• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.277-278
• /
• 2021

최근 손동작 인식에 대한 연구들이 활발하다. 하지만 대부분 Depth 정보를 포함한3D 정보를 필요로 한다. 이는 기존 연구들이 Depth 카메라 없이는 동작하지 않는다는 한계점이 있다는 것을 의미한다. 본 프로젝트는 Depth 카메라를 사용하지 않고 2D 이미지에서 Hand Keypoint Detection을 통해 손동작 인식을 하는 방법론을 제안한다. 학습 데이터 셋으로 Facebook에서 제공하는 InterHand2.6M 데이터셋[1]을 사용한다. 제안 방법은 크게 두 단계로 진행된다. 첫째로, Object Detection으로 Hand Detection을 수행한다. 데이터 셋이 어두운 배경에서 촬영되어 실 사용 환경에서 Detection 성능이 나오지 않는 점을 해결하기 위한 이미지 합성 Augmentation 기법을 제안한다. 둘째로, Keypoint Detection으로 21개의 Hand Keypoint들을 얻는다. 실험을 통해 유의미한 벡터들을 생성한 뒤 Annoy (Approximate nearest neighbors Oh Yeah) Tree를 생성한다. 생성된 Annoy Tree들로 후처리 작업을 거친 뒤 최종 Pose Estimation을 완료한다. Annoy Tree를 사용한 Pose Estimation에서는 NN(Neural Network)을 사용한 것보다 빠르며 동등한 성능을 냈다.

• Imaging Science in Dentistry
• /
• v.44 no.3
• /
• pp.213-220
• /
• 2014

Purpose: This study was performed to determine the efficacy of observers' prediction for the need of bone grafting and presence of perioperative complications on the basis of cone-beam computed tomography (CBCT) and panoramic radiographic (PAN) planning as compared to the surgical outcome. Materials and Methods: One hundred and eight partially edentulous patients with a need for implant rehabilitation were referred for preoperative imaging. Imaging consisted of PAN and CBCT images. Four observers carried out implant planning using PAN image datasets, and at least one month later, using CBCT image datasets. Based on their own planning, the observers assessed the need for bone graft augmentation as well as complication prediction. The implant length and diameter, the need for bone graft augmentation, and the occurrence of anatomical complications during planning and implant placement were statistically compared. Results: In the 108 patients, 365 implants were installed. Receiver operating characteristic analyses of both PAN and CBCT preoperative planning showed that CBCT performed better than PAN-based planning with respect to the need for bone graft augmentation and perioperative complications. The sensitivity and the specificity of CBCT for implant complications were 96.5% and 90.5%, respectively, and for bone graft augmentation, they were 95.2% and 96.3%, respectively. Significant differences were found between PAN-based planning and the surgery of posterior implant lengths. Conclusion: Our findings indicated that CBCT-based preoperative implant planning enabled treatment planning with a higher degree of prediction and agreement as compared to the surgical standard. In PAN-based surgery, the prediction of implant length was poor.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.57-66
• /
• 2023

In this study, we propose a novel research framework for the recommendation system that can estimate the user's emotional state and reflect it in the recommendation process by applying deep learning techniques and emotion AI (artificial intelligence). To this end, we build an emotion classification model that classifies each of the seven emotions of angry, disgust, fear, happy, sad, surprise, and neutral, respectively, and propose a model that can reflect this result in the recommendation process. However, in the general emotion classification data, the difference in distribution ratio between each label is large, so it may be difficult to expect generalized classification results. In this study, since the number of emotion data such as disgust in emotion image data is often insufficient, correction is made through augmentation. Lastly, we propose a method to reflect the emotion prediction model based on data through image augmentation in the recommendation systems.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1707-1720
• /
• 2023

With the increase in satellite time series data, the utility of remote sensing data is growing. In the analysis of time series data, the relative positional accuracy between images has a significant impact on the results, making image registration essential for correction. In recent years, research on image registration has been increasing by applying deep learning, which outperforms existing image registration algorithms. To train deep learning-based registration models, a large number of image pairs are required. Additionally, creating a correlation map between the data of existing deep learning models and applying additional computations to extract registration points is inefficient. To overcome these drawbacks, this study developed a data augmentation technique for training image registration models and applied it to OffsetNet, a registration model that predicts the offset amount itself, to perform image registration for KOMSAT-2, -3, and -3A. The results of the model training showed that OffsetNet accurately predicted the offset amount for the test data, enabling effective registration of the master and slave images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.521-523
• /
• 2021

Data augmentation are techniques used to increase the amount of data by using small amount of existing data. With the spread of the Internet, we can easily obtain data. However, there are still certain industries, like medicine, where it is difficult to obtain data. The same is true for image data in which a black screen is displayed on video wall controller. Because it is rare that a black screen is displayed during operation, it is not easy to obtain an image with a black screen. We propose a DCGAN based architecture that generate dataset using a small amount of black screen image.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.55-65
• /
• 2022

Recently, deep learning-based automated systems for identifying and detecting landmarks have been proposed. In order to train such a deep learning-based model without overfitting, a large amount of image and labeling data is required. Conventionally, an experienced reader manually identifies and labels landmarks in a patient's image. However, such measurement is not only expensive, but also has poor reproducibility, so the need for an automated labeling method has been raised. In addition, in the X-ray image, since various human tissues on the path through which the photons pass are displayed, it is difficult to identify the landmark compared to a general natural image or a 3D image modality image. In this study, we propose a geometric data augmentation technique that enables the generation of a large amount of labeling data in X-ray images. In addition, the optimal attention mechanism for landmark detection was presented through the implementation and application of various attention techniques to improve the detection performance of 16 major landmarks in the skull. Finally, among the major cranial landmarks, markers that ensure stable detection are derived, and these markers are expected to have high clinical application potential.

• Journal of Convergence for Information Technology
• /
• v.10 no.11
• /
• pp.1-8
• /
• 2020

As power consumption is maximized, research on augmented reality-based monitoring systems for on-site facility managers to maintain and repair power facilities is being actively conducted as individual power brokerages and power production facilities increase. However, in the case of existing augmented reality-based monitoring systems, it is difficult to accurately detect patterns due to problems such as external environment, facility complexity, and interference with the lighting environment, and it is not possible to match various sensing information and service information for power facilities to one pattern. there is a problem. For this reason, since sensor information is matched using a single image pattern for each sensor of a power facility, a plurality of image patterns are required to augment and provide all information. In this paper, we propose a single image pattern arrangement method that matches and provides a plurality of information through an array combination of feature patterns in a single image composed of a plurality of feature patterns.

• Tunnel and Underground Space
• /
• v.29 no.3
• /
• pp.184-196
• /
• 2019

This study aims to extract a 3D image of micro-cracks generated by hydraulic fracturing tests, using the deep learning method and X-ray computed tomography images. The pixel-level cracks are difficult to be detected via conventional image processing methods, such as global thresholding, canny edge detection, and the region growing method. Thus, the convolutional neural network-based encoder-decoder network is adapted to extract and analyze the micro-crack quantitatively. The number of training data can be acquired by dividing, rotating, and flipping images and the optimum combination for the image augmentation method is verified. Application of the optimal image augmentation method shows enhanced performance for not only the validation dataset but also the test dataset. In addition, the influence of the original number of training data to the performance of the deep learning-based neural network is confirmed, and it leads to succeed the pixel-level crack detection.

• Imaging Science in Dentistry
• /
• v.51 no.3
• /
• pp.243-250
• /
• 2021

Purpose: The objective of this study was to evaluate the amount of height available for a maxillary sinus augmentation procedure without blocking the ostium and jeopardizing the drainage of the ostiomeatal complex using cone-beam computed tomography (CBCT) imaging. Materials and Methods: A total of 200 sinonasal complexes comprising 100 dentate and 100 edentulous scans were retrospectively assessed using CBCT. Invivo 5.0, a CBCT reconstruction program, was used for image evaluation. The coronal section demonstrating the ostiomeatal complex was selected as a reference view to perform measurements of the sinus. The measurements were done by 2 evaluators in separate sessions. Comparative analyses of measurements were performed between dentate and edentulous patients and between male and female patients. Results: The safe height to which the sinus can be elevated without compromising the integrity of the ostiomeatal complex was calculated for each sinus. In the presence of significant mucosal thickening, the height available for augmentation was calculated by subtracting the height of mucosal thickening from the sinus floor to the location of the ostium. In this study, the available height was approximately 27.05 mm for dentate and 23.40 mm for edentulous patients. The inter-operator reliability was excellent for all the parameters evaluated. Conclusion: This retrospective study with a limited number of patients from a single university-based site shows that CBCT is valuable in evaluating the location and patency of the ostium for planning sinus augmentation procedures for dental implant placement.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1663-1676
• /
• 2022

Recently, a number of deep-learning based land cover segmentation studies have been introduced. Some studies denoted that the performance of land cover segmentation deteriorated due to insufficient training data. In this study, we verified the improvement of land cover segmentation performance through data augmentation. U-Net was implemented for the segmentation model. And 2020 satellite-derived landcover dataset was utilized for the study data. The pixel accuracies were 0.905 and 0.923 for U-Net trained by original and augmented data respectively. And the mean F1 scores of those models were 0.720 and 0.775 respectively, indicating the better performance of data augmentation. In addition, F1 scores for building, road, paddy field, upland field, forest, and unclassified area class were 0.770, 0.568, 0.433, 0.455, 0.964, and 0.830 for the U-Net trained by original data. It is verified that data augmentation is effective in that the F1 scores of every class were improved to 0.838, 0.660, 0.791, 0.530, 0.969, and 0.860 respectively. Although, we applied data augmentation without considering class balances, we find that data augmentation can mitigate biased segmentation performance caused by data imbalance problems from the comparisons between the performances of two models. It is expected that this study would help to prove the importance and effectiveness of data augmentation in various image processing fields.