|
Anjan Dutta, Josep Llados, Horst Bunke and Umapada Pal. 2013. Near Convex Region Adjacency Graph and Approximate Neighborhood String Matching for Symbol Spotting in Graphical Documents. 12th International Conference on Document Analysis and Recognition.1078–1082.
Abstract: This paper deals with a subgraph matching problem in Region Adjacency Graph (RAG) applied to symbol spotting in graphical documents. RAG is a very important, efficient and natural way of representing graphical information with a graph but this is limited to cases where the information is well defined with perfectly delineated regions. What if the information we are interested in is not confined within well defined regions? This paper addresses this particular problem and solves it by defining near convex grouping of oriented line segments which results in near convex regions. Pure convexity imposes hard constraints and can not handle all the cases efficiently. Hence to solve this problem we have defined a new type of convexity of regions, which allows convex regions to have concavity to some extend. We call this kind of regions Near Convex Regions (NCRs). These NCRs are then used to create the Near Convex Region Adjacency Graph (NCRAG) and with this representation we have formulated the problem of symbol spotting in graphical documents as a subgraph matching problem. For subgraph matching we have used the Approximate Edit Distance Algorithm (AEDA) on the neighborhood string, which starts working after finding a key node in the input or target graph and iteratively identifies similar nodes of the query graph in the neighborhood of the key node. The experiments are performed on artificial, real and distorted datasets.
|
|
|
Manuel Carbonell. 2020. Neural Information Extraction from Semi-structured Documents A. (Ph.D. thesis, Ediciones Graficas Rey.)
Abstract: Sectors as fintech, legaltech or insurance process an inflow of millions of forms, invoices, id documents, claims or similar every day. Together with these, historical archives provide gigantic amounts of digitized documents containing useful information that needs to be stored in machine encoded text with a meaningful structure. This procedure, known as information extraction (IE) comprises the steps of localizing and recognizing text, identifying named entities contained in it and optionally finding relationships among its elements. In this work we explore multi-task neural models at image and graph level to solve all steps in a unified way. While doing so we find benefits and limitations of these end-to-end approaches in comparison with sequential separate methods. More specifically, we first propose a method to produce textual as well as semantic labels with a unified model from handwritten text line images. We do so with the use of a convolutional recurrent neural model trained with connectionist temporal classification to predict the textual as well as semantic information encoded in the images. Secondly, motivated by the success of this approach we investigate the unification of the localization and recognition tasks of handwritten text in full pages with an end-to-end model, observing benefits in doing so. Having two models that tackle information extraction subsequent task pairs in an end-to-end to end manner, we lastly contribute with a method to put them all together in a single neural network to solve the whole information extraction pipeline in a unified way. Doing so we observe some benefits and some limitations in the approach, suggesting that in certain cases it is beneficial to train specialized models that excel at a single challenging task of the information extraction process, as it can be the recognition of named entities or the extraction of relationships between them. For this reason we lastly study the use of the recently arrived graph neural network architectures for the semantic tasks of the information extraction process, which are recognition of named entities and relation extraction, achieving promising results on the relation extraction part.
|
|
|
Thanh Ha Do, Salvatore Tabbone and Oriol Ramos Terrades. 2013. New Approach for Symbol Recognition Combining Shape Context of Interest Points with Sparse Representation. 12th International Conference on Document Analysis and Recognition.265–269.
Abstract: In this paper, we propose a new approach for symbol description. Our method is built based on the combination of shape context of interest points descriptor and sparse representation. More specifically, we first learn a dictionary describing shape context of interest point descriptors. Then, based on information retrieval techniques, we build a vector model for each symbol based on its sparse representation in a visual vocabulary whose visual words are columns in the learneddictionary. The retrieval task is performed by ranking symbols based on similarity between vector models. Evaluation of our method, using benchmark datasets, demonstrates the validity of our approach and shows that it outperforms related state-of-theart methods.
|
|
|
Thanh Ha Do, Salvatore Tabbone and Oriol Ramos Terrades. 2012. Noise suppression over bi-level graphical documents using a sparse representation. Colloque International Francophone sur l'Écrit et le Document.
|
|
|
Anguelos Nicolaou, Sounak Dey, V.Christlein, A.Maier and Dimosthenis Karatzas. 2018. Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings. International Workshop on Reproducible Research in Pattern Recognition.71–82. (LNCS.)
Abstract: Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized distances introduce and provide bounds on the effect. We demonstrate that it can have a measurable effect in empirical data in state-of-the-art systems. We also approach the phenomenon from a computer security perspective and demonstrate how someone being evaluated by a third party can exploit this ambiguity and greatly outperform a random predictor without even access to the input data. We also suggest a simple solution making the performance metrics, which rely on ranking, totally deterministic and impervious to such exploits.
|
|
|
Marçal Rusiñol, J. Chazalon and Jean-Marc Ogier. 2014. Normalisation et validation d'images de documents capturées en mobilité. Colloque International Francophone sur l'Écrit et le Document.109–124.
Abstract: Mobile document image acquisition integrates many distortions which must be corrected or detected on the device, before the document becomes unavailable or paying data transmission fees. In this paper, we propose a system to correct perspective and illumination issues, and estimate the sharpness of the image for OCR recognition. The correction step relies on fast and accurate border detection followed by illumination normalization. Its evaluation on a private dataset shows a clear improvement on OCR accuracy. The quality assessment
step relies on a combination of focus measures. Its evaluation on a public dataset shows that this simple method compares well to state of the art, learning-based methods which cannot be embedded on a mobile, and outperforms metric-based methods.
Keywords: mobile document image acquisition; perspective correction; illumination correction; quality assessment; focus measure; OCR accuracy prediction
|
|
|
Robert Benavente, Gemma Sanchez, Ramon Baldrich, Maria Vanrell and Josep Llados. 2000. Normalized colour segmentation for human appearance description. 15 th International Conference on Pattern Recognition.637–641.
|
|
|
Lluis Pere de las Heras, Joan Mas, Gemma Sanchez and Ernest Valveny. 2013. Notation-invariant patch-based wall detector in architectural floor plans. Graphics Recognition. New Trends and Challenges. Springer Berlin Heidelberg, 79–88. (LNCS.)
Abstract: Architectural floor plans exhibit a large variability in notation. Therefore, segmenting and identifying the elements of any kind of plan becomes a challenging task for approaches based on grouping structural primitives obtained by vectorization. Recently, a patch-based segmentation method working at pixel level and relying on the construction of a visual vocabulary has been proposed in [1], showing its adaptability to different notations by automatically learning the visual appearance of the elements in each different notation. This paper presents an evolution of that previous work, after analyzing and testing several alternatives for each of the different steps of the method: Firstly, an automatic plan-size normalization process is done. Secondly we evaluate different features to obtain the description of every patch. Thirdly, we train an SVM classifier to obtain the category of every patch instead of constructing a visual vocabulary. These variations of the method have been tested for wall detection on two datasets of architectural floor plans with different notations. After studying in deep each of the steps in the process pipeline, we are able to find the best system configuration, which highly outperforms the results on wall segmentation obtained by the original paper.
|
|
|
Hongxing Gao, Marçal Rusiñol, Dimosthenis Karatzas, Josep Llados, R.Jain and D.Doermann. 2015. Novel Line Verification for Multiple Instance Focused Retrieval in Document Collections. 13th International Conference on Document Analysis and Recognition ICDAR2015.481–485.
|
|
|
Ernest Valveny and Antonio Lopez. 2003. Numeral Recognition for Quality Control of Surgical Sachets.
|
|