The MIT lincoln laboratory / JHU / EPITA-LSE LRE17 system
In Odyssey 2018, the speaker and language recognition workshop
A morphological method for music score staff removal
In Proceedings of the 21st international conference on image processing (ICIP)
Abstract
Removing the staff in music score images is a key to improve the recognition of music symbols and, with ancient and degraded handwritten music scores, it is not a straightforward task. In this paper we present the method that has won in 2013 the staff removal competition, organized at the International Conference on Document Analysis and Recognition (ICDAR). The main characteristics of this method is that it essentially relies on mathematical morphology filtering. So it is simple, fast, and its full source code is provided to favor reproducible research.
On making $n$D images well-composed by a self-dual local interpolation
In Proceedings of the 18th international conference on discrete geometry for computer imagery (DGCI)
Abstract
Natural and synthetic discrete images are generally not well-composed, leading to many topological issues: connectivities in binary images are not equivalent, the Jordan Separation theorem is not true anymore, and so on. Conversely, making images well-composed solves those problems and then gives access to many powerful tools already known in mathematical morphology as the Tree of Shapes which is of our principal interest. In this paper, we present two main results: a characterization of 3D well-composed gray-valued images; and a counter-example showing that no local self-dual interpolation with a classical set of properties makes well-composed images with one subdivision in 3D, as soon as we choose the mean operator to interpolate in 1D. Then, we briefly discuss various constraints that could be interesting to change to make the problem solvable in nD.
A first parallel algorithm to compute the morphological tree of shapes of $n$D images
In Proceedings of the 21st international conference on image processing (ICIP)
Abstract
The tree of shapes is a self-dual tree-based image representation belonging to the field of mathematical morphology. This representation is highly interesting since it is invariant to contrast changes and inversion, and allows for numerous and powerful applications. A new algorithm to compute the tree of shapes has been recently presented: it has a quasi-linear complexity; it is the only known algorithm that is also effective for nD images with n > 2; yet it is sequential. With the increasing size of data to process, the need of a parallel algorithm to compute that tree is of prime importance; in this paper, we present such an algorithm. We also give some benchmarks that show that the parallel version is computationally effective. As a consequence, that makes possible to process 3D images with some powerful self-dual morphological tools.
A precise skew estimation algorithm for document images using KNN clustering and fourier transform
In Proceedings of the 21st international conference on image processing (ICIP)
Abstract
In this article, we propose a simple and precise skew estimation algorithm for binarized document images. The estimation is performed in the frequency domain. To get a precise result, the Fourier transform is not applied to the document itself but the document is preprocessed: all regions of the document are clustered using a KNN and contours of grouped regions are smoothed using the convex hull to form more regular shapes, with better orientation. No assumption has been made concerning the nature or the content of the document. This method has been shown to be very accurate and was ranked first at the DISEC’13 contest, during the ICDAR competitions.
Getting a morphological tree of shapes for multivariate images: Paths, traps and pitfalls
In Proceedings of the 21st international conference on image processing (ICIP)
Abstract
The Tree of Shapes is a morphological tree that provides an high-level hierarchical representation of the image suitable for many image processing tasks. This structure has the desirable properties to be self-dual and contrast-invariant and describes the organization of the objects through level lines inclusion. Yet it is defined on gray-level while many images have multivariate data (color images, multispectral images…) where information are split across channels. In this paper, we propose some leads to extend the tree of shapes on colors with classical approaches based on total orders, more recent approaches based on graphs and also a new distance-based method. Eventually, we compare these approaches through denoising to highlight their strengths and weaknesses and show the strong potential of the new methods compared to classical ones.
Meaningful disjoint level lines selection
In Proceedings of the 21st international conference on image processing (ICIP)
Abstract
Many methods based on the morphological notion of shapes (i.e., connected components of level sets) have been proved to be very efficient in shape recognition and shape analysis. The inclusion relationship of the level lines (boundaries of level sets) forms the tree of shapes, a tree-based image representation with a high potential. Numerous applications using this tree representation have been proposed. In this article, we propose an efficient algorithm that extracts a set of disjoint level lines in the image. These selected level lines yields a simplified image with clean contours, which also provides an intuitive idea about the main structure of the tree of shapes. Besides, we obtain a saliency map without transition problems around the contours by weighting level lines with their significance. Experimental results demonstrate the efficiency and usefulness of our method.
A type system for weighted automata and rational expressions
In Proceedings of implementation and application of automata, 19th international conference (CIAA’14)
Abstract
We present a type system for automata and rational expressions, expressive enough to encompass weighted automata and transducers in a single coherent formalism. The system allows to express useful properties about the applicability of operations including binary heterogeneous functions over automata. We apply the type system to the design of the platform, a library dedicated to the computation with finite weighted automata, in which genericity and high efficiency are obtained at the lowest level through the use of template metaprogramming, by letting the template system play the role of a static type system for automata. Between such a low-level layer and the interactive high-level interface, the type system plays the crucial role of a mediator and allows for a cleanly-structured use of dynamic compilation.
A morphological tree of shapes for color images
In Proceedings of the 22nd international conference on pattern recognition (ICPR)
Abstract
Symbolic model checking of stutter invariant properties using generalized testing automata
In Proceedings of the 20th international conference on tools and algorithms for the construction and analysis of systems (TACAS’14)
Abstract
In a previous work, we showed that a kind of $\omega$-automata known as Transition-based Generalized Testing Automata (TGTA) can outperform the Büchi automata traditionally used for explicit model checking when verifying stutter-invariant properties. In this work, we investigate the use of these generalized testing automata to improve symbolic model checking of stutter-invariant LTL properties. We propose an efficient symbolic encoding of stuttering transitions in the product between a model and a TGTA. Saturation techniques available for decision diagrams then benefit from the presence of stuttering self-loops on all states of TGTA. Experimentation of this approach confirms that it outperforms the symbolic approach based on (transition-based) Generalized Büchi Automata.