Pub Date : 2017-05-01DOI: 10.1109/ATSIP.2017.8075546
Lahcen El Bouny, Mohammed Khalil, A. Adib
In this paper, we propose a new ECG signal enhancement based on Ensemble Empirical Mode Decomposition (EEMD) and Higher Order Statistics (HOS). In our scheme, the EEMD is used to decompose adaptively the noisy ECG signal into Intrinsic Mode Functions (IMFs), and a novel criterion based on kurtosis is proposed to determine the IMFs that contain sufficient information about the QRS complex in ECG signal and which need to be filtered. After that, two EEMD interval thresholding methods have been applied to each selected IMF in order to reduce the noise and to preserve the QRS complex. The final denoised ECG signal is then reconstructed by summing the thresholded IMFs with the retained unprocessed lower frequency IMFs. To assess the usefulness of our approach, we evaluate the performance of the proposed scheme on a set of real ECG signals acquired from MIT-BIH arrhythmia database. The experimental results demonstrate that the proposed method shows better Signal to Noise Ratio (SNR) and lower Mean Square Error (MSE) compared to some of the state-of-the-art denoising methods.
{"title":"ECG signal denoising based on ensemble emd thresholding and higher order statistics","authors":"Lahcen El Bouny, Mohammed Khalil, A. Adib","doi":"10.1109/ATSIP.2017.8075546","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075546","url":null,"abstract":"In this paper, we propose a new ECG signal enhancement based on Ensemble Empirical Mode Decomposition (EEMD) and Higher Order Statistics (HOS). In our scheme, the EEMD is used to decompose adaptively the noisy ECG signal into Intrinsic Mode Functions (IMFs), and a novel criterion based on kurtosis is proposed to determine the IMFs that contain sufficient information about the QRS complex in ECG signal and which need to be filtered. After that, two EEMD interval thresholding methods have been applied to each selected IMF in order to reduce the noise and to preserve the QRS complex. The final denoised ECG signal is then reconstructed by summing the thresholded IMFs with the retained unprocessed lower frequency IMFs. To assess the usefulness of our approach, we evaluate the performance of the proposed scheme on a set of real ECG signals acquired from MIT-BIH arrhythmia database. The experimental results demonstrate that the proposed method shows better Signal to Noise Ratio (SNR) and lower Mean Square Error (MSE) compared to some of the state-of-the-art denoising methods.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114740639","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075603
Malek Boujebli, Hassen Drira, M. Mestiri, I. Farah
Human action recognition is currently a hot topic research domain including a variety of applications such as human HMI, rehabilitation and surveillance. The majority of existing approaches are based on the skeleton. They utilize either the joint locations or the joint angles in order to present a human skeleton. This study introduce a novel framework, which allows compact representation, quick comparison and accurate recognition of human action in video sequences from depth sensors. First, we represent the evolution of body parts in successive frames by rotations and translations. Mathematically, in 3D space, rigid body transformations are members of the special Euclidean group SE(3). We can represent the actions by trajectories in the Lie group SE(3) ×…× SE(3) with the proposed skeleton representation. We map these trajectories from Lie group to the corresponding Lie algebra se(3) ×…× se(3), by using the identity element of the group in the tangent space group. We propose then to use an elastic shape analysis framework to compare the resulting trajectories in the lie algebra, thus the comparison is invariant to the rate of execution of the action. Finally, a Hoeffding tree (VFDT)-based classification is performed. Experimentations on two challenging action datasets show that our proposed approach operates equally well or better when compared to state of the art.
{"title":"Rate invariant action recognition in Lie algebra","authors":"Malek Boujebli, Hassen Drira, M. Mestiri, I. Farah","doi":"10.1109/ATSIP.2017.8075603","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075603","url":null,"abstract":"Human action recognition is currently a hot topic research domain including a variety of applications such as human HMI, rehabilitation and surveillance. The majority of existing approaches are based on the skeleton. They utilize either the joint locations or the joint angles in order to present a human skeleton. This study introduce a novel framework, which allows compact representation, quick comparison and accurate recognition of human action in video sequences from depth sensors. First, we represent the evolution of body parts in successive frames by rotations and translations. Mathematically, in 3D space, rigid body transformations are members of the special Euclidean group SE(3). We can represent the actions by trajectories in the Lie group SE(3) ×…× SE(3) with the proposed skeleton representation. We map these trajectories from Lie group to the corresponding Lie algebra se(3) ×…× se(3), by using the identity element of the group in the tangent space group. We propose then to use an elastic shape analysis framework to compare the resulting trajectories in the lie algebra, thus the comparison is invariant to the rate of execution of the action. Finally, a Hoeffding tree (VFDT)-based classification is performed. Experimentations on two challenging action datasets show that our proposed approach operates equally well or better when compared to state of the art.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121860078","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075513
R. Baklouti, M. Mansouri, H. Nounou, M. Nounou, M. Slima, A. Hamida
In this paper, we address the problem of nonlinear fault detection of chemical processes. The objective is to extend our previous work [1] to provide a better performance in terms of fault detection accuracies by developing a pre-image kernel PCA (KPCA)-based Generalized Likelihood Ratio Test (GLRT) technique. The benefit of the pre-image kPCA technique lies in its ability to compute the residual in the original space using the KPCA from the feature space. In addition, GLRT provides more accurate results in terms of fault detection. The performance of the developed pre-image KPCA-based GLRT fault detection technique is evaluated using simulated continuously stirred tank reactor (CSTR) model.
{"title":"Fault detection of chemical processes using KPCA-based GLRT technique","authors":"R. Baklouti, M. Mansouri, H. Nounou, M. Nounou, M. Slima, A. Hamida","doi":"10.1109/ATSIP.2017.8075513","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075513","url":null,"abstract":"In this paper, we address the problem of nonlinear fault detection of chemical processes. The objective is to extend our previous work [1] to provide a better performance in terms of fault detection accuracies by developing a pre-image kernel PCA (KPCA)-based Generalized Likelihood Ratio Test (GLRT) technique. The benefit of the pre-image kPCA technique lies in its ability to compute the residual in the original space using the KPCA from the feature space. In addition, GLRT provides more accurate results in terms of fault detection. The performance of the developed pre-image KPCA-based GLRT fault detection technique is evaluated using simulated continuously stirred tank reactor (CSTR) model.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124789719","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075588
Meriem Hacini, Akram Hacini, H. Akdag, F. Hachouf
Feature extraction is a classic problem of machine vision and image processing. Edges are often detected using integer-order differential operators. In this paper, a one-dimensional digital fractional-order Charef differentiator (1D-FCD) is introduced and extended to 2D by a multi-directional operator. The obtained 2D-fractional differentiation (2D-FCD) is a new edge detection operation. The computed multi-directional mask coefficients are computed in a way that image details are detected and preserved. Experiments on texture images have demonstrated the efficiency of the proposed filter compared to existing techniques.
{"title":"A 2D-fractional derivative mask for image feature edge detection","authors":"Meriem Hacini, Akram Hacini, H. Akdag, F. Hachouf","doi":"10.1109/ATSIP.2017.8075588","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075588","url":null,"abstract":"Feature extraction is a classic problem of machine vision and image processing. Edges are often detected using integer-order differential operators. In this paper, a one-dimensional digital fractional-order Charef differentiator (1D-FCD) is introduced and extended to 2D by a multi-directional operator. The obtained 2D-fractional differentiation (2D-FCD) is a new edge detection operation. The computed multi-directional mask coefficients are computed in a way that image details are detected and preserved. Experiments on texture images have demonstrated the efficiency of the proposed filter compared to existing techniques.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123600208","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075609
A. Abbad, K. Abbad, H. Tairi
In this paper we propose a new post-processing approach for dimensionality reduction methods based on multidimensional ensemble empirical mode decomposition (MEEMD). In the proposed method, the features are decomposed into different components and then we maximize the dependency and the dispersion between classes thanks to Gaussian filter and Butterworth filter. The performance of the proposed algorithm is demonstrated in experiments by several dimensionality reduction techniques on two public databases.
{"title":"An efficient post-processing approach for dimensionality reduction methods for face recognition","authors":"A. Abbad, K. Abbad, H. Tairi","doi":"10.1109/ATSIP.2017.8075609","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075609","url":null,"abstract":"In this paper we propose a new post-processing approach for dimensionality reduction methods based on multidimensional ensemble empirical mode decomposition (MEEMD). In the proposed method, the features are decomposed into different components and then we maximize the dependency and the dispersion between classes thanks to Gaussian filter and Butterworth filter. The performance of the proposed algorithm is demonstrated in experiments by several dimensionality reduction techniques on two public databases.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134591120","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075536
B. Boufama, Pejman Habashi, Imran Ahmad
Sparse representation is widely used by different human activity recognition methods. Although many sparse feature extraction algorithms have been proposed in the literature, most of them focused on low-level features. This paper proposes a new method using trajectories, as mid-level features, for human activity recognition. Even though the use of trajectories is not new in this field, their potential is yet to be fully attained. In this paper, inspired by previous works, we have proposed new trajectory extraction methods, which are very flexible. Then we have emphasized the difference between trajectories and traditional descriptors, and have shown the advantages of using trajectories for human activity recognition. The pros and cons of trajectories are demonstrated through proposed trajectory-based methods. We have used a simple shape descriptor and the standard bag of word algorithm for human activity classification. The results of these different algorithms have been compared. We have also compared our results with other popular existing methods based on low level extracted features. In particular, we have shown that using proposed sparse trajectories can produce similar or better results than using dense trajectories. Furthermore, the computational time has been reduced as we are dealing with fewer data.
{"title":"Trajectory-based human activity recognition from videos","authors":"B. Boufama, Pejman Habashi, Imran Ahmad","doi":"10.1109/ATSIP.2017.8075536","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075536","url":null,"abstract":"Sparse representation is widely used by different human activity recognition methods. Although many sparse feature extraction algorithms have been proposed in the literature, most of them focused on low-level features. This paper proposes a new method using trajectories, as mid-level features, for human activity recognition. Even though the use of trajectories is not new in this field, their potential is yet to be fully attained. In this paper, inspired by previous works, we have proposed new trajectory extraction methods, which are very flexible. Then we have emphasized the difference between trajectories and traditional descriptors, and have shown the advantages of using trajectories for human activity recognition. The pros and cons of trajectories are demonstrated through proposed trajectory-based methods. We have used a simple shape descriptor and the standard bag of word algorithm for human activity classification. The results of these different algorithms have been compared. We have also compared our results with other popular existing methods based on low level extracted features. In particular, we have shown that using proposed sparse trajectories can produce similar or better results than using dense trajectories. Furthermore, the computational time has been reduced as we are dealing with fewer data.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114392300","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075551
Soumaya Zribi, Imen Messaoudi, A. Oueslati, Z. Lachiri
Microsatellites, or short tandem repeats (STRs), belong to the category of DNA tandem repeats which are present in all genomes with a size of 1 to 6 base-pairs. They are useful in several research domains such as population studies and DNA fingerprinting. They are also the cause of diverse genetic diseases. Thus, it's important to characterize and define them. Bioinformatics tools still deficient in this field because they demand a prior knowledge of repeat. Things which cannot be always available in databases. Signal and image processing scientists looked up for more efficient methods to remediate to these tool's limits. In this paper, we investigate microsatellites’ characterization in the DNA sequence using a new modification on the S-Transform (ST) analysis applied on the PNUC coding. To study further about the contribution of our method in the detection of STRs, a comparison with different methods including bioinformatics tools (TRF, Mreps, Etandem, AST, PSE, EMWD and Parametric) is established.
{"title":"Identification of microsatellites in DNA sequence based on S-transform","authors":"Soumaya Zribi, Imen Messaoudi, A. Oueslati, Z. Lachiri","doi":"10.1109/ATSIP.2017.8075551","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075551","url":null,"abstract":"Microsatellites, or short tandem repeats (STRs), belong to the category of DNA tandem repeats which are present in all genomes with a size of 1 to 6 base-pairs. They are useful in several research domains such as population studies and DNA fingerprinting. They are also the cause of diverse genetic diseases. Thus, it's important to characterize and define them. Bioinformatics tools still deficient in this field because they demand a prior knowledge of repeat. Things which cannot be always available in databases. Signal and image processing scientists looked up for more efficient methods to remediate to these tool's limits. In this paper, we investigate microsatellites’ characterization in the DNA sequence using a new modification on the S-Transform (ST) analysis applied on the PNUC coding. To study further about the contribution of our method in the detection of STRs, a comparison with different methods including bioinformatics tools (TRF, Mreps, Etandem, AST, PSE, EMWD and Parametric) is established.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133465514","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075557
Mohammed Assaouy, O. Zytoune, D. Aboutajdine
In this paper, we consider a wireless point-to-point communication in the context of battery powered embedded systems with energy harvesting equipment. The successive actions taken by the transmitter constitutes the policy that it follows. In the first stage, we suppose a limited knowledge of the system behavior characterized by its probability transition matrix, and then use the policy iteration algorithm to find the optimal policy. In the second stage, we consider that such basic stochastic knowledge is not available at the transmitter, and consider the Q-Sarsa algorithm to find out optimal policies. The two approaches are first simulated and then compared.
{"title":"Policy iteration vs Q-Sarsa approach optimization for embedded system communications with energy harvesting","authors":"Mohammed Assaouy, O. Zytoune, D. Aboutajdine","doi":"10.1109/ATSIP.2017.8075557","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075557","url":null,"abstract":"In this paper, we consider a wireless point-to-point communication in the context of battery powered embedded systems with energy harvesting equipment. The successive actions taken by the transmitter constitutes the policy that it follows. In the first stage, we suppose a limited knowledge of the system behavior characterized by its probability transition matrix, and then use the policy iteration algorithm to find the optimal policy. In the second stage, we consider that such basic stochastic knowledge is not available at the transmitter, and consider the Q-Sarsa algorithm to find out optimal policies. The two approaches are first simulated and then compared.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121686305","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075529
L. Elmansouri
Currently in Morocco, crop plantation information is mostly collected by three ways: (1) farmer communications, (2) spatially limited land survey and (3) manually photo-interpretation of a newly registered digital image. These procedures provide limited and subjective information with unguaranteed consistency. Land survey could map accurately crop types but it's too time, high cost and labor-intensive which limits its use as a periodic process to monitor crop changes. Remote sensing imagery is shown to be a cost-effective crop mapping approach which can be regularly used to produce an accurate and up-to-date crop map at the different temporal and spatial resolution. In this paper, a phenology based-time series-multiple classifier combination approach is developed instead of a classical one-image-one classifier approach to map crop types. The whole process is performed mainly on four steps. First, all images were radiometrically and atmospherically corrected and the specific ETM+ gap had been resolved. Then, a phonological metrics are extracted from annual Enhanced Vegetation Index (EVI) profiles. In the third step, two classical supervised learning algorithms: Decision Tree (DT), K Near Neighborhood (KNN) and four advanced ones: Support Vector Machines (SVM), Bagging, Random Forest (RF) and Extremely Randomized Trees (Extra Trees) are used in ascending experimental protocol of 3 levels of crossed validation to (1) adjust classifiers' parameters, (2) select the best three classifiers to combine and (3) find the best linear combination from five ones tested. All these three optimization operations are done according to the best error rate computed based on f-measure of omission and commission errors. In the last, the final pixels' prediction is deducted thanks to average decision given by (SVM, RF and Extra Trees) which outperforms the best individual classifier score and all other tested combiners. We show the efficiency of the proposed scheme with experiments carried out with 11 LANDSAT free cloud images depicting Gharb region, one of the largest agriculture plain in Morocco.
{"title":"Multiple classifier combination for crop types phenology based mapping","authors":"L. Elmansouri","doi":"10.1109/ATSIP.2017.8075529","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075529","url":null,"abstract":"Currently in Morocco, crop plantation information is mostly collected by three ways: (1) farmer communications, (2) spatially limited land survey and (3) manually photo-interpretation of a newly registered digital image. These procedures provide limited and subjective information with unguaranteed consistency. Land survey could map accurately crop types but it's too time, high cost and labor-intensive which limits its use as a periodic process to monitor crop changes. Remote sensing imagery is shown to be a cost-effective crop mapping approach which can be regularly used to produce an accurate and up-to-date crop map at the different temporal and spatial resolution. In this paper, a phenology based-time series-multiple classifier combination approach is developed instead of a classical one-image-one classifier approach to map crop types. The whole process is performed mainly on four steps. First, all images were radiometrically and atmospherically corrected and the specific ETM+ gap had been resolved. Then, a phonological metrics are extracted from annual Enhanced Vegetation Index (EVI) profiles. In the third step, two classical supervised learning algorithms: Decision Tree (DT), K Near Neighborhood (KNN) and four advanced ones: Support Vector Machines (SVM), Bagging, Random Forest (RF) and Extremely Randomized Trees (Extra Trees) are used in ascending experimental protocol of 3 levels of crossed validation to (1) adjust classifiers' parameters, (2) select the best three classifiers to combine and (3) find the best linear combination from five ones tested. All these three optimization operations are done according to the best error rate computed based on f-measure of omission and commission errors. In the last, the final pixels' prediction is deducted thanks to average decision given by (SVM, RF and Extra Trees) which outperforms the best individual classifier score and all other tested combiners. We show the efficiency of the proposed scheme with experiments carried out with 11 LANDSAT free cloud images depicting Gharb region, one of the largest agriculture plain in Morocco.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115506158","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 : 2017-05-01DOI: 10.1109/ATSIP.2017.8075516
K. Amiri, Mohamed Farah, I. Farah
Annotation of images is largely studied in the literature and used in many application fields such as in image interpretation, indexation and retrieval. Manually annotating images gives valuable information on the semantic content of images, but is no longer acceptable when dealing with real corpora of images, especially in the era of big data. Content-based approaches had known great success to deal with large datasets, using low-level features such as color, texture, and shape, which are easy to compute automatically. Nonetheless, they suffer from the well known semantic gap problem, since they produce semantically very limited representations of images. In this paper, we propose a semantic image annotation approach that simultaneously handles contextual, spatial and spectral information of the image. We consider a predefined remotely sensed ontology and develop an annotation process that produces semantically rich hypergraphs representing objects in scenes, as well as their spatial and spectral attributes. We apply our approach to build a hypergraph corresponding to the Jasper Ridge AVIRIS image, showing the promising use of such representation in remote sensing.
{"title":"Fuzzy hypergraph of concepts for semantic annotation of remotely sensed images","authors":"K. Amiri, Mohamed Farah, I. Farah","doi":"10.1109/ATSIP.2017.8075516","DOIUrl":"https://doi.org/10.1109/ATSIP.2017.8075516","url":null,"abstract":"Annotation of images is largely studied in the literature and used in many application fields such as in image interpretation, indexation and retrieval. Manually annotating images gives valuable information on the semantic content of images, but is no longer acceptable when dealing with real corpora of images, especially in the era of big data. Content-based approaches had known great success to deal with large datasets, using low-level features such as color, texture, and shape, which are easy to compute automatically. Nonetheless, they suffer from the well known semantic gap problem, since they produce semantically very limited representations of images. In this paper, we propose a semantic image annotation approach that simultaneously handles contextual, spatial and spectral information of the image. We consider a predefined remotely sensed ontology and develop an annotation process that produces semantically rich hypergraphs representing objects in scenes, as well as their spatial and spectral attributes. We apply our approach to build a hypergraph corresponding to the Jasper Ridge AVIRIS image, showing the promising use of such representation in remote sensing.","PeriodicalId":259951,"journal":{"name":"2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124880099","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：