Pub Date : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120596
Mithun Biswas, Rafiqul Islam, Gautam Kumar Shom, Nabeel Mohammed, S. Momen, N. Mansoor, Md. Anowarul Abedin
Bangla is one of the most widely used languages worldwide. This paper presents an application of image retrieval techniques to automatically judge the aesthetic quality of handwritten Bangla isolated characters. Retrieval techniques are also adapted to give improvement suggestions, with a plan to incorporate the methods in applications which can assist in learning/teaching handwriting. The proposed method borrows key concepts from content-based image retrieval. Our method was tested on the BanglaLekha-Isolated data set, which contains images of 84 Bangla characters, with nearly 2000 samples per character. The data set contains evaluation of the aesthetic quality of the handwriting judged on a scale of 1–5. For this work, the dataset was partitioned into a test set of 400 images and a database-set of ≈ 1600 images, per Bangla character. Assuming that a scoring difference of 1 is acceptable, the proposed method achieves an accuracy of 77.39% when using features extracted by a convolutional neural network based autoencoder. Experiments were also done with the popular HOG feature. However, the autoencoder-based results showed clear superiority compared the HOG-based results. Our proposed method for improvement suggestions also shows that it is possible to shows samples from the dataset which will help users improve their handwriting while requiring small changes to their own handwriting.
{"title":"Application of image retrieval for aesthetic evaluation and improvement suggestion of isolated Bangla handwritten characters","authors":"Mithun Biswas, Rafiqul Islam, Gautam Kumar Shom, Nabeel Mohammed, S. Momen, N. Mansoor, Md. Anowarul Abedin","doi":"10.1109/ICSIPA.2017.8120596","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120596","url":null,"abstract":"Bangla is one of the most widely used languages worldwide. This paper presents an application of image retrieval techniques to automatically judge the aesthetic quality of handwritten Bangla isolated characters. Retrieval techniques are also adapted to give improvement suggestions, with a plan to incorporate the methods in applications which can assist in learning/teaching handwriting. The proposed method borrows key concepts from content-based image retrieval. Our method was tested on the BanglaLekha-Isolated data set, which contains images of 84 Bangla characters, with nearly 2000 samples per character. The data set contains evaluation of the aesthetic quality of the handwriting judged on a scale of 1–5. For this work, the dataset was partitioned into a test set of 400 images and a database-set of ≈ 1600 images, per Bangla character. Assuming that a scoring difference of 1 is acceptable, the proposed method achieves an accuracy of 77.39% when using features extracted by a convolutional neural network based autoencoder. Experiments were also done with the popular HOG feature. However, the autoencoder-based results showed clear superiority compared the HOG-based results. Our proposed method for improvement suggestions also shows that it is possible to shows samples from the dataset which will help users improve their handwriting while requiring small changes to their own handwriting.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116048440","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120571
Adrian Emiell U. Berbano, Hanz Niccole V. Pengson, Cedric Gerard V. Razon, Kristel Chloe G. Tungcul, Seigfred V. Prado
The paper presents further research on neural engineering that focuses on the classification of emotional, mental, physical and no stress through the use of Electroencephalography (EEG) signal analysis. Stress is one of the leading causes of several health-related problems and diseases. Therefore, it becomes necessary for people to monitor their stress. The human body acquires and responds to stress in different ways resulting to two classifications of stress namely, mental and emotional stress. Traditional methods in classifying stress such as through questionnaires and self-assessment tests are said to be subjective since they rely on personal judgment. Thus, in this study, stress is classified through an objective measure which is EEG signal analysis. The features of the EEG recordings are then pre-processed, extracted, and selected using Discrete Wavelet Transform (DWT). These features are then ussed as inputs to classify stress using Artificial Neural Network (ANN) and validated using K-fold Cross Validation Method. Lastly, the results from the software assisted method is compared to the results of the traditional method.
{"title":"Classification of stress into emotional, mental, physical and no stress using electroencephalogram signal analysis","authors":"Adrian Emiell U. Berbano, Hanz Niccole V. Pengson, Cedric Gerard V. Razon, Kristel Chloe G. Tungcul, Seigfred V. Prado","doi":"10.1109/ICSIPA.2017.8120571","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120571","url":null,"abstract":"The paper presents further research on neural engineering that focuses on the classification of emotional, mental, physical and no stress through the use of Electroencephalography (EEG) signal analysis. Stress is one of the leading causes of several health-related problems and diseases. Therefore, it becomes necessary for people to monitor their stress. The human body acquires and responds to stress in different ways resulting to two classifications of stress namely, mental and emotional stress. Traditional methods in classifying stress such as through questionnaires and self-assessment tests are said to be subjective since they rely on personal judgment. Thus, in this study, stress is classified through an objective measure which is EEG signal analysis. The features of the EEG recordings are then pre-processed, extracted, and selected using Discrete Wavelet Transform (DWT). These features are then ussed as inputs to classify stress using Artificial Neural Network (ANN) and validated using K-fold Cross Validation Method. Lastly, the results from the software assisted method is compared to the results of the traditional method.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134318501","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120671
Loshini Thiruchelvam, V. Asirvadam, S. Dass, H. Daud, B. Gill
The paper proposed prediction model to study dengue occurrence in Malaysia, focusing on a region of Petaling district, in the state of Selangor. A number of different linear regression models were compared using model orders of lag time, and best model is selected using Akaike Information Criterion (AIC) value. First, dengue estimation models were built for Petaling district using weather variables of mean temperature, relative humidity, cumulative rainfall, and dengue feedback data. The best estimation model is then used to build dengue prediction models, using the k-steps ahead prediction (with one and multiple-step ahead predictions). One-step ahead prediction model was found to capture well pattern of dengue incidences. This information is believed to help health authorities in providing a reminder alarm to the public through medias, on precautions specifically against mosquitoes bites, especially when dengue occurrences is expected to be high.
本文提出了以马来西亚雪兰莪州Petaling地区为研究对象的登革热发生预测模型。利用滞后时间的模型阶数对多个不同的线性回归模型进行比较，并利用赤池信息准则(Akaike Information Criterion, AIC)值选择最佳模型。首先，利用平均气温、相对湿度、累积降雨量等气象变量和登革热反馈数据，建立了花瓣陵区登革热估计模型;然后使用最佳估计模型构建登革热预测模型，使用提前k步预测(提前一步和多步预测)。一步预测模型较好地反映了登革热的发病规律。这些信息被认为有助于卫生当局通过媒体向公众发出提醒警报，特别是针对蚊虫叮咬的预防措施，特别是在预计登革热发病率将很高的时候。
{"title":"K-step ahead prediction models for dengue occurrences","authors":"Loshini Thiruchelvam, V. Asirvadam, S. Dass, H. Daud, B. Gill","doi":"10.1109/ICSIPA.2017.8120671","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120671","url":null,"abstract":"The paper proposed prediction model to study dengue occurrence in Malaysia, focusing on a region of Petaling district, in the state of Selangor. A number of different linear regression models were compared using model orders of lag time, and best model is selected using Akaike Information Criterion (AIC) value. First, dengue estimation models were built for Petaling district using weather variables of mean temperature, relative humidity, cumulative rainfall, and dengue feedback data. The best estimation model is then used to build dengue prediction models, using the k-steps ahead prediction (with one and multiple-step ahead predictions). One-step ahead prediction model was found to capture well pattern of dengue incidences. This information is believed to help health authorities in providing a reminder alarm to the public through medias, on precautions specifically against mosquitoes bites, especially when dengue occurrences is expected to be high.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132392375","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120617
Faraz Bhatti, Thomas Greiner, M. Heizmann, Mathias Ziebarth
The use of image processing is being accelerated over the past years in areas, including artificial intelligence, medical field, remote sensing and microscopic imaging. For 3D reconstruction of the objects, deflectometry is used to collect topographic information of surfaces. Due to computationally intensive nature of the algorithm, the execution time is one of the challenges faced by the deflectometry. In this paper, an extended FPGA based architecture is proposed to execute and improve the performance of deflectometry algorithm. The whole process consists of several stages, including initialization, acquisition and processing of data. The main idea is to utilize the optimizations e.g., pipelining, parallelization, provided by an FPGA to improve the performance of the algorithm. However, the advantage of parallelization can only be utilized if the associated algorithm contains the number of tasks, which can run independent of each other. For this reason, the deflectometry algorithm is adapted to the architecture of an FPGA to improve the performance. After successful realization of proposed architecture, the results have shown that performance is significantly improved in terms of execution time. Moreover, a rapid design development methodology is employed to decrease the prototyping time.
{"title":"An extended architecture to optimize execution time of 3D image processing deflectometry algorithm using FPGA","authors":"Faraz Bhatti, Thomas Greiner, M. Heizmann, Mathias Ziebarth","doi":"10.1109/ICSIPA.2017.8120617","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120617","url":null,"abstract":"The use of image processing is being accelerated over the past years in areas, including artificial intelligence, medical field, remote sensing and microscopic imaging. For 3D reconstruction of the objects, deflectometry is used to collect topographic information of surfaces. Due to computationally intensive nature of the algorithm, the execution time is one of the challenges faced by the deflectometry. In this paper, an extended FPGA based architecture is proposed to execute and improve the performance of deflectometry algorithm. The whole process consists of several stages, including initialization, acquisition and processing of data. The main idea is to utilize the optimizations e.g., pipelining, parallelization, provided by an FPGA to improve the performance of the algorithm. However, the advantage of parallelization can only be utilized if the associated algorithm contains the number of tasks, which can run independent of each other. For this reason, the deflectometry algorithm is adapted to the architecture of an FPGA to improve the performance. After successful realization of proposed architecture, the results have shown that performance is significantly improved in terms of execution time. Moreover, a rapid design development methodology is employed to decrease the prototyping time.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123318627","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120609
Stephen, Wen Hwooi Khor, Aznul Qalid Md. Sabri
A study of the effectiveness of Enhanced Correlation Coefficient (ECC) on the performance of feature-based image registration approaches is carried out. This investigation determines if ECC improves image registration performance on datasets which test on invariance to scale, rotation and viewpoint change. Five state-of-the-arts methods are considered, namely KAZE, Binary Robust Invariant Scalable Keypoints (BRISK), Oriented FAST and Rotated Brief (ORB), Speeded-Up Robust Features (SURF), and Scale-Invariant Feature Transform (SIFT). Root-mean-squared error of control points is used to evaluate the image registration performance on datasets taken from the Oxford Robotics Database. A global ranking factor is used to rank each method within a dataset. The efficiency of each method is recorded as a guide for selecting a method for a specific application. Results indicate that ECC improves image registration performance in most cases with a small time addition.
{"title":"Enhanced correlation coefficient as a refinement of image registration","authors":"Stephen, Wen Hwooi Khor, Aznul Qalid Md. Sabri","doi":"10.1109/ICSIPA.2017.8120609","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120609","url":null,"abstract":"A study of the effectiveness of Enhanced Correlation Coefficient (ECC) on the performance of feature-based image registration approaches is carried out. This investigation determines if ECC improves image registration performance on datasets which test on invariance to scale, rotation and viewpoint change. Five state-of-the-arts methods are considered, namely KAZE, Binary Robust Invariant Scalable Keypoints (BRISK), Oriented FAST and Rotated Brief (ORB), Speeded-Up Robust Features (SURF), and Scale-Invariant Feature Transform (SIFT). Root-mean-squared error of control points is used to evaluate the image registration performance on datasets taken from the Oxford Robotics Database. A global ranking factor is used to rank each method within a dataset. The efficiency of each method is recorded as a guide for selecting a method for a specific application. Results indicate that ECC improves image registration performance in most cases with a small time addition.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"568 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124241611","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120613
Irfan Al-Hussaini, Zubayer Islam, Antik Mallick, M. E. Hoque
In this paper, we propound a command processing mechanism for an autonomous arm manipulator using real-time speech and images. We propose a novel two-stage speech recognition algorithm using two-fold Dynamic Time Warping in each stage. Real-time wake-up word recognition is followed by offline command recognition using k-means. Since high precision is paramount in any control system activation mechanism, a restrictive threshold is set to gain a precision of 1. This alleviates the problem of accidental triggering of the control system. Object recognition and classification is performed by matching features resulting from a local feature detector and descriptor. The algorithm controls an arm manipulator with 5 degrees of freedom.
{"title":"Object recognition and real-time spoken word recognition using two-fold dynamic time warping for autonomous arm manipulator","authors":"Irfan Al-Hussaini, Zubayer Islam, Antik Mallick, M. E. Hoque","doi":"10.1109/ICSIPA.2017.8120613","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120613","url":null,"abstract":"In this paper, we propound a command processing mechanism for an autonomous arm manipulator using real-time speech and images. We propose a novel two-stage speech recognition algorithm using two-fold Dynamic Time Warping in each stage. Real-time wake-up word recognition is followed by offline command recognition using k-means. Since high precision is paramount in any control system activation mechanism, a restrictive threshold is set to gain a precision of 1. This alleviates the problem of accidental triggering of the control system. Object recognition and classification is performed by matching features resulting from a local feature detector and descriptor. The algorithm controls an arm manipulator with 5 degrees of freedom.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115399130","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120623
Kishore Bingi, R. Ibrahim, M. N. Karsiti, S. Hassan
Control of CSTR process has been challenging due to highly nonlinear and dynamic behavior. Furthermore, the CSTR processes are unstable. The use of PID controllers for such processes has been attempted. However, poor performance is obtained due to limitations of the PID controllers. On the other hand, using heuristic algorithms to tune the controllers only gives optimal performance for a restricted range of parameter variations. This paper proposes the use of fuzzy gain scheduling (FGS) adaptation mechanism to tune set-point weighted PID controller for the CSTR process. The result of comparison from the simulation performed showed that proposed method achieved better set-point tracking and disturbance rejection compared to the FGS-PID controller.
{"title":"Fuzzy gain scheduled set-point weighted PID controller for unstable CSTR systems","authors":"Kishore Bingi, R. Ibrahim, M. N. Karsiti, S. Hassan","doi":"10.1109/ICSIPA.2017.8120623","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120623","url":null,"abstract":"Control of CSTR process has been challenging due to highly nonlinear and dynamic behavior. Furthermore, the CSTR processes are unstable. The use of PID controllers for such processes has been attempted. However, poor performance is obtained due to limitations of the PID controllers. On the other hand, using heuristic algorithms to tune the controllers only gives optimal performance for a restricted range of parameter variations. This paper proposes the use of fuzzy gain scheduling (FGS) adaptation mechanism to tune set-point weighted PID controller for the CSTR process. The result of comparison from the simulation performed showed that proposed method achieved better set-point tracking and disturbance rejection compared to the FGS-PID controller.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130765915","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120659
Babar Sultan, J. Ahmed, A. Jalil, H. Nazir, M. Abbasi, J. Shah, Ahmad Ali, Haider Ali
Use of camera has increased among professionals and nonprofessionals in recent years and videos are being captured widely and wildly for information, knowledge, surveillance, adventures and memories. So these videos are highly vulnerable to suffer from translational and rotational noises. These noise are caused by multiple factors and it is difficult to remove all those causes. So digital video stabilization is a process of acquiring and minimizing/removing the undesired motion from the video. In this paper we have presented a method which utilizes existing algorithms and techniques in a novel fashion for digital video stabilization. The quality of feature extraction is improved by using Speeded Up Robust Features (SURF) and the process for the selection of extracted features, for global motion acquisition, is also refined. Actual motion of the camera and the undesired motion are separated by applying the moving average filter. Finally, stable frames are obtained through affine transformation to produce an out of phase motion. We have also presented a way to use interpolation for improving the quality of video stabilization. Our system has been successfully tested on various videos including VIRAT dataset, disaster videos, rush hour videos, mountain cycling, street walking, TV reports etc.
{"title":"Translation and rotation invariant video stabilization for real time applications","authors":"Babar Sultan, J. Ahmed, A. Jalil, H. Nazir, M. Abbasi, J. Shah, Ahmad Ali, Haider Ali","doi":"10.1109/ICSIPA.2017.8120659","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120659","url":null,"abstract":"Use of camera has increased among professionals and nonprofessionals in recent years and videos are being captured widely and wildly for information, knowledge, surveillance, adventures and memories. So these videos are highly vulnerable to suffer from translational and rotational noises. These noise are caused by multiple factors and it is difficult to remove all those causes. So digital video stabilization is a process of acquiring and minimizing/removing the undesired motion from the video. In this paper we have presented a method which utilizes existing algorithms and techniques in a novel fashion for digital video stabilization. The quality of feature extraction is improved by using Speeded Up Robust Features (SURF) and the process for the selection of extracted features, for global motion acquisition, is also refined. Actual motion of the camera and the undesired motion are separated by applying the moving average filter. Finally, stable frames are obtained through affine transformation to produce an out of phase motion. We have also presented a way to use interpolation for improving the quality of video stabilization. Our system has been successfully tested on various videos including VIRAT dataset, disaster videos, rush hour videos, mountain cycling, street walking, TV reports etc.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127314301","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120612
Pu Chuan Hsian, Ezra Morris Abraham Gnanamuthu, Lo Fook Loong
Conventional iterative timing recovery is developed based on the widely used assumption of Additive White Gaussian noise (AWGN) interference. The Gaussian-based approach is excellent for timing recovery over AWGN channel with matched filtering approach but does not perform well in the presence of non-Gaussian noise. Overall performance of the conventional iterative timing recovery with matched filtering is significantly degraded in non-Gaussian channel. The root cause of the degradation is due to the received symbols are purged by the impulsive outliers from the non-Gaussian channels. Hence, this paper proposed a mitigation technique to address the issue for iterative timing recovery. In order to overcome this problem, a Matched Myriad filtering framework is proposed to be incorporated into iterative timing recovery as front-end receive filter. With the k tuning parameter of the robust Matched Myriad filter which caters for varying channel conditions, the iterative timing recovery can perform robustly and its performance is close to the benchmark of having its performance over the Gaussian channel. It is shown from simulations that more reliable received samples can be acquired to produce the accurate timing estimates and outputs.
{"title":"Impulsive noise suppression for robust iterative timing recovery in non-Gaussian channels","authors":"Pu Chuan Hsian, Ezra Morris Abraham Gnanamuthu, Lo Fook Loong","doi":"10.1109/ICSIPA.2017.8120612","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120612","url":null,"abstract":"Conventional iterative timing recovery is developed based on the widely used assumption of Additive White Gaussian noise (AWGN) interference. The Gaussian-based approach is excellent for timing recovery over AWGN channel with matched filtering approach but does not perform well in the presence of non-Gaussian noise. Overall performance of the conventional iterative timing recovery with matched filtering is significantly degraded in non-Gaussian channel. The root cause of the degradation is due to the received symbols are purged by the impulsive outliers from the non-Gaussian channels. Hence, this paper proposed a mitigation technique to address the issue for iterative timing recovery. In order to overcome this problem, a Matched Myriad filtering framework is proposed to be incorporated into iterative timing recovery as front-end receive filter. With the k tuning parameter of the robust Matched Myriad filter which caters for varying channel conditions, the iterative timing recovery can perform robustly and its performance is close to the benchmark of having its performance over the Gaussian channel. It is shown from simulations that more reliable received samples can be acquired to produce the accurate timing estimates and outputs.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123168320","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120586
N. Mohammad, Z. Omar, U. U. Sheikh, A. Rahman, M. Sahrim
Aortic stenosis (AS) is a condition where the calcification deposit within the heart leaflets narrows the valve and restricts the blood from flowing through it. This disease is progressive over time where it may affect the mechanism of the heart valve. To alleviate this condition without resorting to surgery, which runs the risk of mortality, a new method of treatment has been introduced: Transcatheter Aortic Valve Implantation (TAVI), in which imagery acquired from real-time echocardiogram (Echo) are needed to determine the exact size of aortic annulus. However, Echo data often suffers from speckle noise and low pixel resolution, which may result in incorrect sizing of the annulus. Our study therefore aims to perform an automated detection and measurement of aortic annulus size from Echo imagery. Two stages of algorithm are presented — image denoising and object detection. For the removal of speckle noise, Wavelet thresholding technique is applied. It consists of three sequential steps; applying linear discrete wavelet transform, thresholding wavelet coefficients and performing linear inverse wavelet transform. For the next stage of analysis, several morphological operations are used to perform object detection as well as valve sizing. The results showed that the automated system is able to produce more accurate sizing based on ground truth.
{"title":"Wavelet-based aortic annulus sizing of echocardiography images","authors":"N. Mohammad, Z. Omar, U. U. Sheikh, A. Rahman, M. Sahrim","doi":"10.1109/ICSIPA.2017.8120586","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120586","url":null,"abstract":"Aortic stenosis (AS) is a condition where the calcification deposit within the heart leaflets narrows the valve and restricts the blood from flowing through it. This disease is progressive over time where it may affect the mechanism of the heart valve. To alleviate this condition without resorting to surgery, which runs the risk of mortality, a new method of treatment has been introduced: Transcatheter Aortic Valve Implantation (TAVI), in which imagery acquired from real-time echocardiogram (Echo) are needed to determine the exact size of aortic annulus. However, Echo data often suffers from speckle noise and low pixel resolution, which may result in incorrect sizing of the annulus. Our study therefore aims to perform an automated detection and measurement of aortic annulus size from Echo imagery. Two stages of algorithm are presented — image denoising and object detection. For the removal of speckle noise, Wavelet thresholding technique is applied. It consists of three sequential steps; applying linear discrete wavelet transform, thresholding wavelet coefficients and performing linear inverse wavelet transform. For the next stage of analysis, several morphological operations are used to perform object detection as well as valve sizing. The results showed that the automated system is able to produce more accurate sizing based on ground truth.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125271126","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：