPS dose profile to OD profile along z-axis, and the 3D OD data were converted to the absorbed doses using the curve. Supra-linearity was observed between doses and ODs, and the ODs were decayed about 60% per 24 hours depending on their magnitudes. Measured doses from the $PRESAGE^{REU}$ Gel were well agreed with the TPS doses at central region, but large under-doses were observed at peripheral region at the cylindrical geometry. Gamma passing rate for 3D doses was 70.36% under the gamma criteria of 3% of dose difference and 3 mm of distance to agreement. The low passing rate was resulted from the mismatching of the refractive index between the PRESAGE gel and oil bath in the optical CT scanner. In conclusion, the developed software was useful for 3D dose verification from PRESAGE gel dosimetry, but further improvement of the Gel dosimetry system were required.