• Journal of Information Processing Systems
• /
• v.10 no.4
• /
• pp.589-601
• /
• 2014

The performance of edge detection often relies on its ability to correctly determine the dissimilarities of connected pixels. For grayscale images, the dissimilarity of two pixels is estimated by a scalar difference of their intensities and for color images, this is done by using the vector difference (color distance) of the three-color components. The Euclidean distance in the RGB color space typically measures a color distance. However, the RGB space is not suitable for edge detection since its color components do not coincide with the information human perception uses to separate objects from backgrounds. In this paper, we propose a novel method for color edge detection by taking advantage of the HSV color space and the Mahalanobis distance. The HSV space models colors in a manner similar to human perception. The Mahalanobis distance independently considers the hue, saturation, and lightness and gives them different degrees of contribution for the measurement of color distances. Therefore, our method is robust against the change of lightness as compared to previous approaches. Furthermore, we will introduce a noise-resistant technique for determining image gradients. Various experiments on simulated and real-world images show that our approach outperforms several existing methods, especially when the images vary in lightness or are corrupted by noise.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.5_6
• /
• pp.257-267
• /
• 2004

Most algorithms for handling distributed deadlock problem in the generalized request model use the diffusing computation technique where propagation of probes and backward propagation of replies carrying dependency information between processes are both required to detect deadlock Since fast deadlock detection is critical, we propose an algorithm that lets probes rather than replies carry the information required for deadlock detection. This helps to remove the backward propagation of replies and reduce the time cost for deadlock detection to almost half of that of the existing algorithms. Moreover, the proposed algorithm is extended to deal with concurrent executions, which achieves further improvement of deadlock detection time, whereas the current algorithms deal only with a single execution. We compare the performance of the proposed algorithm with that of the other algorithms through simulation experiments.

• Nuclear Engineering and Technology
• /
• v.52 no.12
• /
• pp.2910-2917
• /
• 2020

Digital light processing three-dimensional (3D) printing technique is a powerful tool to rapidly manufacture plastic scintillators of almost any shape or geometric features. In our previous study, the main properties of light output and transmission were analyzed. However, a more detailed study of the other properties is required to develop 3D printed plastic scintillators with expectable and reproducible properties. The 3D printed plastic scintillator displayed an average decay time constants of 15.6 ns, intrinsic energy resolution of 13.2%, and intrinsic detection efficiency of 6.81% for 477 keV Compton electrons from the ¹³⁷Cs γ-ray source. The 3D printed plastic scintillator showed a similar decay time and intrinsic detection efficiency as that of a commercial plastic scintillator BC408. Furthermore, the presented estimates for the properties showed good agreement with the analyzed data.

• Asia-Pacific Journal of Atmospheric Sciences
• /
• v.54 no.4
• /
• pp.527-544
• /
• 2018

This paper presents a nighttime sea fog detection algorithm incorporating unsupervised learning technique. The algorithm is based on data sets that combine brightness temperatures from the $3.7{\mu}m$ and $10.8{\mu}m$ channels of the meteorological imager (MI) onboard the Communication, Ocean and Meteorological Satellite (COMS), with sea surface temperature from the Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA). Previous algorithms generally employed threshold values including the brightness temperature difference between the near infrared and infrared. The threshold values were previously determined from climatological analysis or model simulation. Although this method using predetermined thresholds is very simple and effective in detecting low cloud, it has difficulty in distinguishing fog from stratus because they share similar characteristics of particle size and altitude. In order to improve this, the unsupervised learning approach, which allows a more effective interpretation from the insufficient information, has been utilized. The unsupervised learning method employed in this paper is the expectation-maximization (EM) algorithm that is widely used in incomplete data problems. It identifies distinguishing features of the data by organizing and optimizing the data. This allows for the application of optimal threshold values for fog detection by considering the characteristics of a specific domain. The algorithm has been evaluated using the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) vertical profile products, which showed promising results within a local domain with probability of detection (POD) of 0.753 and critical success index (CSI) of 0.477, respectively.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.79-84
• /
• 2021

Detecting brain tumors of different sizes is a challenging task. This study aimed to identify brain tumors using detection algorithms. Most studies in this area use segmentation; however, we utilized detection owing to its advantages. Data were obtained from 64 patients and 11,200 MR images. The deep learning model used was RetinaNet, which is based on ResNet152. The model learned three different types of pre-processing images: normal, general histogram equalization, and contrast-limited adaptive histogram equalization (CLAHE). The three types of images were compared to determine the pre-processing technique that exhibits the best performance in the deep learning algorithms. During pre-processing, we converted the MR images from DICOM to JPG format. Additionally, we regulated the window level and width. The model compared the pre-processed images to determine which images showed adequate performance; CLAHE showed the best performance, with a sensitivity of 81.79%. The RetinaNet model for detecting brain tumors through deep learning algorithms demonstrated satisfactory performance in finding lesions. In future, we plan to develop a new model for improving the detection performance using well-processed data. This study lays the groundwork for future detection technologies that can help doctors find lesions more easily in clinical tasks.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.546-557
• /
• 2022

Recently, the demand to interpret image data with artificial intelligence in various fields is rapidly increasing. Object recognition and detection techniques using deep learning are mainly used, and video integration analysis to determine unstructured object recognition is a particularly important problem. In the case of natural disasters or social disasters, there is a limit to the object recognition structure alone because it has an unstructured shape. In this paper, we propose intelligent video integration analysis system that can recognize unstructured objects based on video turning point and object detection. We also introduce a method to apply and evaluate object recognition using virtual augmented images from 2D to 3D through GAN.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.129-138
• /
• 2022

Collecting and labeling sufficient training data, which is essential to deep learning-based visual inspection, is difficult for manufacturers to perform because it is very expensive. This paper presents a steel plate surface defect detection system with industrial-grade detection performance by training a small amount of steel plate surface images consisting of labeled and non-labeled data. To overcome the problem of lack of training data, we propose two data augmentation techniques: program-based augmentation, which generates defect images in a geometric way, and generative model-based augmentation, which learns the distribution of labeled data. We also propose a 4-step semi-supervised learning using pseudo labels and consistency training with fixed-size augmentation in order to utilize unlabeled data for training. The proposed technique obtained about 99% defect detection performance for four defect types by using 100 real images including labeled and unlabeled data.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.5
• /
• pp.410-416
• /
• 2022

A grid-connected inverter with critical loads uses mode transfer control to supply stable voltage to the load. An islanding detection method should also be used to quickly detect the grid fault and disconnect the inverter from the grid. However using the existing islanding detection method to detect islanding is difficult due to the small fluctuation of the voltage and frequency of the point of common coupling. This study proposes a reactive power P&O islanding detection method by using the positive feedback technique. The proposed method always injects a small variation of reactive power. When a grid fault occurs, the injected reactive power accelerates the reactive power injection reference. As a result, the reactive power reference value and the sensed reactive power become mismatched, and islanding is detected. Reducing the amount of real-time injected reactive power results in high efficiency and power factor. The simulation and experimental results of a 3 kW single-phase inverter are provided to verify the proposed islanding detection method.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• Journal of the Korea Society for Simulation
• /
• v.18 no.1
• /
• pp.9-16
• /
• 2009

Since a deadlock is a condition in which the excessive demand for the resources being used by others causes activities to stop, it is very important to detect and prevent a deadlock. About the deadlock detection analysis methods are may divide like as Siphon, DAPN and transitive matrix, but it's very difficult to evaluate the performance. Since DES (Discrete Event Systems) is NP-hard, and these detection and avoidance methods used various factors in each technique, it's made difficult to compare with each other's. In this paper, we are benchmarked these deadlock detection analyze methods based on the complexity, the detection time and the understanding after approached to one example.