|
Stepan Simsa and 10 others. 2023. Overview of DocILE 2023: Document Information Localization and Extraction. International Conference of the Cross-Language Evaluation Forum for European Languages.276–293. (LNCS.)
Abstract: This paper provides an overview of the DocILE 2023 Competition, its tasks, participant submissions, the competition results and possible future research directions. This first edition of the competition focused on two Information Extraction tasks, Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR). Both of these tasks require detection of pre-defined categories of information in business documents. The second task additionally requires correctly grouping the information into tuples, capturing the structure laid out in the document. The competition used the recently published DocILE dataset and benchmark that stays open to new submissions. The diversity of the participant solutions indicates the potential of the dataset as the submissions included pure Computer Vision, pure Natural Language Processing, as well as multi-modal solutions and utilized all of the parts of the dataset, including the annotated, synthetic and unlabeled subsets.
Keywords: Information Extraction; Computer Vision; Natural Language Processing; Optical Character Recognition; Document Understanding
|
|
|
Sergi Garcia Bordils and 7 others. 2022. Out-of-Vocabulary Challenge Report. Proceedings European Conference on Computer Vision Workshops.359–375. (LNCS.)
Abstract: This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV contest introduces an important aspect that is not commonly studied by Optical Character Recognition (OCR) models, namely, the recognition of unseen scene text instances at training time. The competition compiles a collection of public scene text datasets comprising of 326,385 images with 4,864,405 scene text instances, thus covering a wide range of data distributions. A new and independent validation and test set is formed with scene text instances that are out of vocabulary at training time. The competition was structured in two tasks, end-to-end and cropped scene text recognition respectively. A thorough analysis of results from baselines and different participants is presented. Interestingly, current state-of-the-art models show a significant performance gap under the newly studied setting. We conclude that the OOV dataset proposed in this challenge will be an essential area to be explored in order to develop scene text models that achieve more robust and generalized predictions.
|
|
|
Oriol Ramos Terrades, Salvatore Tabbone and Ernest Valveny. 2007. Optimal Linear Combination for Two-class Classifiers. Proceedings of the International Conference on Advances in Pattern Recognition.
|
|
|
Oriol Ramos Terrades, Ernest Valveny and Salvatore Tabbone. 2009. Optimal Classifier Fusion in a Non-Bayesian Probabilistic Framework. TPAMI, 31(9), 1630–1644.
Abstract: The combination of the output of classifiers has been one of the strategies used to improve classification rates in general purpose classification systems. Some of the most common approaches can be explained using the Bayes' formula. In this paper, we tackle the problem of the combination of classifiers using a non-Bayesian probabilistic framework. This approach permits us to derive two linear combination rules that minimize misclassification rates under some constraints on the distribution of classifiers. In order to show the validity of this approach we have compared it with other popular combination rules from a theoretical viewpoint using a synthetic data set, and experimentally using two standard databases: the MNIST handwritten digit database and the GREC symbol database. Results on the synthetic data set show the validity of the theoretical approach. Indeed, results on real data show that the proposed methods outperform other common combination schemes.
|
|
|
Arnau Baro, Pau Riba, Jorge Calvo-Zaragoza and Alicia Fornes. 2017. Optical Music Recognition by Recurrent Neural Networks. 14th IAPR International Workshop on Graphics Recognition.25–26.
Abstract: Optical Music Recognition is the task of transcribing a music score into a machine readable format. Many music scores are written in a single staff, and therefore, they could be treated as a sequence. Therefore, this work explores the use of Long Short-Term Memory (LSTM) Recurrent Neural Networks for reading the music score sequentially, where the LSTM helps in keeping the context. For training, we have used a synthetic dataset of more than 40000 images, labeled at primitive level
Keywords: Optical Music Recognition; Recurrent Neural Network; Long Short-Term Memory
|
|
|
Arnau Baro, Pau Riba, Jorge Calvo-Zaragoza and Alicia Fornes. 2018. Optical Music Recognition by Long Short-Term Memory Networks. In A. Fornes, B.L., ed. Graphics Recognition. Current Trends and Evolutions. Springer, 81–95. (LNCS.)
Abstract: Optical Music Recognition refers to the task of transcribing the image of a music score into a machine-readable format. Many music scores are written in a single staff, and therefore, they could be treated as a sequence. Therefore, this work explores the use of Long Short-Term Memory (LSTM) Recurrent Neural Networks for reading the music score sequentially, where the LSTM helps in keeping the context. For training, we have used a synthetic dataset of more than 40000 images, labeled at primitive level. The experimental results are promising, showing the benefits of our approach.
Keywords: Optical Music Recognition; Recurrent Neural Network; Long ShortTerm Memory
|
|
|
Lluis Pere de las Heras, Oriol Ramos Terrades and Josep Llados. 2017. Ontology-Based Understanding of Architectural Drawings. International Workshop on Graphics Recognition. GREC 2015.Graphic Recognition. Current Trends and Challenges.75–85. (LNCS.)
Abstract: In this paper we present a knowledge base of architectural documents aiming at improving existing methods of floor plan classification and understanding. It consists of an ontological definition of the domain and the inclusion of real instances coming from both, automatically interpreted and manually labeled documents. The knowledge base has proven to be an effective tool to structure our knowledge and to easily maintain and upgrade it. Moreover, it is an appropriate means to automatically check the consistency of relational data and a convenient complement of hard-coded knowledge interpretation systems.
Keywords: Graphics recognition; Floor plan analysi; Domain ontology
|
|
|
Mohamed Ali Souibgui and 7 others. 2022. One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition. Winter Conference on Applications of Computer Vision.
Abstract: Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). This appears, for example, in the case of historical ciphered manuscripts, which are usually written with invented alphabets to hide the content. Thus, in this paper we address this problem through a data generation technique based on Bayesian Program Learning (BPL). Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using only one sample of each symbol from the desired alphabet. After generating symbols, we create synthetic lines to train state-of-the-art HTR architectures in a segmentation free fashion. Quantitative and qualitative analyses were carried out and confirm the effectiveness of the proposed method, achieving competitive results compared to the usage of real annotated data.
Keywords: Document Analysis
|
|
|
N. Zakaria, Jean-Marc Ogier and Josep Llados. 2005. On-line Graphics Recognition based on Invariant Spatio-Sequential Descriptor: Fuzzy Matrix.
|
|
|
Alicia Fornes, Josep Llados, Gemma Sanchez and Horst Bunke. 2009. On the use of textural features for writer identification in old handwritten music scores. 10th International Conference on Document Analysis and Recognition.996–1000.
Abstract: Writer identification consists in determining the writer of a piece of handwriting from a set of writers. In this paper we present a system for writer identification in old handwritten music scores which uses only music notation to determine the author. The steps of the proposed system are the following. First of all, the music sheet is preprocessed for obtaining a music score without the staff lines. Afterwards, four different methods for generating texture images from music symbols are applied. Every approach uses a different spatial variation when combining the music symbols to generate the textures. Finally, Gabor filters and Grey-scale Co-ocurrence matrices are used to obtain the features. The classification is performed using a k-NN classifier based on Euclidean distance. The proposed method has been tested on a database of old music scores from the 17th to 19th centuries, achieving encouraging identification rates.
|
|