|
|
Lluis Gomez, Y. Patel, Marçal Rusiñol, C.V. Jawahar and Dimosthenis Karatzas. 2017. Self‐supervised learning of visual features through embedding images into text topic spaces. 30th IEEE Conference on Computer Vision and Pattern Recognition.
Abstract: End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches.
|
|
|
|
Marçal Rusiñol and Josep Llados. 2017. Flowchart Recognition in Patent Information Retrieval. In M. Lupu, K. Mayer, N. Kando and A.J. Trippe, eds. Current Challenges in Patent Information Retrieval. Springer Berlin Heidelberg, 351–368.
|
|
|
|
Hana Jarraya, Muhammad Muzzamil Luqman and Jean-Yves Ramel. 2017. Improving Fuzzy Multilevel Graph Embedding Technique by Employing Topological Node Features: An Application to Graphics Recognition. In B. Lamiroy and R Dueire Lins, eds. Graphics Recognition. Current Trends and Challenges. Springer. (LNCS.)
|
|
|
|
Hana Jarraya, Oriol Ramos Terrades and Josep Llados. 2017. Graph Embedding through Probabilistic Graphical Model applied to Symbolic Graphs. 8th Iberian Conference on Pattern Recognition and Image Analysis.
Abstract: We propose a new Graph Embedding (GEM) method that takes advantages of structural pattern representation. It models an Attributed Graph (AG) as a Probabilistic Graphical Model (PGM). Then, it learns the parameters of this PGM presented by a vector. This vector is a signature of AG in a lower dimensional vectorial space. We apply Structured Support Vector Machines (SSVM) to process classification task. As first tentative, results on the GREC dataset are encouraging enough to go further on this direction.
Keywords: Attributed Graph; Probabilistic Graphical Model; Graph Embedding; Structured Support Vector Machines
|
|
|
|
Lasse Martensson, Anders Hast and Alicia Fornes. 2017. Word Spotting as a Tool for Scribal Attribution. 2nd Conference of the association of Digital Humanities in the Nordic Countries.87–89.
|
|
|
|
Pau Riba, Alicia Fornes and Josep Llados. 2017. Towards the Alignment of Handwritten Music Scores. In Bart Lamiroy and R Dueire Lins, eds. International Workshop on Graphics Recognition. GREC 2015.Graphic Recognition. Current Trends and Challenges.103–116. (LNCS.)
Abstract: It is very common to nd di erent versions of the same music work in archives of Opera Theaters. These di erences correspond to modi cations and annotations from the musicians. From the musicologist point of view, these variations are very interesting and deserve study.
This paper explores the alignment of music scores as a tool for automatically detecting the passages that contain such di erences. Given the diculties in the recognition of handwritten music scores, our goal is to align the music scores and at the same time, avoid the recognition of music elements as much as possible. After removing the sta lines, braces and ties, the bar lines are detected. Then, the bar units are described as a whole using the Blurred Shape Model. The bar units alignment is performed by using Dynamic Time Warping. The analysis of the alignment path is used to detect the variations in the music scores. The method has been evaluated on a subset of the CVC-MUSCIMA dataset, showing encouraging results.
Keywords: Optical Music Recognition; Handwritten Music Scores; Dynamic Time Warping alignment
|
|
|
|
Hana Jarraya, Oriol Ramos Terrades and Josep Llados. 2017. Learning structural loss parameters on graph embedding applied on symbolic graphs. 12th IAPR International Workshop on Graphics Recognition.
Abstract: We propose an amelioration of proposed Graph Embedding (GEM) method in previous work that takes advantages of structural pattern representation and the structured distortion. it models an Attributed Graph (AG) as a Probabilistic Graphical Model (PGM). Then, it learns the parameters of this PGM presented by a vector, as new signature of AG in a lower dimensional vectorial space. We focus to adapt the structured learning algorithm via 1_slack formulation with a suitable risk function, called Graph Edit Distance (GED). It defines the dissimilarity of the ground truth and predicted graph labels. It determines by the error tolerant graph matching using bipartite graph matching algorithm. We apply Structured Support Vector Machines (SSVM) to process classification task. During our experiments, we got our results on the GREC dataset.
|
|
|
|
J. Chazalon and 9 others. 2017. SmartDoc 2017 Video Capture: Mobile Document Acquisition in Video Mode. 1st International Workshop on Open Services and Tools for Document Analysis.
Abstract: As mobile document acquisition using smartphones is getting more and more common, along with the continuous improvement of mobile devices (both in terms of computing power and image quality), we can wonder to which extent mobile phones can replace desktop scanners. Modern applications can cope with perspective distortion and normalize the contrast of a document page captured with a smartphone, and in some cases like bottle labels or posters, smartphones even have the advantage of allowing the acquisition of non-flat or large documents. However, several cases remain hard to handle, such as reflective documents (identity cards, badges, glossy magazine cover, etc.) or large documents for which some regions require an important amount of detail. This paper introduces the SmartDoc 2017 benchmark (named “SmartDoc Video Capture”), which aims at
assessing whether capturing documents using the video mode of a smartphone could solve those issues. The task under evaluation is both a stitching and a reconstruction problem, as the user can move the device over different parts of the document to capture details or try to erase highlights. The material released consists of a dataset, an evaluation method and the associated tool, a sample method, and the tools required to extend the dataset. All the components are released publicly under very permissive licenses, and we particularly cared about maximizing the ease of
understanding, usage and improvement.
|
|
|
|
Lluis Gomez, Marçal Rusiñol and Dimosthenis Karatzas. 2017. LSDE: Levenshtein Space Deep Embedding for Query-by-string Word Spotting. 14th International Conference on Document Analysis and Recognition.
Abstract: n this paper we present the LSDE string representation and its application to handwritten word spotting. LSDE is a novel embedding approach for representing strings that learns a space in which distances between projected points are correlated with the Levenshtein edit distance between the original strings.
We show how such a representation produces a more semantically interpretable retrieval from the user’s perspective than other state of the art ones such as PHOC and DCToW. We also conduct a preliminary handwritten word spotting experiment on the George Washington dataset.
|
|
|
|
E. Royer, J. Chazalon, Marçal Rusiñol and F. Bouchara. 2017. Benchmarking Keypoint Filtering Approaches for Document Image Matching. 14th International Conference on Document Analysis and Recognition.
Abstract: Best Poster Award.
Reducing the amount of keypoints used to index an image is particularly interesting to control processing time and memory usage in real-time document image matching applications, like augmented documents or smartphone applications. This paper benchmarks two keypoint selection methods on a task consisting of reducing keypoint sets extracted from document images, while preserving detection and segmentation accuracy. We first study the different forms of keypoint filtering, and we introduce the use of the CORE selection method on
keypoints extracted from document images. Then, we extend a previously published benchmark by including evaluations of the new method, by adding the SURF-BRISK detection/description scheme, and by reporting processing speeds. Evaluations are conducted on the publicly available dataset of ICDAR2015 SmartDOC challenge 1. Finally, we prove that reducing the original keypoint set is always feasible and can be beneficial
not only to processing speed but also to accuracy.
|
|
