• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제44권1호
• /
• pp.18-24
• /
• 2018

Objectives: Foreign bodies (FBs) account for 3.8% of all pathologies of the head and neck region, and approximately one third of them are missed on initial examination. Thus, FBs represent diagnostic challenges to maxillofacial surgeons, rendering it necessary to employ an appropriate imaging modality in suspected cases. Materials and Methods: In this cross-sectional study, five different materials, including wood, metal, glass, tooth and stone, were prepared in three sizes (0.5, 1, and 2 mm) and placed in three locations (soft tissue, air-filled space and bone surface) within a sheep's head (one day after death) and scanned by panoramic radiography, cone-beam computed tomography (CBCT), and ultrasonography (US) devices. The images were reviewed, and accuracy of the detection modalities was recorded. The data were analyzed statistically using the Kruskal-Wallis, Mann-Whitney U-test, Friedman, Wilcoxon signed-rank and kappa tests (P<0.05). Results: CBCT was more accurate in detection of FBs than panoramic radiography and US (P<0.001). Metal was the most visible FB in all of modalities. US was the most accurate technique for detecting wooden materials, and CBCT was the best modality for detecting all other materials, regardless of size or location (P<0.05). The detection accuracy of US was greater in soft tissue, while both CBCT and panoramic radiography had minimal accuracy in detection of FBs in soft tissue. Conclusion: CBCT was the most accurate detection modality for all the sizes, locations and compositions of FBs, except for the wooden materials. Therefore, we recommend CBCT as the gold standard of imaging for detecting FBs in the maxillofacial region.

• 한국멀티미디어학회논문지
• /
• 제15권6호
• /
• pp.722-730
• /
• 2012

최근 생체 인식 분야나, HCI 분야 등에서 사람의 눈 영상 정보를 이용하여 홍채 인식을 하거나 시선위치 정보를 이용하는 연구가 활발히 진행 되고 있다. 특히 사용자의 편의성을 위한 원거리 카메라 기반시스템이 늘어나면서 눈 영상 촬영에 단순히 동공 중심 영역만 촬영 되는 것이 아니라, 눈썹, 이마, 피부영역 등 부정확한 검출을 일으킬 수 있는 요소가 포함되어 촬영되고 이러한 불필요한 요소들은 동공 중심영역의 검출 성능을 저하시킨다. 또한 앞서 얘기한 이용분야들은 실시간 환경에서 실행되는 시스템들로 정확한 검출 성능뿐만 아니라 빠른 실행시간도 요구 한다. 본 논문에서는 정확하고 빠른 눈동자 영역 검출을 위하여 기존에 가장 많이 사용하는 AdaBoost 눈 검출 알고리즘, 적응적 템플릿 정합+AdaBoost 알고리즘, CAMShift+AdBoost 알고리즘, rapid eye 검출 알고리즘에 대하여 분석하고, 조명변화와 콘택트 렌즈 및 안경 착용자와 미 착용자등 다양한 경우에 대해서 앞서 말한 알고리즘들을 적용하여 각 알고리즘 별로 정확도와 실행시간을 비교 분석하도록 한다.

• 품질경영학회지
• /
• 제43권4호
• /
• pp.521-532
• /
• 2015

Purpose: The purpose of this study is to compare two multivariate cumulative sum (MCUSUM) charts designed for spatio-temporal surveillance in terms of not only temporal detection performance but also spatial detection performance. Method: Experiments under various configurations are designed and performed to test two CUSUM charts, namely SMCUSUM and RMCUSUM. In addition to average run length(ARL), two measures of spatial identification accuracy are reported and compared. Results: The RMCUSUM chart provides higher level of spatial identification accuracy while two charts show comparable performance in terms of ARL. Conclusion: The RMCUSUM chart has more flexibility, robustness, and spatial identification accuracy when compared to those of the SMCUSUM chart. We recommend to use the RMCUSUM chart if control limit calibration is not an urgent task.

• 한국산업융합학회 논문집
• /
• 제25권3호
• /
• pp.397-406
• /
• 2022

Recently, research and development to revitalize smart construction are being actively carried out. Accordingly, 3D mapping technology that digitizes construction site is drawing attention. To create a 3D digital map for construction site a point cloud generation method based on LiDAR(Light detection and ranging) using MMS(Mobile mapping system) is mainly used. The purpose of this study is to analyze the accuracy of MMS LiDAR-based point cloud data. As a result, accuracy of MMS point cloud data was analyzed as dx = 0.048m, dy = 0.018m, dz = 0.045m on average. In future studies, accuracy comparison of point cloud data produced via UAV(Unmanned aerial vegicle) photogrammetry and MMS LiDAR should be studied.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1345-1360
• /
• 2016

In this paper, we propose a new real-time human detection under omni-directional cameras for visual surveillance purpose, based on CNN with unified detection and AGMM. Compared to CNN-based state-of-the-art object detection methods. YOLO model-based object detection method boasts of very fast object detection, but with less accuracy. The proposed method adapts the unified detecting CNN of YOLO model so as to be intensified by the additional foreground contextual information obtained from pre-stage AGMM. Increased computational time incurred by additional AGMM processing is compensated by speed-up gain obtained from utilizing 2-D input data consisting of grey-level image data and foreground context information instead of 3-D color input data. Through various experiments, it is shown that the proposed method performs better with respect to accuracy and more robust to environment changes than YOLO model-based human detection method, but with the similar processing speeds to that of YOLO model-based one. Thus, it can be successfully employed for embedded surveillance application.

• Journal of International Society for Simulation Surgery
• /
• 제3권1호
• /
• pp.9-11
• /
• 2016

Purpose In this paper we proposed bi-directional hierarchical regression for accurate human finger landmark detection with only using depth information.Materials and Methods Our algorithm consisted of two different step, initialization and landmark estimation. To detect initial landmark, we used difference of random pixel pair as the feature descriptor. After initialization, 16 landmarks were estimated using cascaded regression methods. To improve accuracy and stability, we proposed bi-directional hierarchical structure.Results In our experiments, the ICVL database were used for evaluation. According to our experimental results, accuracy and stability increased when applying bi-directional hierarchical regression more than typical method on the test set. Especially, errors of each finger tips of hierarchical case significantly decreased more than other methods.Conclusion Our results proved that our proposed method improved accuracy and stability and also could be applied to a large range of applications such as augmented reality and simulation surgery.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 춘계학술발표대회
• /
• pp.232-235
• /
• 2018

Convolutional Neural Network is arguably the most popular deep learning architecture that is one of the most attractive area of research since it has various applications including face detection and recognition. The cascaded CNN operates at multiple resolution and rejects the background regions in the fast low resolution stages. By considering that advantage, we carry out the study on accuracy of cascaded CNN for face detection applications. The key point for our study is to analysing and improving the accuracy of cascaded CNN by applying simulations of algorithm where by we used Google's Tensorflow GPU as deep learning framework.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 봄 학술논문 발표대회
• /
• pp.73-74
• /
• 2022

Concrete structures occupy the largest proportion of modern infrastructure, and concrete structures often have cracking problems. Existing concrete crack diagnosis methods have limitations in crack evaluation because they rely on expert visual inspection. Therefore, in this study, we design a deep learning model that detects, visualizes, and outputs cracks on the surface of RC structures based on image data by using a CNN (Convolution Neural Networks) model that can process two- and three-dimensional data such as video and image data. do. An experimental study was conducted on an algorithm to automatically detect concrete cracks and visualize them using a CNN model. For the three deep learning models used for algorithm learning in this study, the concrete crack prediction accuracy satisfies 90%, and in particular, the 'InceptionV3'-based CNN model showed the highest accuracy. In the case of the crack detection visualization model, it showed high crack detection prediction accuracy of more than 95% on average for data with crack width of 0.2 mm or more.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.920-923
• /
• 2020

사이버 공격이 더욱 지능화됨에 따라 기존의 침입 탐지 시스템(Intrusion Detection System)은 기존의 저장된 패턴에서 벗어난 지능형 공격을 탐지하기에 적절하지 않다. 딥러닝(Deep Learning) 기반 침입 탐지는 새로운 탐지 규칙을 생성하는데 적절하다. 그 이유는 딥러닝은 데이터 학습을 통해 새로운 침입 규칙을 자체적으로 생성하기 때문이다. 침입 탐지 시스템 데이터 세트는 가장 널리 사용되는 KDD99 데이터와 LID-DS(Leipzig Intrusion Detection-Data Set)를 사용했다. 본 논문에서는 1차원 벡터를 이미지로 변환하고 CNN(Convolutional Neural Network)을 적용하여 두 데이터 세트에 대한 성능을 실험했다. 평가를 위해 Accuracy, Precision, Recall 및 F1-Score 지표를 측정했다. 그 결과 LID-DS 데이터 세트의 Accuracy가 KDD99 데이터 세트의 Accuracy 보다 약 8% 높은 것을 확인했다. 또한, 1차원 벡터에 대한 데이터를 Kibana를 사용하여 데이터를 시각화하여 대용량 데이터를 한눈에 보기 어려운 단점을 해결하는 방법을 제안한다.

• ETRI Journal
• /
• 제37권2호
• /
• pp.251-261
• /
• 2015

We present a novel method for real-time automatic license plate detection in high-resolution videos. Although there have been extensive studies of license plate detection since the 1970s, the suggested approaches resulting from such studies have difficulties in processing high-resolution imagery in real-time. Herein, we propose a novel cascade structure, the fastest classifier available, by rejecting false positives most efficiently. Furthermore, we train the classifier using the core patterns of various types of license plates, improving both the computation load and the accuracy of license plate detection. To show its superiority, our approach is compared with other state-of-the-art approaches. In addition, we collected 20,000 images including license plates from real traffic scenes for comprehensive experiments. The results show that our proposed approach significantly reduces the computational load in comparison to the other state-of-the-art approaches, with comparable performance accuracy.