{"title":"Zero-aliasing correlation filters","authors":"Joseph A. Fernandez, B. Kumar","doi":"10.1109/ISPA.2013.6703722","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703722","url":null,"abstract":"Traditional correlation filters are designed and implemented via the frequency domain, where the correlation of two signals may be computed efficiently. However, when the discrete Fourier transform (DFT) of length N is used, multiplication in the frequency domain results in an N-point circular correlation, rather than a linear correlation. The resulting correlation filter output is therefore corrupted by the aliasing effects of circular correlation. One solution is to design and implement the correlation filter directly in the space domain. However, this is more computationally intense. Recent literature has discussed ways in which to minimize circular correlation effects, but the effects are not completely removed. We propose a new frequency domain method for completely eliminating circular correlation effects when designing correlation filters. We demonstrate this idea with the well-known minimum average correlation energy (MACE) filter and show how the reformulated MACE filter in the frequency domain outperforms the original formulation of the MACE filter.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124424899","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}
{"title":"Motion estimation by X-ray tomography: A variational formulation for 3D-volume DIC and a finite element implementation","authors":"R. Fedele, L. Galantucci, A. Ciani","doi":"10.1109/ISPA.2013.6703812","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703812","url":null,"abstract":"In this study a robust strategy for 3D-Volume Digital Image Correlation (DIC) is presented, apt to provide accurate kinematic measurements within a loaded sample on the basis of three-dimensional digital images by X-ray computed micro-tomography. As an alternative to conventional Rayleigh-Ritz approach, a novel variational formulation is presented for the continuum DIC estimation. In the framework of a Galerkin finite element discretization of the displacement field, the inverse problem of estimating 3D motion inside the bulk material is solved recursively on a hierarchical family of grids, linked by suitable restriction and prolongation operators. Such structured grids are defined over an image pyramid, which is generated starting from the raw tomographic reconstructions by a reiterated application of average filters and sub-sampling operators. To achieve robust estimates of the underlying displacement fields, multi-grid cycles are performed ascending and descending along the pyramid in a selected sequence, with only one Newton iteration per level irrespectively of the tolerance satisfaction, as if the problem were linear. A Tychonoff regularization provision is implemented, which preserves the estimates against spurious oscillations. Results are presented concerning a laboratory X-ray micro-tomography experiment on a polymeric foam sample, subjected to uniaxial loading by an apparatus ad-hoc realized.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130770014","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}
{"title":"Low-complexity iris recognition method using 2D Gauss-Hermite moments","authors":"S. Rahman, M. Reza, Q. M. Z. Hasani","doi":"10.1109/ISPA.2013.6703729","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703729","url":null,"abstract":"The authenticity and reliability of iris recognition-based biometric identification system is well-proven. Traditional iris recognition methods use expensive feature extraction algorithms and complex-valued IrisCodes that may hinder the development of a fast identification technique for multimodal biometric system. In this paper, a new set of computationally efficient real-valued features is proposed for recognition of iris patterns using the two dimensional higher-order Gauss-Hermite moments. The IrisCodes generated from the zero-crossings of these moment-based features are capable of capturing hidden nonlinear structures and are potentially invariant to distortions of iris patterns. Experimental results conducted on a generic data set consisting of iris images obtained from two well-known databases show that the proposed method provides encouraging performance. In particular, an acceptable recognition performance in terms of probability of detection for a given false alarm rate may be achieved by the proposed method with a significantly low-level of computational complexity.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134113863","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}
M. Ajčević, A. D. Lorenzo, P. Accardo, Alberto Bartoli, Eric Medvet
{"title":"A novel estimation methodology for tracheal pressure in mechanical ventilation control","authors":"M. Ajčević, A. D. Lorenzo, P. Accardo, Alberto Bartoli, Eric Medvet","doi":"10.1109/ISPA.2013.6703827","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703827","url":null,"abstract":"High-frequency percussive ventilation (HFPV) is a non-conventional mechanical ventilatory strategy which has proven useful in the treatment of a number of pathological conditions. HFPV usually involves the usage of endotracheal tubes (EET) connecting the ventilator circuit to the airway of the patient. The pressure of the air flow insufflated by HFPV must be controlled very accurately in order to avoid barotrauma and volutrauma. Since the actual tracheal pressure cannot be measured, a model for estimating such a pressure based on the EET properties and on the air flow properties that can actually be measured in clinical practice is necessary. In this work we propose a novel methodology, based on Genetic Programming, for synthesizing such a model. We experimentally evaluated our models against the state-of-the-art baseline models, crafted by human experts, and found that our models for estimating tracheal pressure are significantly more accurate.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134312035","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}
{"title":"Comparative analysis of various thresholding techniques on TerraSAR-X images in the presence of speckle noise","authors":"Eyram Schwinger, A. Munthe-Kaas","doi":"10.1109/ISPA.2013.6703711","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703711","url":null,"abstract":"This paper compares several methods of thresholding applied to TerraSAR-X radar images in the presence of speckle noise and a method based on the use of the local extremas of the histogram. The methods used are Otsu's, Valley-emphasis, maximum entropy, fuzzy sets, Yagar's measure of fuzziness and histogram clustering. The local minimum of the histogram provides a good threshold candidate for global thresholding in ship detection in the case of moderate signal noise but fails for high signal noise and variable illumination. The methods are tested on sample images to evaluate their performance in object detection in real TerraSAR-X datasets.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129044090","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}
{"title":"Sparse coding and Gaussian modeling of coefficients average for background subtraction","authors":"Ciprian David, V. Gui","doi":"10.1109/ISPA.2013.6703744","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703744","url":null,"abstract":"A sparse coding based approach for background subtraction is proposed in this paper. The background model is composed from a K-SVD dictionary and a set of mean coefficients associated to each image location. Due to the use of sparse coding, our approach has a regional character. The recovered value of a pixel is obtained by reconstructing the surrounding image patch. In order to avoid problems introduced by difficult situations like dynamic backgrounds, an additional Gaussian model on the average of the coefficients set is used. A foreground confidence image results from this modeling. Two threshold will output the final background-foreground binary map. A first threshold on the confidence image selects possible foreground candidates. For these candidates we consider the reconstruction error, represented by the absolute difference between the reconstructed frame and the estimated background. A second threshold on these candidates offers the final discrimination. Our approach is tested against state-of-the-art methods. It is proved to perform better both in terms of visual comparison and quantitative measures.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114841796","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}
A. Pelagotti, F. Uccheddu, F. Nex, Fabio Remondino, Livia Chisari
{"title":"Automatic graves' orientation detection: A tool for spatial archeology","authors":"A. Pelagotti, F. Uccheddu, F. Nex, Fabio Remondino, Livia Chisari","doi":"10.1109/ISPA.2013.6703807","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703807","url":null,"abstract":"The assessment of the preferred orientation of graves in a necropolis represents an interesting contribution to the study of a civilization. In this paper two different methods are presented. The first one implies a parameterization of the map, i.e. its manual translation into a shapefile, where each grave of the necropolis is separately analyzed and a subsequent automatic orientation of the whole necropolis is achieved. This method proved to be highly reliable in the determining the tomb orientation and entrance direction, although it was quite time consuming, since a fairly important amount of manual work was required. On the other hand, the alternative proposed method using the Radon transform proved to be able to assess the main direction of the whole necropolis analyzing the scanned map image, in a fast and reliable way, without the need of any manual intervention. However in the simplest implementation and for the entire image at once, with the Radon transform it is not possible to determine the versus of the located lines. This is instead achievable when analyzing the single graves. In both cases, the main orientation was correctly detected.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122567017","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}
{"title":"Ancient degraded document image binarization based on texture features","authors":"A. Sehad, Y. Chibani, M. Cheriet, Yacine Yaddaden","doi":"10.1109/ISPA.2013.6703737","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703737","url":null,"abstract":"In this paper, we present a promising method for binarization of historical and degraded document images, based on texture features. The proposed method is an adaptive threshold-based. This latter is computed by using a descriptor based on a co-occurrence matrix. The proposed method is tested objectively, using DIBCO dataset degraded documents and subjectively, using a set of ancient degraded documents provided by a national library. The results are satisfactory and promising, and present an improvement to classical methods.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116584741","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}
{"title":"Likelihood based combining of subband estimates for wideband DOA","authors":"Petri Helin, B. Dumitrescu, J. Astola, I. Tabus","doi":"10.1109/ISPA.2013.6703760","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703760","url":null,"abstract":"We propose a method for the estimation of direction of arrival (DOA) of wideband sources using a sensor array, especially directed for improving the DOA estimation accuracy in the case of close sources. Starting from the spatial spectrum estimated by MVDR separately in each subband, we select a number of peaks in each subband and build the likelihood of a direction based on the probability distribution of the closest peak. We are resorting to existing bias and variance formulas for MVDR estimates in the narrowband case, accounting for the bias due to multiple sources. The log-likelihood functions are combined additively over the subbands, as opposed to the traditional additive combination of MVDR spatial spectra in each subband. The maxima of the combined log-likelihood function are shown experimentally to be more accurate than the maxima of the combined MVDR spectra.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116456546","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}
Tetyana Ivanovska, Lei Wang, R. Laqua, K. Hegenscheid, H. Völzke, V. Liebscher
{"title":"A fast global variational bias field correction method for MR images","authors":"Tetyana Ivanovska, Lei Wang, R. Laqua, K. Hegenscheid, H. Völzke, V. Liebscher","doi":"10.1109/ISPA.2013.6703822","DOIUrl":"https://doi.org/10.1109/ISPA.2013.6703822","url":null,"abstract":"Magnetic resonance (MR) images are prone to inhomogeneity artefacts that hinder an efficient automatic segmentation. Existing correction methods are often dependent on initialization and computationally expensive. This paper proposes a novel variational approach for the simultaneous bias field correction and image segmentation together with its efficient implementation, which produces the global solution that does not depend on initializations. The method is compared against another recently proposed method in terms of speed, efficiency, and performance.","PeriodicalId":425029,"journal":{"name":"2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133361989","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}