Pub Date : 2019-11-01DOI: 10.1109/SITIS.2019.00034
Muhammad Ilyas, A. Naït-Ali
Hearing loss or hearing impairment is the primary reason of deafness throughout the world. Hearing impairment can occur to one or both the ears. If hearing loss is identified in time, it can be minimized by practicing specific precautions. In this paper, we investigate the likelihood of detection of hearing loss through auditory system responses. Auditory perception and human age are highly interrelated. Likewise, detecting a significant gap within the real age and the estimated age, the hearing loss can easily be identified. Our proposed system for human age estimation has promising results with a Root Mean Square Error (RMSE) value of 4.1 years, and classification performance efficiency for hearing loss is 94%, showing the applicability of our approach for detection of hearing loss.
{"title":"Machine Learning Based Detection of Hearing Loss Using Auditory Perception Responses","authors":"Muhammad Ilyas, A. Naït-Ali","doi":"10.1109/SITIS.2019.00034","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00034","url":null,"abstract":"Hearing loss or hearing impairment is the primary reason of deafness throughout the world. Hearing impairment can occur to one or both the ears. If hearing loss is identified in time, it can be minimized by practicing specific precautions. In this paper, we investigate the likelihood of detection of hearing loss through auditory system responses. Auditory perception and human age are highly interrelated. Likewise, detecting a significant gap within the real age and the estimated age, the hearing loss can easily be identified. Our proposed system for human age estimation has promising results with a Root Mean Square Error (RMSE) value of 4.1 years, and classification performance efficiency for hearing loss is 94%, showing the applicability of our approach for detection of hearing loss.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115683679","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 : 2019-11-01DOI: 10.1109/SITIS.2019.00119
J. Filip, M. Kolafová, R. Vávra
Quality control applications in the coating industry characterize visual properties of coatings containing effect pigments using glint impression, often denoted as sparkle. They rely on a collection of static images capturing sparkle properties of pigment flakes. However, visual characteristics of pigment flakes are highly correlated to their material properties and their orientations in coating layers. Thus, while two effect coatings can exhibit similar static sparkle behavior, their dynamic sparkle behavior may be very distinct. In this paper, we analyzed the perception of static and dynamic sparkle using two psychophysical studies on 38 effect coatings and 31 human subjects. First, we have shown a good agreement between the perception of sparkle in real specimens and in photographs. Second, we observed significant differences in perceived static and dynamic sparkle. Our results demonstrate a need for a multiangle recording of sparkle when assessing effect pigment visual characteristics.
{"title":"Perceived Effects of Static and Dynamic Sparkle in Captured Effect Coatings","authors":"J. Filip, M. Kolafová, R. Vávra","doi":"10.1109/SITIS.2019.00119","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00119","url":null,"abstract":"Quality control applications in the coating industry characterize visual properties of coatings containing effect pigments using glint impression, often denoted as sparkle. They rely on a collection of static images capturing sparkle properties of pigment flakes. However, visual characteristics of pigment flakes are highly correlated to their material properties and their orientations in coating layers. Thus, while two effect coatings can exhibit similar static sparkle behavior, their dynamic sparkle behavior may be very distinct. In this paper, we analyzed the perception of static and dynamic sparkle using two psychophysical studies on 38 effect coatings and 31 human subjects. First, we have shown a good agreement between the perception of sparkle in real specimens and in photographs. Second, we observed significant differences in perceived static and dynamic sparkle. Our results demonstrate a need for a multiangle recording of sparkle when assessing effect pigment visual characteristics.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"33 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120973704","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 : 2019-11-01DOI: 10.1109/SITIS.2019.00105
P. D. Luca, A. Galletti, L. Marcellino
Gaussian convolutions computation is required in several scientific fields and, to this aim, efficient approximation methods, based on Recursive Filters (RFs), have been developed recently. Among them, Gaussian Recursive Filters (RFs) are designed to approximate the Gaussian convolution in a very efficient way. The accuracy of these methods, as is well known, can be improved by means of the use of the so-called K-iterated Gaussian recursive filters, that is in the repeated application of the basic RF. To improve the provided accuracy, K-iterated versions of these methods are also considered. Since it is often necessary to handle large size one-dimensional input signals, a parallel approach becomes mandatory. Recently, we proposed a parallel algorithm for the implementation of the K-iterated first-order Gaussian RF on multicore architectures. Here, using a similar parallelization strategy, based on a domain decomposition with overlapping, we propose a new implementation that would exploit, in terms of both accuracy and performance, the GPU (Graphics Processing Unit) capabilities on CUDA environment. Tests and experiments confirm the reliability and the efficiency of the proposed implementation.
{"title":"A Gaussian Recursive Filter Parallel Implementation with Overlapping","authors":"P. D. Luca, A. Galletti, L. Marcellino","doi":"10.1109/SITIS.2019.00105","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00105","url":null,"abstract":"Gaussian convolutions computation is required in several scientific fields and, to this aim, efficient approximation methods, based on Recursive Filters (RFs), have been developed recently. Among them, Gaussian Recursive Filters (RFs) are designed to approximate the Gaussian convolution in a very efficient way. The accuracy of these methods, as is well known, can be improved by means of the use of the so-called K-iterated Gaussian recursive filters, that is in the repeated application of the basic RF. To improve the provided accuracy, K-iterated versions of these methods are also considered. Since it is often necessary to handle large size one-dimensional input signals, a parallel approach becomes mandatory. Recently, we proposed a parallel algorithm for the implementation of the K-iterated first-order Gaussian RF on multicore architectures. Here, using a similar parallelization strategy, based on a domain decomposition with overlapping, we propose a new implementation that would exploit, in terms of both accuracy and performance, the GPU (Graphics Processing Unit) capabilities on CUDA environment. Tests and experiments confirm the reliability and the efficiency of the proposed implementation.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"55 21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115351211","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 : 2019-11-01DOI: 10.1109/SITIS.2019.00024
Kazuki Kurihara, Hiromi Yoshida, Y. Iiguni
Low light images affect various computer vision algorithms due to their low visibility and much noise hidden in dark regions. Although many methods based on the Retinex theory, which decomposes an observed image into the reflectance and illumination, have been proposed to alleviate the problem, existing methods inevitably cause under-and over-enhancement. In this paper, we propose a new joint optimization equation that sufficiently considers the features of both reflectance and illumination. More concretely, we adopt L2-Lp norm regularization terms to estimate the reflectance as much as possible to preserve details and textures, and the illumination as much as possible to preserve the structure information with texture-less. We solve the optimization equation in an alternating minimization method. Furthermore, we introduce a new adaptive texture prior to reveal more details and textures with noise reduction on both bright and dark regions. Experimental results, including qualitative and quantitative evaluations, show that the proposed method can establish a better performance than the other state-of-the-art methods.
{"title":"Low-Light Image Enhancement via Adaptive Shape and Texture Prior","authors":"Kazuki Kurihara, Hiromi Yoshida, Y. Iiguni","doi":"10.1109/SITIS.2019.00024","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00024","url":null,"abstract":"Low light images affect various computer vision algorithms due to their low visibility and much noise hidden in dark regions. Although many methods based on the Retinex theory, which decomposes an observed image into the reflectance and illumination, have been proposed to alleviate the problem, existing methods inevitably cause under-and over-enhancement. In this paper, we propose a new joint optimization equation that sufficiently considers the features of both reflectance and illumination. More concretely, we adopt L2-Lp norm regularization terms to estimate the reflectance as much as possible to preserve details and textures, and the illumination as much as possible to preserve the structure information with texture-less. We solve the optimization equation in an alternating minimization method. Furthermore, we introduce a new adaptive texture prior to reveal more details and textures with noise reduction on both bright and dark regions. Experimental results, including qualitative and quantitative evaluations, show that the proposed method can establish a better performance than the other state-of-the-art methods.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122459919","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 : 2019-11-01DOI: 10.1109/SITIS.2019.00076
Reda Belaiche, C. Migniot, D. Ginhac, Fan Yang
Machine learning has known a tremendous growth within the last years, and lately, thanks to that, some computer vision algorithms started to access what is difficult or even impossible to perceive by the human eye. While deep learning based computer vision algorithms have made themselves more and more present in the recent years, more classical feature extraction methods, such as the ones based on Local Binary Patterns (LBP), still present a non negligible interest, especially when dealing with small datasets. Furthermore, this operator has proven to be quite useful for facial emotions and human gestures recognition in general. Micro-Expression (ME) classification is among the applications of computer vision that heavily relied on hand crafted features in the past years. LBP Three Orthogonal Planes (LBP_TOP) is one of the most used hand crafted features extractor in the scientific literature to tackle the problem of ME classification. In this paper we present a time unification method that provides better results than the classical LBP_TOP while also drastically reducing the calculations required for feature extraction.
{"title":"Time Unification on Local Binary Patterns Three Orthogonal Planes for Facial Expression Recognition","authors":"Reda Belaiche, C. Migniot, D. Ginhac, Fan Yang","doi":"10.1109/SITIS.2019.00076","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00076","url":null,"abstract":"Machine learning has known a tremendous growth within the last years, and lately, thanks to that, some computer vision algorithms started to access what is difficult or even impossible to perceive by the human eye. While deep learning based computer vision algorithms have made themselves more and more present in the recent years, more classical feature extraction methods, such as the ones based on Local Binary Patterns (LBP), still present a non negligible interest, especially when dealing with small datasets. Furthermore, this operator has proven to be quite useful for facial emotions and human gestures recognition in general. Micro-Expression (ME) classification is among the applications of computer vision that heavily relied on hand crafted features in the past years. LBP Three Orthogonal Planes (LBP_TOP) is one of the most used hand crafted features extractor in the scientific literature to tackle the problem of ME classification. In this paper we present a time unification method that provides better results than the classical LBP_TOP while also drastically reducing the calculations required for feature extraction.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121674082","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 : 2019-11-01DOI: 10.1109/SITIS.2019.00035
Stefano Savian, Mehdi Elahi, T. Tillo
Optical Flow (OF) estimation is an important task which could be effectively used for a variety of Computer Vision (CV) applications. While a range of techniques have been already proposed, however accurately estimating the OF is still a very challenging task. The most recent approaches for OF estimation exploit advanced Deep Learning techniques which have resulted in a shift in the paradigm. These techniques have shown substantial improvements particularly in the case of large displacements, brightness change, and non-rigid motion. However, these approaches are data-driven and hence they can be biased towards the specific training data, which could in turn lead to considerable inaccuracy of the estimated OF. In this paper, we address this problem and provide a novel benchmark that can be used to identify and to measure the bias magnitude of the OF estimation. We have performed several experiments based on public datasets (Monkaa and Sintel) as well as on data designed on purpose 1. The results have shown that OF estimation based on some of the state-of-the-art deep learning techniques strongly depend on factors such as motion orientation within the data. Indeed, we have observed substantial degree of bias toward certain directions of motion. The framework can help researchers and practitioners in order to develop more effective data augmentation techniques and training schedules for deep learning based optical flow estimators.
{"title":"Benchmarking The Imbalanced Behavior of Deep Learning Based Optical Flow Estimators","authors":"Stefano Savian, Mehdi Elahi, T. Tillo","doi":"10.1109/SITIS.2019.00035","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00035","url":null,"abstract":"Optical Flow (OF) estimation is an important task which could be effectively used for a variety of Computer Vision (CV) applications. While a range of techniques have been already proposed, however accurately estimating the OF is still a very challenging task. The most recent approaches for OF estimation exploit advanced Deep Learning techniques which have resulted in a shift in the paradigm. These techniques have shown substantial improvements particularly in the case of large displacements, brightness change, and non-rigid motion. However, these approaches are data-driven and hence they can be biased towards the specific training data, which could in turn lead to considerable inaccuracy of the estimated OF. In this paper, we address this problem and provide a novel benchmark that can be used to identify and to measure the bias magnitude of the OF estimation. We have performed several experiments based on public datasets (Monkaa and Sintel) as well as on data designed on purpose 1. The results have shown that OF estimation based on some of the state-of-the-art deep learning techniques strongly depend on factors such as motion orientation within the data. Indeed, we have observed substantial degree of bias toward certain directions of motion. The framework can help researchers and practitioners in order to develop more effective data augmentation techniques and training schedules for deep learning based optical flow estimators.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124319970","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 : 2019-11-01DOI: 10.1109/SITIS.2019.00096
István Megyeri, Melinda Katona, L. G. Nyúl
Optical Coherence Tomography (OCT) has become a basic non-invasive tool in diagnosing and following different types of eye diseases. This technique can produce high-resolution cross-sectional images of retinal layers. Outer retinal tubulation (ORT) is one of the detectable biomarker by SD-OCT. ORTs defined as hyporeflective, tubular structures with hyperreflective borders or reversed within the retina and appear in many retinal diseases, including age-related macular degeneration (AMD). Our aim is to develop an automatic method that can efficiently characterize ORT biomarker. Detection of this biomarker can be challenging because of its variable size, location, and reflectivity. In this paper, we present a fully convolutional U-Net based architecture to detect ORT. The proposed approach is evaluated using a dataset annotated by ophthalmologists. One of the main challenges was the limited amount of training data that we resolve with real-time augmentation during training and using nested cross-validation. Our method achieved near human performance reaching an overall object-based recall score of 0.847 and Dice score of 0.579 on the test set.
{"title":"A Novel Approach to Detect Outer Retinal Tubulation Using U-Net in SD-OCT Images","authors":"István Megyeri, Melinda Katona, L. G. Nyúl","doi":"10.1109/SITIS.2019.00096","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00096","url":null,"abstract":"Optical Coherence Tomography (OCT) has become a basic non-invasive tool in diagnosing and following different types of eye diseases. This technique can produce high-resolution cross-sectional images of retinal layers. Outer retinal tubulation (ORT) is one of the detectable biomarker by SD-OCT. ORTs defined as hyporeflective, tubular structures with hyperreflective borders or reversed within the retina and appear in many retinal diseases, including age-related macular degeneration (AMD). Our aim is to develop an automatic method that can efficiently characterize ORT biomarker. Detection of this biomarker can be challenging because of its variable size, location, and reflectivity. In this paper, we present a fully convolutional U-Net based architecture to detect ORT. The proposed approach is evaluated using a dataset annotated by ophthalmologists. One of the main challenges was the limited amount of training data that we resolve with real-time augmentation during training and using nested cross-validation. Our method achieved near human performance reaching an overall object-based recall score of 0.847 and Dice score of 0.579 on the test set.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124320451","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}
No one refutes the importance of datasets in the development of any new approach. Despite their importance, datasets in computer vision remain insufficient for some applications. Presently, very limited autism datasets associated with clinical tests or screening are available, and most of them are genetic in nature. However, there is no database that combines both the abnormal facial expressions and the aggressive behaviors of an autistic child during Meltdown crisis. This paper introduces a Meltdown Crisis, a new and rich dataset that can be used for the evaluation/development of computer vision-based applications pertinent to children who suffer of autism as security tool, e.g. Meltdown crisis detection. In particular, the "MeltdownCrisis" dataset includes video streams captured with Kinect which offers a wide range of visual information. It is divided on a facial expressions data and physical activities data. The current "MeltdownCrisis " dataset version covers several Meltdown crisis scenarios of autistic children along various normal state scenarios grouped into one set. Each scenario is represented through a rich set of features that can be extracted from Kinect camera.
{"title":"MeltdownCrisis: Dataset of Autistic Children During Meltdown Crisis","authors":"Marwa Masmoudi, Salma Kammoun Jarraya, Mohamed Hammami","doi":"10.1109/SITIS.2019.00048","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00048","url":null,"abstract":"No one refutes the importance of datasets in the development of any new approach. Despite their importance, datasets in computer vision remain insufficient for some applications. Presently, very limited autism datasets associated with clinical tests or screening are available, and most of them are genetic in nature. However, there is no database that combines both the abnormal facial expressions and the aggressive behaviors of an autistic child during Meltdown crisis. This paper introduces a Meltdown Crisis, a new and rich dataset that can be used for the evaluation/development of computer vision-based applications pertinent to children who suffer of autism as security tool, e.g. Meltdown crisis detection. In particular, the \"MeltdownCrisis\" dataset includes video streams captured with Kinect which offers a wide range of visual information. It is divided on a facial expressions data and physical activities data. The current \"MeltdownCrisis \" dataset version covers several Meltdown crisis scenarios of autistic children along various normal state scenarios grouped into one set. Each scenario is represented through a rich set of features that can be extracted from Kinect camera.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124475902","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 : 2019-11-01DOI: 10.1109/SITIS.2019.00064
Tung Pham Thanh, S. Benferhat, M. Chau, T. Ma, Karim Tabia, L. T. Ha
The problem addressed in this paper is the one of classifying Vietnamese dances' videos. In particular, we focus on an automatic detection of movements in the Ethnic Vietnamese Thai dances (ETVD). We first propose an ontology-based description of ETVD movements in terms of main movements' steps. We then associate with each movement step a profile containing typical features that characterize a movement step. The automatic detection of ETVD movements is based on a correlation method that matches movements' steps profiles with concepts present in frames of dances' videos. The last part of the paper contain experimental studies that show the good classification rate of our ETVD movement detection method.
{"title":"On the Detection of Video's Ethnic Vietnamese Thai Dance Movements","authors":"Tung Pham Thanh, S. Benferhat, M. Chau, T. Ma, Karim Tabia, L. T. Ha","doi":"10.1109/SITIS.2019.00064","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00064","url":null,"abstract":"The problem addressed in this paper is the one of classifying Vietnamese dances' videos. In particular, we focus on an automatic detection of movements in the Ethnic Vietnamese Thai dances (ETVD). We first propose an ontology-based description of ETVD movements in terms of main movements' steps. We then associate with each movement step a profile containing typical features that characterize a movement step. The automatic detection of ETVD movements is based on a correlation method that matches movements' steps profiles with concepts present in frames of dances' videos. The last part of the paper contain experimental studies that show the good classification rate of our ETVD movement detection method.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126278633","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 : 2019-11-01DOI: 10.1109/SITIS.2019.00021
M. Stasolla, X. Neyt
This paper presents a new method for the detection of abrupt changes (i.e. mean shifts) in time series. It is a follow-up to a previous article by the authors where, for the first time, the possibility of combining the multi-scale analysis capabilities of wavelets with mathematical morphology, a theoretical framework for the analysis of spatial structures, had been explored. The processing chain has been revised and enhanced in order to improve the overall results, and a performance assessment has been carried out to evaluate the accuracy and robustness of the method to noise, also providing a comparison with its original implementation.
{"title":"Enhanced Morphological Filtering for Wavelet-Based Changepoint Detection","authors":"M. Stasolla, X. Neyt","doi":"10.1109/SITIS.2019.00021","DOIUrl":"https://doi.org/10.1109/SITIS.2019.00021","url":null,"abstract":"This paper presents a new method for the detection of abrupt changes (i.e. mean shifts) in time series. It is a follow-up to a previous article by the authors where, for the first time, the possibility of combining the multi-scale analysis capabilities of wavelets with mathematical morphology, a theoretical framework for the analysis of spatial structures, had been explored. The processing chain has been revised and enhanced in order to improve the overall results, and a performance assessment has been carried out to evaluate the accuracy and robustness of the method to noise, also providing a comparison with its original implementation.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115777141","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：