2011
Journal article
Restricted
A deterministic algorithm for optical flow estimation
Gerace I., Martinelli F., Pucci P.
In this paper we propose a new deterministic algorithm for determining optical flow through regularization techniques so that the solution of the problem is defined as the minimum of an appropriate energy function. We also assume that the displacements are piecewise continuous and that the discontinuities are variable to be estimated. More precisely, we introduce a hierarchical three-step optimization strategy to minimize the constructed energy function, which is not convex. In the first step we find a suitable initial guess of the displacements field by a gradient-based GNC algorithm. In the second step we define the local energy of a displacement field as the energy function obtained by fixing all the field with the exception of a row or of a column. Then, through an application of the shortest path technique we minimize iteratively each local energy function restricted to a row or to a column until we arrive at a fixed point. In the last step we use again a GNC algorithm to recover a sub-pixel accuracy. The experimental results confirm the goodness of this technique.Source: Communications in Applied and Industrial Mathematics 1 (2011): 249–268. doi:10.1685/2010CAIM584
DOI: 10.1685/2010caim584
Metrics:
Gerace I., Martinelli F., Pucci P.
In this paper we propose a new deterministic algorithm for determining optical flow through regularization techniques so that the solution of the problem is defined as the minimum of an appropriate energy function. We also assume that the displacements are piecewise continuous and that the discontinuities are variable to be estimated. More precisely, we introduce a hierarchical three-step optimization strategy to minimize the constructed energy function, which is not convex. In the first step we find a suitable initial guess of the displacements field by a gradient-based GNC algorithm. In the second step we define the local energy of a displacement field as the energy function obtained by fixing all the field with the exception of a row or of a column. Then, through an application of the shortest path technique we minimize iteratively each local energy function restricted to a row or to a column until we arrive at a fixed point. In the last step we use again a GNC algorithm to recover a sub-pixel accuracy. The experimental results confirm the goodness of this technique.Source: Communications in Applied and Industrial Mathematics 1 (2011): 249–268. doi:10.1685/2010CAIM584
DOI: 10.1685/2010caim584
Metrics:
See at:
caim.simai.eu 
| CNR ExploRA
2011
Other
Open Access
Nonlinear model identification and seethrough cancellation from recto-verso data
Salerno Emanuele, Martinelli Francesca, Tonazzini Anna
The problem of seethrough cancellation in digital images of double-sided documents is addressed. Previous approaches to solve this problem from recto-verso pairs of grayscale data images show a number of drawbacks, ranging from errors due to an inadequate data model to excessive computational complexities. While satisfying the need to assume a nonlinear convolutional mixture model and to estimate its parameters along with the recto and verso patterns, we propose a simple and fast strategy to estimate the trasparency of the paper and the seethrough convolutional kernel, thus enabling an efficient correction of this distortion. Compared to other separation strategies, our choice is slightly more cumbersome since average background values must be estimated and a pure showthrough area must be isolated manually by the operator. Although the procedure cannot be fully automatic, however, it outperforms other restoration strategies, especially if based on linear instantaneous models.
Salerno Emanuele, Martinelli Francesca, Tonazzini Anna
The problem of seethrough cancellation in digital images of double-sided documents is addressed. Previous approaches to solve this problem from recto-verso pairs of grayscale data images show a number of drawbacks, ranging from errors due to an inadequate data model to excessive computational complexities. While satisfying the need to assume a nonlinear convolutional mixture model and to estimate its parameters along with the recto and verso patterns, we propose a simple and fast strategy to estimate the trasparency of the paper and the seethrough convolutional kernel, thus enabling an efficient correction of this distortion. Compared to other separation strategies, our choice is slightly more cumbersome since average background values must be estimated and a pure showthrough area must be isolated manually by the operator. Although the procedure cannot be fully automatic, however, it outperforms other restoration strategies, especially if based on linear instantaneous models.
See at:
CNR IRIS 
| ISTI Repository | CNR IRIS
2011
Other
Metadata Only Access
See-through correction in recto-verso documents via a regularized nonlinear model
Gerace Ivan, Martinelli Francesca, Tonazzini Anna
In this paper, we approach the removal of back-to-front interferences from scans of double-sided documents as a blind source separation problem. We consider the front and back ideal images as two individual patterns, overlapped in the observed recto and verso scans through a nonlinear convolutional mixing model. We adopt a regularization approach to estimate both the ideal images and the model parameters, by minimizing a suitable energy function of all the unknowns. The regularity of the solution images is described by typical local autocorrelation constraints, accounting also for well-behaved edges. This a priori information is particularly suitable for the kind of objects depicted in the images treated, i.e. homogeneous texts in homogeneous background, and, as such, is capable to stabilize the ill-posed, inverse problem considered. We show that the results obtained by this approach are much better than the ones obtained through data decorrelation or independent component analysis. As compared to approaches based on segmentation/classification, which often aim at cleaning a foreground text by removing all the textured background, one of the advantages of our method is that cleaning does not alter genuine features of the document, such as color or other structures it may contain. This is particularly interesting when the document has a historical importance, since its readability can be improved while maintaining the original appearance.
Gerace Ivan, Martinelli Francesca, Tonazzini Anna
In this paper, we approach the removal of back-to-front interferences from scans of double-sided documents as a blind source separation problem. We consider the front and back ideal images as two individual patterns, overlapped in the observed recto and verso scans through a nonlinear convolutional mixing model. We adopt a regularization approach to estimate both the ideal images and the model parameters, by minimizing a suitable energy function of all the unknowns. The regularity of the solution images is described by typical local autocorrelation constraints, accounting also for well-behaved edges. This a priori information is particularly suitable for the kind of objects depicted in the images treated, i.e. homogeneous texts in homogeneous background, and, as such, is capable to stabilize the ill-posed, inverse problem considered. We show that the results obtained by this approach are much better than the ones obtained through data decorrelation or independent component analysis. As compared to approaches based on segmentation/classification, which often aim at cleaning a foreground text by removing all the textured background, one of the advantages of our method is that cleaning does not alter genuine features of the document, such as color or other structures it may contain. This is particularly interesting when the document has a historical importance, since its readability can be improved while maintaining the original appearance.
See at:
CNR IRIS