Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590601
Xuan Chen, Ryota Nakada, Kien Nguyen, H. Sekiya
There is an increasing interest in adopting distributed ledger technologies (DLTs) to IoT applications that enable secured interaction between IoT devices without third-party involvement. Among recent advanced DLTs, Ethereum blockchain and IOTA Tangle are emerging as promising candidates for various IoT use cases. Both offer various IoT-friendly features such as lightweight crypto, open-source implementations, energy-efficient operations, etc. So far, the two technologies have only been qualitatively evaluated together in the literature. There has not yet been a performance comparison between IOTA and Ethereum in an IoT application. To address the issue, we build an IoT environment that can run both DLTs and compare their performance. We thoroughly investigate the DLTs' three layers (i.e., Consensus, Network, and Storage layers). In the first layer, we evaluate the CPU utilization and number of transaction; in the second one, the DLTs' network performance is compared. Meanwhile, disk and memory usage are derived in the third layer. The results show that IOTA performs better with most performance metrics.
{"title":"A Comparison of Distributed Ledger Technologies in IoT: IOTA versus Ethereum","authors":"Xuan Chen, Ryota Nakada, Kien Nguyen, H. Sekiya","doi":"10.1109/ISCIT52804.2021.9590601","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590601","url":null,"abstract":"There is an increasing interest in adopting distributed ledger technologies (DLTs) to IoT applications that enable secured interaction between IoT devices without third-party involvement. Among recent advanced DLTs, Ethereum blockchain and IOTA Tangle are emerging as promising candidates for various IoT use cases. Both offer various IoT-friendly features such as lightweight crypto, open-source implementations, energy-efficient operations, etc. So far, the two technologies have only been qualitatively evaluated together in the literature. There has not yet been a performance comparison between IOTA and Ethereum in an IoT application. To address the issue, we build an IoT environment that can run both DLTs and compare their performance. We thoroughly investigate the DLTs' three layers (i.e., Consensus, Network, and Storage layers). In the first layer, we evaluate the CPU utilization and number of transaction; in the second one, the DLTs' network performance is compared. Meanwhile, disk and memory usage are derived in the third layer. The results show that IOTA performs better with most performance metrics.","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124976246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590604
Taito Murano, M. Muneyasu, Soh Yoshida, K. Chamnongthai, A. Asano, K. Uchida
Calcification regions are sometimes observed on dental panoramic radiographs and it is known that these regions are a sign of vascular disease. It has been pointed out that the detection of calcification regions in dental panoramic radiographs can encourage patients to undergo medical checkups by a physician. Medical checkups can prevent the sudden onset of vascular disease. For this purpose, a method of automatically detecting calcification regions using an object detector based on deep learning has been proposed. Although this method significantly reduces the number of false positives compared with conventional methods based on image features, its detection accuracy is still insufficient. In this paper, we propose a method of detecting calcification regions in dental panoramic radiographs using a novel object detector based on deep learning. On the basis of PraNet, which has been increasingly applied to medical image processing in recent years, we introduce the Double U-Net structure and enhance the prediction accuracy for the initial guidance region. The proposed method can improve the detection accuracy for calcification regions. The experimental results show that the proposed method improves the detection performance compared with other methods.
{"title":"New Method of Detecting Calcification Regions in Dental Panoramic Radiographs Based on U-PraNet","authors":"Taito Murano, M. Muneyasu, Soh Yoshida, K. Chamnongthai, A. Asano, K. Uchida","doi":"10.1109/ISCIT52804.2021.9590604","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590604","url":null,"abstract":"Calcification regions are sometimes observed on dental panoramic radiographs and it is known that these regions are a sign of vascular disease. It has been pointed out that the detection of calcification regions in dental panoramic radiographs can encourage patients to undergo medical checkups by a physician. Medical checkups can prevent the sudden onset of vascular disease. For this purpose, a method of automatically detecting calcification regions using an object detector based on deep learning has been proposed. Although this method significantly reduces the number of false positives compared with conventional methods based on image features, its detection accuracy is still insufficient. In this paper, we propose a method of detecting calcification regions in dental panoramic radiographs using a novel object detector based on deep learning. On the basis of PraNet, which has been increasingly applied to medical image processing in recent years, we introduce the Double U-Net structure and enhance the prediction accuracy for the initial guidance region. The proposed method can improve the detection accuracy for calcification regions. The experimental results show that the proposed method improves the detection performance compared with other methods.","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122705266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590577
Koki Kato, H. Takano, M. Saiko, Masahiro Kubo, Hitoshi Imaoka
Bad news, such as cancer notifications from doctors, has a big impact on patients. The patient does not remember the contents of the interview. Therefore, it is necessary for medical doctors to estimate the patient's emotions during the interview and to understand the patient's internal condition. In the medical field, the development of a communication support system is required. The purpose of this study is to improve the accuracy of emotional estimation using micro-expressions which would express true emotions. The emotional estimation employs the feature selected LBP-TOP (Local Binary Patterns from Three Orthogonal Planes) using the ratio of the inter-class variance to within class one. In this paper, we show the characteristics of emotional classification using LBP-TOP feature based on the experimental results obtained with the XGBoost and SVM (Support Vector Machine).
坏消息,比如来自医生的癌症通知,对病人有很大的影响。病人不记得面谈的内容。因此,医生有必要在访谈中估计患者的情绪,了解患者的内部情况。在医疗领域,需要开发通信支持系统。本研究的目的是为了提高微表情对真实情绪的估计准确性。情感估计采用特征选择LBP-TOP (Local Binary Patterns from Three Orthogonal plane),使用类间方差与类内方差的比值。本文基于XGBoost和SVM (Support Vector Machine)的实验结果,展示了LBP-TOP特征在情绪分类中的特点。
{"title":"Characteristics of LBP-TOP Feature for Emotional Estimation by Micro-expression","authors":"Koki Kato, H. Takano, M. Saiko, Masahiro Kubo, Hitoshi Imaoka","doi":"10.1109/ISCIT52804.2021.9590577","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590577","url":null,"abstract":"Bad news, such as cancer notifications from doctors, has a big impact on patients. The patient does not remember the contents of the interview. Therefore, it is necessary for medical doctors to estimate the patient's emotions during the interview and to understand the patient's internal condition. In the medical field, the development of a communication support system is required. The purpose of this study is to improve the accuracy of emotional estimation using micro-expressions which would express true emotions. The emotional estimation employs the feature selected LBP-TOP (Local Binary Patterns from Three Orthogonal Planes) using the ratio of the inter-class variance to within class one. In this paper, we show the characteristics of emotional classification using LBP-TOP feature based on the experimental results obtained with the XGBoost and SVM (Support Vector Machine).","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122272122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590594
S. Ogawa, K. Ishii
The deep-learning optimization method for a consensus problem, which can significantly accelerate the convergence performance, has been proposed by Kishida et al. However, the optimized parameters can be applied only to the network topology used in the training. To make the optimized parameters versatile for the network topology, our previous work [1] proposed the optimization method constrained by degree and eigenvector centralities. There are several types of centralities. However, the problem of which centrality is the most suitable for the consensus problem is still open. This work applies betweenness centrality to the proposed optimization method and shows that the case with betweenness centrality can achieve better performance than the cases with degree and eigenvector centralities.
{"title":"Deep Leaning Aided Consensus Problem with Betweenness Centrality Approach","authors":"S. Ogawa, K. Ishii","doi":"10.1109/ISCIT52804.2021.9590594","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590594","url":null,"abstract":"The deep-learning optimization method for a consensus problem, which can significantly accelerate the convergence performance, has been proposed by Kishida et al. However, the optimized parameters can be applied only to the network topology used in the training. To make the optimized parameters versatile for the network topology, our previous work [1] proposed the optimization method constrained by degree and eigenvector centralities. There are several types of centralities. However, the problem of which centrality is the most suitable for the consensus problem is still open. This work applies betweenness centrality to the proposed optimization method and shows that the case with betweenness centrality can achieve better performance than the cases with degree and eigenvector centralities.","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"422 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131144424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590616
Jyo Matsushima, Tomohiro Kiguchi, H. Habuchi
In this paper, a frame synchronization method for parallel transmission is proposed in RGB-LED communications using a binary pulse position modulation (BPPM). In the proposed system, the different colors of RGB-LED transmit different source data sequences by BPPM. Therefore, in the synchronous case where the frame is synchronized, the probability that the correlation value between the received signal and the Manchester signal becomes $pm 1$ is 1. In the asynchronous case where the frame synchronization timing slips off 1 slot, the probability of the correlation value being $pm 1$ is 1/2. A simple frame synchronization system, that utilizes this difference in probability between synchronous and asynchronous states, is shown. Furthermore, the average frame retention time and average frame recovery time are evaluated. Consequently, it is shown that there is a trade-off between the average frame retention time and the average frame recovery time. It is also found that there is an optimal number of counter stages in the frame synchronization system for achieving the required frame recovery time.
{"title":"Novel Frame Synchronization System for RGB-LED Parallel Transmission employing BPPM Format","authors":"Jyo Matsushima, Tomohiro Kiguchi, H. Habuchi","doi":"10.1109/ISCIT52804.2021.9590616","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590616","url":null,"abstract":"In this paper, a frame synchronization method for parallel transmission is proposed in RGB-LED communications using a binary pulse position modulation (BPPM). In the proposed system, the different colors of RGB-LED transmit different source data sequences by BPPM. Therefore, in the synchronous case where the frame is synchronized, the probability that the correlation value between the received signal and the Manchester signal becomes $pm 1$ is 1. In the asynchronous case where the frame synchronization timing slips off 1 slot, the probability of the correlation value being $pm 1$ is 1/2. A simple frame synchronization system, that utilizes this difference in probability between synchronous and asynchronous states, is shown. Furthermore, the average frame retention time and average frame recovery time are evaluated. Consequently, it is shown that there is a trade-off between the average frame retention time and the average frame recovery time. It is also found that there is an optimal number of counter stages in the frame synchronization system for achieving the required frame recovery time.","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130987670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590602
Shintaro Mori
This paper addresses a large-scale river monitoring system, an essential component of smart cities and disaster area networks. We investigate a velocity and direction measurement method for river surface. To measure the velocity vectors from the pictures taken by a camera located on the riverbank, the proposed method uses a visual particle image velocimetry. In this paper, we present the overall blueprint of our study and a preliminary evaluation of the field experiment conducted in the Onga River in Fukuoka, Japan.
{"title":"Prototype Development of River Velocimetry using Visual Particle Image Velocimetry for Smart Cities and Disaster Area Networks","authors":"Shintaro Mori","doi":"10.1109/ISCIT52804.2021.9590602","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590602","url":null,"abstract":"This paper addresses a large-scale river monitoring system, an essential component of smart cities and disaster area networks. We investigate a velocity and direction measurement method for river surface. To measure the velocity vectors from the pictures taken by a camera located on the riverbank, the proposed method uses a visual particle image velocimetry. In this paper, we present the overall blueprint of our study and a preliminary evaluation of the field experiment conducted in the Onga River in Fukuoka, Japan.","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132182994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590618
Hirotomo Nakashima, Yoshiaki Shindo, I. Nakanishi
In this study, we examine electroencephalogram (EEG) biometric information that can be detected continuously with high confidentiality to realize personal verification using the evoked EEG when presented with an imperceptible vibration stimulus. Considering the survey of conventional studies on brain-waves evoked by perceptible vibration stimulation, we determined that to use the evoked EEG, including the immediately response after the stimulus is effective in verification. Therefore, we introduce a method for repeating the stimulus presentation over a short time. In addition, to improve the verification performance, we introduce support vector machine (SVM). Furthermore, we evaluated the verification performance and obtained an equal error rate of 11%.
{"title":"Performance Improvement in User Verification Using Evoked Electroencephalogram by Imperceptible Vibration Stimuli","authors":"Hirotomo Nakashima, Yoshiaki Shindo, I. Nakanishi","doi":"10.1109/ISCIT52804.2021.9590618","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590618","url":null,"abstract":"In this study, we examine electroencephalogram (EEG) biometric information that can be detected continuously with high confidentiality to realize personal verification using the evoked EEG when presented with an imperceptible vibration stimulus. Considering the survey of conventional studies on brain-waves evoked by perceptible vibration stimulation, we determined that to use the evoked EEG, including the immediately response after the stimulus is effective in verification. Therefore, we introduce a method for repeating the stimulus presentation over a short time. In addition, to improve the verification performance, we introduce support vector machine (SVM). Furthermore, we evaluated the verification performance and obtained an equal error rate of 11%.","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116561461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590613
Y. Ashida
Data-driven control design is one of the hot-topic in control. Among them, Fictitious Reference Iterative Tuning (FRIT) is considered useful, and some practical examples have been reported. However, few studies have considered the effect of observation noise and disturbance on FRIT, and there are no studies that have mathematically analyzed the influence of noise and disturbance on FRIT. In this paper, regression equation is derived from an optimization problem of FRIT and identical control parameters. As a result, residuals of the regression equation are colored, and optimized result of normal least squares method has bias. In response to this analysis, three regression methods which often employed in system identification are tested in a numerical example. All of the three methods are implemented as functions in MATLAB software, and it is easy to actually use.
{"title":"Comparison of Regression Methods on Data-Driven Controller Design for Systems with Observation Noise","authors":"Y. Ashida","doi":"10.1109/ISCIT52804.2021.9590613","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590613","url":null,"abstract":"Data-driven control design is one of the hot-topic in control. Among them, Fictitious Reference Iterative Tuning (FRIT) is considered useful, and some practical examples have been reported. However, few studies have considered the effect of observation noise and disturbance on FRIT, and there are no studies that have mathematically analyzed the influence of noise and disturbance on FRIT. In this paper, regression equation is derived from an optimization problem of FRIT and identical control parameters. As a result, residuals of the regression equation are colored, and optimized result of normal least squares method has bias. In response to this analysis, three regression methods which often employed in system identification are tested in a numerical example. All of the three methods are implemented as functions in MATLAB software, and it is easy to actually use.","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115423242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590627
Daiki Toda, Ren Anzai, K. Ichige, Ryo Saito, Daichi Ueki
This paper presents a method for radar-based contactless vital sensing and ECG (ElectroCardioGram) signal reconstruction using deep learning. ECG signal is a typical representation of heartbeat signals. However, its measurement usually requires any contact device, which is not suitable due to discomfort of subjects. Radar system is effective for vital sensing because it can measure small displacement of body surface caused by breathing and heartbeat without contact. On the other hand, most of the methods using radar system are limited to evaluating simple indices such as heart rate and heartbeat interval while subjects or devices are stationary. In this paper, we propose a method for body surface displacement signals using FMCW (Frequency-Modulated Continuous Wave) radar and reconstructing ECG signals using CNN (Convolutional Neural Network). The result of experiments on six healthy males shows the ECG signals are successfully reconstructed. Furthermore, we confirmed that the proposed method can reconstruct signal waveforms even in an environment with low SNR (Signal-to-Noise Ratio).
{"title":"ECG Signal Reconstruction Using FMCW Radar and Convolutional Neural Network","authors":"Daiki Toda, Ren Anzai, K. Ichige, Ryo Saito, Daichi Ueki","doi":"10.1109/ISCIT52804.2021.9590627","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590627","url":null,"abstract":"This paper presents a method for radar-based contactless vital sensing and ECG (ElectroCardioGram) signal reconstruction using deep learning. ECG signal is a typical representation of heartbeat signals. However, its measurement usually requires any contact device, which is not suitable due to discomfort of subjects. Radar system is effective for vital sensing because it can measure small displacement of body surface caused by breathing and heartbeat without contact. On the other hand, most of the methods using radar system are limited to evaluating simple indices such as heart rate and heartbeat interval while subjects or devices are stationary. In this paper, we propose a method for body surface displacement signals using FMCW (Frequency-Modulated Continuous Wave) radar and reconstructing ECG signals using CNN (Convolutional Neural Network). The result of experiments on six healthy males shows the ECG signals are successfully reconstructed. Furthermore, we confirmed that the proposed method can reconstruct signal waveforms even in an environment with low SNR (Signal-to-Noise Ratio).","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"340 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124310568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-19DOI: 10.1109/ISCIT52804.2021.9590600
Johei Matsuoka
In this paper, we propose an algorithm that uses a switching process to reduce the processing time of nonlocal median filters with retaining its advantages. The non-local median filter provides noise reduction performance with excellent structure preservation performance, but it has been recognized that the method cannot be applicable to real-time applications due to the slow processing speed caused by the nature of the algorithm. The goal of the proposal is to provide a solution to the issue by switching to a simpler filter in the flat regions of the image. Achieving both high structure-preserving performance and short process time in video noise reduction systems becomes very important because applying real-time video processing to IoT devices such as vehicles and embedded devices is now spreading widely.
{"title":"Processing Time Reduction for Non-local Median Filter","authors":"Johei Matsuoka","doi":"10.1109/ISCIT52804.2021.9590600","DOIUrl":"https://doi.org/10.1109/ISCIT52804.2021.9590600","url":null,"abstract":"In this paper, we propose an algorithm that uses a switching process to reduce the processing time of nonlocal median filters with retaining its advantages. The non-local median filter provides noise reduction performance with excellent structure preservation performance, but it has been recognized that the method cannot be applicable to real-time applications due to the slow processing speed caused by the nature of the algorithm. The goal of the proposal is to provide a solution to the issue by switching to a simpler filter in the flat regions of the image. Achieving both high structure-preserving performance and short process time in video noise reduction systems becomes very important because applying real-time video processing to IoT devices such as vehicles and embedded devices is now spreading widely.","PeriodicalId":337293,"journal":{"name":"2021 20th International Symposium on Communications and Information Technologies (ISCIT)","volume":"643 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122954717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}