• 대한임베디드공학회논문지
• /
• 제17권2호
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.494-510
• /
• 2024

Internet users are exposed to sophisticated cyberattacks that intrusion detection systems have difficulty detecting. Therefore, research is increasing on intrusion detection methods that use artificial intelligence technology for detecting novel cyberattacks. Unsupervised learning-based methods are being researched that learn only from normal data and detect abnormal behaviors by finding patterns. This study developed an anomaly-detection method based on unsupervised machines and deep learning for a network intrusion detection system (NIDS). We present a hybrid anomaly detection approach based on unsupervised learning techniques using the autoencoder (AE), Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms. An oversampling approach that increased the detection rate was also examined. A hybrid approach that combined deep learning algorithms and traditional machine learning algorithms was highly effective in setting the thresholds for anomalies without subjective human judgment. It achieved precision and recall rates respectively of 88.2% and 92.8% when combining two AEs, IF, and LOF while using an oversampling approach to learn more unknown normal data improved the detection accuracy. This approach achieved precision and recall rates respectively of 88.2% and 94.6%, further improving the detection accuracy compared with the hybrid method. Therefore, in NIDS the proposed approach provides high reliability for detecting cyberattacks.

• 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.

• 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.

• 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.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2230-2252
• /
• 2024

Advances in deep learning technology have enabled the generation of more realistic deepfakes, which not only endanger individuals' identities but also exploit vulnerabilities in face recognition systems. The majority of existing deepfake detection methods have primarily focused on RGB-based analysis, offering unreliable performance in terms of detection accuracy and time. To address the issue, a grayscale-based deepfake detection method has recently been proposed. This method significantly reduces detection time while providing comparable accuracy to RGB-based methods. However, despite its significant effectiveness, the "key components" that directly affect the performance of grayscale-based deepfake detection have not been systematically analyzed. In this paper, we target three key components: RGB-to-grayscale conversion method, brightness level in grayscale, and resolution level in grayscale. To analyze their impacts on the performance of grayscale-based deepfake detection, we conducted comprehensive evaluations, including component-wise analysis and comparative analysis using real-world datasets. For each key component, we quantitatively analyzed its characteristics' performance and identified differences between them. Moreover, we successfully verified the effectiveness of an optimal combination of the key components by comparing it with existing deepfake detection methods.

• 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.

• 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.

• 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.