Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pre-training data to learn intermediate representations and often suffer a significant performance drop in real-world online industrial settings. A primary issue is their heavy reliance on OCR engines to extract local positional information within document pages, which limits the models' ability to capture global information and hinders their generalizability, flexibility, and robustness. In this paper, we introduce GlobalDoc, a cross modal transformer-based architecture pre-trained in a self supervised manner using three novel pretext objective tasks. GlobalDoc improves the learning of richer semantic concepts by unifying language and visual representations, resulting in more transferable models. For proper evaluation, we also propose two novel document-level downstream VDU tasks, Few-Shot Document Image Classification (DIC) and Content-based Document Image Retrieval (DIR), designed to simulate industrial scenarios more closely. Extensive experimentation has been conducted to demonstrate GlobalDoc's effectiveness in practical settings.

Nowadays the paradigm of link discovery problems has shown significant improvements on Knowledge Graphs. However, method performances are harmed by the unbalanced nature of this classification problem, since many methods are easily biased to not find proper links. In this paper we present a discriminative neural variational auto-encoder model, called DNVAE from now on, in which we have introduced latent variables to serve as embedding vectors. As a result, the learnt generative model approximate better the underlying distribution and, at the same time, it better differentiate the type of relations in the knowledge graph. We have evaluated this approach on benchmark knowledge graph and Census records. Results in this last data set are quite impressive since we reach the highest possible score in the evaluation metrics. However, further experiments are still needed to deeper evaluate the performance of the method in more challenging tasks.

This paper is focused on the detection of counterfeit documents via the recurrent comparison of the security textured background regions of two images. The main contributions are twofold: first we apply and adapt a recurrent comparator architecture with attention mechanism to the counterfeit detection task, which constructs a representation of the background regions by recurrently condition the next observation, learning the difference between genuine and counterfeit images through iterative glimpses. Second we propose a new counterfeit document dataset to ensure the generalization of the learned model towards the detection of the lack of resolution during the counterfeit manufacturing. The presented network, outperforms state-of-the-art classification approaches for counterfeit detection as demonstrated in the evaluation.

Tabular structures in documents offer a complementary dimension to the raw textual data, representing logical or quantitative relationships among pieces of information. In digital mail room applications, where a large amount of administrative documents must be processed with reasonable accuracy, the detection and interpretation of tables is crucial. Table recognition has gained interest in document image analysis, in particular in unconstrained formats (absence of rule lines, unknown information of rows and columns). In this work, we propose a graph-based approach for detecting tables in document images. Instead of using the raw content (recognized text), we make use of the location, context and content type, thus it is purely a structure perception approach, not dependent on the language and the quality of the text reading. Our framework makes use of Graph Neural Networks (GNNs) in order to describe the local repetitive structural information of tables in invoice documents. Our proposed model has been experimentally validated in two invoice datasets and achieved encouraging results. Additionally, due to the scarcity of benchmark datasets for this task, we have contributed to the community a novel dataset derived from the RVL-CDIP invoice data. It will be publicly released to facilitate future research.

This paper describes an exhaustive comparative analysis and evaluation of different existing texture descriptor algorithms to differentiate between genuine and counterfeit documents. We include in our experiments different categories of algorithms and compare them in different scenarios with several counterfeit datasets, comprising banknotes and identity documents. Computational time in the extraction of each descriptor is important because the final objective is to use it in a real industrial scenario. HoG and CNN based descriptors stands out statistically over the rest in terms of the F1-score/time ratio performance.

This paper is focused on the detection of counterfeit photocopy banknotes. The main difficulty is to work on a real industrial scenario without any constraint about the acquisition device and with a single image. The main contributions of this paper are twofold: first the adaptation and performance evaluation of existing approaches to classify the genuine and photocopy banknotes using background texture printing analysis, which have not been applied into this context before. Second, a new dataset of Euro banknotes images acquired with several cameras under different luminance conditions to evaluate these methods. Experiments on the proposed algorithms show that mixing SIFT features and sparse coding dictionaries achieves quasi perfect classification using a linear SVM with the created dataset. Approaches using dictionaries to cover all possible texture variations have demonstrated to be robust and outperform the state-of-the-art methods using the proposed benchmark.

Nowadays, document forgery is becoming a real issue. A large amount of documents that contain critical information as payment slips, invoices or contracts, are constantly subject to fraudster manipulation because of the lack of security regarding this kind of document. Previously, a system to detect fraudulent documents based on its intrinsic features has been presented. It was especially designed to retrieve copy-move forgery and imperfection due to fraudster manipulation. However, when a set of characters is not present in the original document, copy-move forgery is not feasible. Hence, the fraudster will use a text toolbox to add or modify information in the document by imitating the font or he will cut and paste characters from another document where the font properties are similar. This often results in font type errors. Thus, a clue to detect document forgery consists of finding characters, words or sentences in a document with font properties different from their surroundings. To this end, we present in this paper an automatic forgery detection method based on document font features. Using the Conditional Random Field a measurement of probability that a character belongs to a specific font is made by comparing the character font features to a knowledge database. Then, the character is classified as a genuine or a fake one by comparing its probability to belong to a certain font type with those of the neighboring characters.

In this paper, we propose the use of an Attributed Graph Grammar as unique framework to model and recognize the structure of floor plans. This grammar represents a building as a hierarchical composition of structurally and semantically related elements, where common representations are learned stochastically from annotated data. Given an input image, the parsing consists on constructing that graph representation that better agrees with the probabilistic model defined by the grammar. The proposed method provides several advantages with respect to the traditional floor plan analysis techniques. It uses an unsupervised statistical approach for detecting walls that adapts to different graphical notations and relaxes strong structural assumptions such are straightness and orthogonality. Moreover, the independence between the knowledge model and the parsing implementation allows the method to learn automatically different building configurations and thus, to cope the existing variability. These advantages are clearly demonstrated by comparing it with the most recent floor plan interpretation techniques on 4 datasets of real floor plans with different notations.

Nowadays, automatic identity document recognition, including passport and driving license recognition, is at the core of many applications within the administrative and service sectors, such as police, hospitality, car renting, etc. In former years, the document information was manually extracted whereas today this data is recognized automatically from images obtained by flat-bed scanners. Yet, since these scanners tend to be expensive and voluminous, companies in the sector have recently turned their attention to cheaper, small and yet computationally powerful scanners: the mobile devices. The document identity recognition from mobile images enclose several new difficulties w.r.t traditional scanned images, such as the loss of a controlled background, perspective, blurring, etc. In this paper we present a real application for identity document classification of images taken from mobile devices. This classification process is of extreme importance since a prior knowledge of the document type and origin strongly facilitates the subsequent information extraction. The proposed method is based on a traditional Bagof-Words in which we have taken into consideration several key aspects to enhance recognition rate. The method performance has been studied on three datasets containing more than 2000 images from 129 different document classes.

This paper proposes a new approach to spot symbols into graphical documents using sparse representations. More specifically, a dictionary is learned from a training database of local descriptors defined over the documents. Following their sparse representations, interest points sharing similar properties are used to define interest regions. Using an original adaptation of information retrieval techniques, a vector model for interest regions and for a query symbol is built based on its sparsity in a visual vocabulary where the visual words are columns in the learned dictionary. The matching process is performed comparing the similarity between vector models. Evaluation on SESYD datasets demonstrates that our method is promising.

In this paper we present a method to perform layout analysis in structured documents. We proposed an EM-based algorithm to fit a set of Gaussian mixtures to the different regions according to the logical distribution along the page. After the convergence, we estimate the final shape of the regions according to the parameters computed for each component of the mixture. We evaluated our method in the task of record detection in a collection of historical structured documents and performed a comparison with other previous works in this task.

In this paper, we propose an algorithm for denoising document images using sparse representations. Following a training set, this algorithm is able to learn the main document characteristics and also, the kind of noise included into the documents. In this perspective, we propose to model the noise energy based on the normalized cross-correlation between pairs of noisy and non-noisy documents. Experimental results on several datasets demonstrate the robustness of our method compared with the state-of-the-art.

Paper documents still represent a large amount of information supports used nowadays and may contain critical data. Even though official documents are secured with techniques such as printed patterns or artwork, paper documents suffer from a lack of security. However, the high availability of cheap scanning and printing hardware allows non-experts to easily create fake documents. As the use of a watermarking system added during the document production step is hardly possible, solutions have to be proposed to distinguish a genuine document from a forged one. In this paper, we present an automatic forgery detection method based on document's intrinsic features at character level. This method is based on the one hand on outlier character detection in a discriminant feature space and on the other hand on the detection of strictly similar characters. Therefore, a feature set is computed for all characters. Then, based on a distance between characters of the same class, the character is classified as a genuine one or a fake one.

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 learned dictionary. The retrieval task is performed by ranking symbols based on similarity between vector models. The evaluation of our method, using benchmark datasets, demonstrates the validity of our approach and shows that it outperforms related state-of-the-art methods.

In this paper we present a handwritten line segmentation method devised to work on documents composed of several paragraphs with multiple line orientations. The method is based on a variation of the EM algorithm for the estimation of a set of regression lines between the connected components that compose the image. We evaluated our method on the ICDAR2009 handwriting segmentation contest dataset with promising results that overcome most of the presented methods. In addition, we prove the usability of the presented method by performing line segmentation on the George Washington database obtaining encouraging results.

The amount of digitized legacy documents has been rising dramatically over the last years due mainly to the increasing number of on-line digital libraries publishing this kind of documents, waiting to be classified and finally transcribed into a textual electronic format (such as ASCII or PDF). Nevertheless, most of the available fully-automatic applications addressing this task are far from being perfect and heavy and inefficient human intervention is often required to check and correct the results of such systems. In contrast, multimodal interactive-predictive approaches may allow the users to participate in the process helping the system to improve the overall performance. With this in mind, two sets of recent advances are introduced in this work: a novel interactive method for text block detection and two multimodal interactive handwritten text transcription systems which use active learning and interactive-predictive technologies in the recognition process.

A new handwritten text database, GERMANA, is presented to facilitate empirical comparison of different approaches to text line extraction and off-line handwriting recognition. GERMANA is the result of digitising and annotating a 764-page Spanish manuscript from 1891, in which most pages only contain nearly calligraphed text written on ruled sheets of well-separated lines. To our knowledge, it is the first publicly available database for handwriting research, mostly written in Spanish and comparable in size to standard databases. Due to its sequential book structure, it is also well-suited for realistic assessment of interactive handwriting recognition systems. To provide baseline results for reference in future studies, empirical results are also reported, using standard techniques and tools for preprocessing, feature extraction, HMM-based image modelling, and language modelling.

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.

In some Thai documents, a single text line of a printed document page may contain words of both Thai and Roman scripts. For the Optical Character Recognition (OCR) of such a document page it is better to identify, at first, Thai and Roman script portions and then to use individual OCR systems of the respective scripts on these identified portions. In this article, an SVM-based method is proposed for identification of word-wise printed Roman and Thai scripts from a single line of a document page. Here, at first, the document is segmented into lines and then lines are segmented into character groups (words). In the proposed scheme, we identify the script of a character group combining different character features obtained from structural shape, profile behavior, component overlapping information, topological properties, and water reservoir concept, etc. Based on the experiment on 10,000 data (words) we obtained 99.62% script identification accuracy from the proposed scheme.

In this paper we present an adaptive method for graphic symbol representation based on shape contexts. The proposed descriptor is invariant under classical geometric transforms (rotation, scale) and based on interest points. To reduce the complexity of matching a symbol to a largeset of candidates we use the popular vector model for information retrieval. In this way, on the set of shape descriptors we build a visual vocabulary where each symbol is retrieved on visual words. Experimental results on complex and occluded symbols show that the approach is very promising.

This paper presents a fast method using simple genetic algorithms (GAs) for features selection. Unlike traditional approaches using GAs, we have used the combination of Adaboost classifiers to evaluate an individual of the population. So, the fitness function we have used is defined by the error rate of this combination. This approach has been implemented and tested on the MNIST database and the results confirm the effectiveness and the robustness of the proposed approach.

In this paper we present a new descriptor based on the Radon transform. We propose a histogram of the Radon transform, called HRT, which is invariant to common geometrical transformations. For black and white shapes, the HRT descriptor is a histogram of shape lengths at each orientation. The experimental results, defined on different databases and compared with several well-known descriptors, show the robustness of our method.

In some Thai documents, a single text line of a document page may contain both Thai and English scripts. For the optical character recognition (OCR) of such a document page it is better to identify, at first, Thai and English script portions and then to use individual OCR system of the respective scripts on these identified portions. In this paper, a SVM based method is proposed for identification of word-wise printed English and Thai scripts from a single line of a document page. Here, at first, the document is segmented into lines and then lines are segmented into character groups (words). In the proposed scheme, we identify the script of the individual character group combining different character features obtained from structural shape, profile, component overlapping information, topological properties, water reservoir concept etc. Based on the experiment on 6110 data we obtained 99.36% script identification accuracy from the proposed scheme.

Shape descriptors play an important role in many document analysis application. In this paper we review some of the shape descriptors proposed in the last years from a new point of view. We propose the definitions of descriptor and primitive and introduce the notion of feature extraction method. With these definitions, we propose a new classification of shape descriptors that permits to classify according to their properties pointing out their strengths and weaknesses.

We propose a set of shape descriptors for image retrieval of graphic documents based on the ridgelets transform, which can be seen as a combination of the Radon transform and the wavelets transform. It is especially well suited to detect linear features, the most relevant features in graphic documents. It also provides a multiscale representation, useful for indexing and retrieval purposes. From the ridgelets representation of an image, we have defined a set of local norm descriptors based on computing a norm over some specific areas of the image. This kind of descriptors are very flexible since we can define different sets of descriptors just by changing such areas of influence in the image. We have also defined a combination of descriptors at several scales of decomposition in order to improve retrieval results.

Content-based retrieval and recognition of graphic images requires good models for symbol representation, able to identify those features providing the most relevant information about the shape and the visual appearance of symbols. In this work we have used the Radon transform as the basis to extract the representation of graphic images as it permits to globally detect lineal singularities in an image, which are the most important source of information in these images. The image obtained after applying Radon transform can be used directly to describe the symbol, or can be used to extract new and compact descriptors from it, which will also be based on lineal information about the image. We present some preliminary results showing the usefulness of this representation with a set of architectural symbols.