Dimosthenis Karatzas, Lluis Gomez, & Marçal Rusiñol. (2017). The Robust Reading Competition Annotation and Evaluation Platform. In 1st International Workshop on Open Services and Tools for Document Analysis.
Abstract: The ICDAR Robust Reading Competition (RRC), initiated in 2003 and re-established in 2011, has become the defacto evaluation standard for the international community. Concurrent with its second incarnation in 2011, a continuous effort started to develop an online framework to facilitate the hosting and management of competitions. This short paper briefly outlines the Robust Reading Competition Annotation and Evaluation Platform, the backbone of the Robust Reading Competition, comprising a collection of tools and processes that aim to simplify the management and annotation
of data, and to provide online and offline performance evaluation and analysis services
|
Lluis Gomez, Marçal Rusiñol, & Dimosthenis Karatzas. (2018). Cutting Sayre's Knot: Reading Scene Text without Segmentation. Application to Utility Meters. In 13th IAPR International Workshop on Document Analysis Systems (pp. 97–102).
Abstract: In this paper we present a segmentation-free system for reading text in natural scenes. A CNN architecture is trained in an end-to-end manner, and is able to directly output readings without any explicit text localization step. In order to validate our proposal, we focus on the specific case of reading utility meters. We present our results in a large dataset of images acquired by different users and devices, so text appears in any location, with different sizes, fonts and lengths, and the images present several distortions such as
dirt, illumination highlights or blur.
Keywords: Robust Reading; End-to-end Systems; CNN; Utility Meters
|
Dena Bazazian, Raul Gomez, Anguelos Nicolaou, Lluis Gomez, Dimosthenis Karatzas, & Andrew Bagdanov. (2019). Fast: Facilitated and accurate scene text proposals through fcn guided pruning. PRL - Pattern Recognition Letters, 119, 112–120.
Abstract: Class-specific text proposal algorithms can efficiently reduce the search space for possible text object locations in an image. In this paper we combine the Text Proposals algorithm with Fully Convolutional Networks to efficiently reduce the number of proposals while maintaining the same recall level and thus gaining a significant speed up. Our experiments demonstrate that such text proposal approaches yield significantly higher recall rates than state-of-the-art text localization techniques, while also producing better-quality localizations. Our results on the ICDAR 2015 Robust Reading Competition (Challenge 4) and the COCO-text datasets show that, when combined with strong word classifiers, this recall margin leads to state-of-the-art results in end-to-end scene text recognition.
|
Lluis Gomez, Y. Patel, Marçal Rusiñol, C.V. Jawahar, & Dimosthenis Karatzas. (2017). Self‐supervised learning of visual features through embedding images into text topic spaces. In 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.
|
J. Chazalon, P. Gomez-Kramer, Jean-Christophe Burie, M.Coustaty, S.Eskenazi, Muhammad Muzzamil Luqman, et al. (2017). SmartDoc 2017 Video Capture: Mobile Document Acquisition in Video Mode. In 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, & Dimosthenis Karatzas. (2017). LSDE: Levenshtein Space Deep Embedding for Query-by-string Word Spotting. In 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, & F. Bouchara. (2017). Benchmarking Keypoint Filtering Approaches for Document Image Matching. In 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.
|
David Aldavert, Marçal Rusiñol, & Ricardo Toledo. (2017). Automatic Static/Variable Content Separation in Administrative Document Images. In 14th International Conference on Document Analysis and Recognition.
Abstract: In this paper we present an automatic method for separating static and variable content from administrative document images. An alignment approach is able to unsupervisedly build probabilistic templates from a set of examples of the same document kind. Such templates define which is the likelihood of every pixel of being either static or variable content. In the extraction step, the same alignment technique is used to match
an incoming image with the template and to locate the positions where variable fields appear. We validate our approach on the public NIST Structured Tax Forms Dataset.
|
Leonardo Galteri, Dena Bazazian, Lorenzo Seidenari, Marco Bertini, Andrew Bagdanov, Anguelos Nicolaou, et al. (2017). Reading Text in the Wild from Compressed Images. In 1st International workshop on Egocentric Perception, Interaction and Computing.
Abstract: Reading text in the wild is gaining attention in the computer vision community. Images captured in the wild are almost always compressed to varying degrees, depending on application context, and this compression introduces artifacts
that distort image content into the captured images. In this paper we investigate the impact these compression artifacts have on text localization and recognition in the wild. We also propose a deep Convolutional Neural Network (CNN) that can eliminate text-specific compression artifacts and which leads to an improvement in text recognition. Experimental results on the ICDAR-Challenge4 dataset demonstrate that compression artifacts have a significant
impact on text localization and recognition and that our approach yields an improvement in both – especially at high compression rates.
|
Masakazu Iwamura, Naoyuki Morimoto, Keishi Tainaka, Dena Bazazian, Lluis Gomez, & Dimosthenis Karatzas. (2017). ICDAR2017 Robust Reading Challenge on Omnidirectional Video. In 14th International Conference on Document Analysis and Recognition.
Abstract: Results of ICDAR 2017 Robust Reading Challenge on Omnidirectional Video are presented. This competition uses Downtown Osaka Scene Text (DOST) Dataset that was captured in Osaka, Japan with an omnidirectional camera. Hence, it consists of sequential images (videos) of different view angles. Regarding the sequential images as videos (video mode), two tasks of localisation and end-to-end recognition are prepared. Regarding them as a set of still images (still image mode), three tasks of localisation, cropped word recognition and end-to-end recognition are prepared. As the dataset has been captured in Japan, the dataset contains Japanese text but also include text consisting of alphanumeric characters (Latin text). Hence, a submitted result for each task is evaluated in three ways: using Japanese only ground truth (GT), using Latin only GT and using combined GTs of both. Finally, by the submission deadline, we have received two submissions in the text localisation task of the still image mode. We intend to continue the competition in the open mode. Expecting further submissions, in this report we provide baseline results in all the tasks in addition to the submissions from the community.
|
Dimosthenis Karatzas, Lluis Gomez, Marçal Rusiñol, & Anguelos Nicolaou. (2018). The Robust Reading Competition Annotation and Evaluation Platform. In 13th IAPR International Workshop on Document Analysis Systems (pp. 61–66).
Abstract: The ICDAR Robust Reading Competition (RRC), initiated in 2003 and reestablished in 2011, has become the defacto evaluation standard for the international community. Concurrent with its second incarnation in 2011, a continuous
effort started to develop an online framework to facilitate the hosting and management of competitions. This short paper briefly outlines the Robust Reading Competition Annotation and Evaluation Platform, the backbone of the
Robust Reading Competition, comprising a collection of tools and processes that aim to simplify the management and annotation of data, and to provide online and offline performance evaluation and analysis services.
|
Lluis Gomez, Ali Furkan Biten, Ruben Tito, Andres Mafla, Marçal Rusiñol, Ernest Valveny, et al. (2021). Multimodal grid features and cell pointers for scene text visual question answering. PRL - Pattern Recognition Letters, 150, 242–249.
Abstract: This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this is that it makes difficult for the model to reason jointly about both modalities. To fix this problem we propose a new model that is based on an single attention mechanism that attends to multi-modal features conditioned to the question. The output weights of this attention module over a grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text to the given question. Our experiments demonstrate competitive performance in two standard datasets with a model that is faster than previous methods at inference time. Furthermore, we also provide a novel analysis of the ST-VQA dataset based on a human performance study. Supplementary material, code, and data is made available through this link.
|
Marçal Rusiñol, J. Chazalon, & Jean-Marc Ogier. (2016). Filtrage de descripteurs locaux pour l'amélioration de la détection de documents. In Colloque International Francophone sur l'Écrit et le Document.
Abstract: In this paper we propose an effective method aimed at reducing the amount of local descriptors to be indexed in a document matching framework.In an off-line training stage, the matching between the model document and incoming images is computed retaining the local descriptors from the model that steadily produce good matches. We have evaluated this approach by using the ICDAR2015 SmartDOC dataset containing near 25000 images from documents to be captured by a mobile device. We have tested the performance of this filtering step by using ORB and SIFT local detectors and descriptors. The results show an important gain both in quality of the final matching as well as in time and space requirements.
Keywords: Local descriptors; mobile capture; document matching; keypoint selection
|
Dimosthenis Karatzas, V. Poulain d'Andecy, & Marçal Rusiñol. (2016). Human-Document Interaction – a new frontier for document image analysis. In 12th IAPR Workshop on Document Analysis Systems (pp. 369–374).
Abstract: All indications show that paper documents will not cede in favour of their digital counterparts, but will instead be used increasingly in conjunction with digital information. An open challenge is how to seamlessly link the physical with the digital – how to continue taking advantage of the important affordances of paper, without missing out on digital functionality. This paper
presents the authors’ experience with developing systems for Human-Document Interaction based on augmented document interfaces and examines new challenges and opportunities arising for the document image analysis field in this area. The system presented combines state of the art camera-based document
image analysis techniques with a range of complementary tech-nologies to offer fluid Human-Document Interaction. Both fixed and nomadic setups are discussed that have gone through user testing in real-life environments, and use cases are presented that span the spectrum from business to educational application
|
Marçal Rusiñol, David Aldavert, Ricardo Toledo, & Josep Llados. (2015). Towards Query-by-Speech Handwritten Keyword Spotting. In 13th International Conference on Document Analysis and Recognition ICDAR2015 (pp. 501–505).
Abstract: In this paper, we present a new querying paradigm for handwritten keyword spotting. We propose to represent handwritten word images both by visual and audio representations, enabling a query-by-speech keyword spotting system. The two representations are merged together and projected to a common sub-space in the training phase. This transform allows to, given a spoken query, retrieve word instances that were only represented by the visual modality. In addition, the same method can be used backwards at no additional cost to produce a handwritten text-tospeech system. We present our first results on this new querying mechanism using synthetic voices over the George Washington
dataset.
|