Search

Information extraction from handwritten documents involves traditionally three distinct steps: Document Layout Analysis, Handwritten Text Recognition, and Named Entity Recognition. Recent approaches have attempted to integrate these steps into a single process using fully end-to-end architectures. Despite this, these integrated approaches have not yet matched the performance of language models, when applied to information extraction in plain text. In this paper, we introduce DANIEL (Document Attention Network for Information Extraction and Labelling), a fully end-to-end architecture integrating a language model and designed for comprehensive handwritten document understanding. DANIEL performs layout recognition, handwriting recognition, and named entity recognition on full-page documents. Moreover, it can simultaneously learn across multiple languages, layouts, and tasks. For named entity recognition, the ontology to be applied can be specified via the input prompt. The architecture employs a convolutional encoder capable of processing images of any size without resizing, paired with an autoregressive decoder based on a transformer-based language model. DANIEL achieves competitive results on four datasets, including a new state-of-the-art performance on RIMES 2009 and M-POPP for Handwriting Text Recognition, and IAM NER for Named Entity Recognition. Furthermore, DANIEL is much faster than existing approaches. We provide the source code and the weights of the trained models at \url{https://github.com/Shulk97/daniel}.

Optical Music Recognition (OMR) has made significant progress since its inception, with various approaches now capable of accurately transcribing music scores into digital formats. Despite these advancements, most so-called \emph{end-to-end} OMR approaches still rely on multi-stage processing pipelines for transcribing full-page score images, which introduces several limitations that hinder the full potential of the field. In this paper, we present the first truly end-to-end approach for page-level OMR. Our system, which combines convolutional layers with autoregressive Transformers, processes an entire music score page and outputs a complete transcription in a music encoding format. This is made possible by both the architecture and the training procedure, which utilizes curriculum learning through incremental synthetic data generation. We evaluate the proposed system using pianoform corpora. This evaluation is conducted first in a controlled scenario with synthetic data, and subsequently against two real-world corpora of varying conditions. Our approach is compared with leading commercial OMR software. The results demonstrate that our system not only successfully transcribes full-page music scores but also outperforms the commercial tool in both zero-shot settings and after fine-tuning with the target domain, representing a significant contribution to the field of OMR.

The EXO-POPP project aims to establish a comprehensive database comprising 300,000 marriage records from Paris and its suburbs, spanning the years 1880 to 1940, which are preserved in over 130,000 scans of double pages. Each marriage record may encompass up to 118 distinct types of information that require extraction from plain text. In this paper, we introduce the M-POPP dataset, a subset of the M-POPP database with annotations for full-page text recognition and information extraction in both handwritten and printed documents, and which is now publicly available. We present a fully end-to-end architecture adapted from the DAN, designed to perform both handwritten text recognition and information extraction directly from page images without the need for explicit segmentation. We showcase the information extraction capabilities of this architecture by achieving a new state of the art for full-page Information Extraction on Esposalles and we use this architecture as a baseline for the M-POPP dataset. We also assess and compare how different encoding strategies for named entities in the text affect the performance of jointly recognizing handwritten text and extracting information, from full pages., Comment: To be published in: International Conference on Document Analysis and Recognition - ICDAR 2024

State-of-the-art end-to-end Optical Music Recognition (OMR) has, to date, primarily been carried out using monophonic transcription techniques to handle complex score layouts, such as polyphony, often by resorting to simplifications or specific adaptations. Despite their efficacy, these approaches imply challenges related to scalability and limitations. This paper presents the Sheet Music Transformer, the first end-to-end OMR model designed to transcribe complex musical scores without relying solely on monophonic strategies. Our model employs a Transformer-based image-to-sequence framework that predicts score transcriptions in a standard digital music encoding format from input images. Our model has been tested on two polyphonic music datasets and has proven capable of handling these intricate music structures effectively. The experimental outcomes not only indicate the competence of the model, but also show that it is better than the state-of-the-art methods, thus contributing to advancements in end-to-end OMR transcription., Comment: Submitted to the International Conference on Document Analysis and Recognition 2024

Recent advances in handwritten text recognition enabled to recognize whole documents in an end-to-end way: the Document Attention Network (DAN) recognizes the characters one after the other through an attention-based prediction process until reaching the end of the document. However, this autoregressive process leads to inference that cannot benefit from any parallelization optimization. In this paper, we propose Faster DAN, a two-step strategy to speed up the recognition process at prediction time: the model predicts the first character of each text line in the document, and then completes all the text lines in parallel through multi-target queries and a specific document positional encoding scheme. Faster DAN reaches competitive results compared to standard DAN, while being at least 4 times faster on whole single-page and double-page images of the RIMES 2009, READ 2016 and MAURDOR datasets. Source code and trained model weights are available at https://github.com/FactoDeepLearning/FasterDAN.

Categorical data are present in key areas such as health or supply chain, and this data require specific treatment. In order to apply recent machine learning models on such data, encoding is needed. In order to build interpretable models, one-hot encoding is still a very good solution, but such encoding creates sparse data. Gradient estimators are not suited for sparse data: the gradient is mainly considered as zero while it simply does not always exists, thus a novel gradient estimator is introduced. We show what this estimator minimizes in theory and show its efficiency on different datasets with multiple model architectures. This new estimator performs better than common estimators under similar settings. A real world retail dataset is also released after anonymization. Overall, the aim of this paper is to thoroughly consider categorical data and adapt models and optimizers to these key features.

Deep neural networks are becoming increasingly powerful and large and always require more labelled data to be trained. However, since annotating data is time-consuming, it is now necessary to develop systems that show good performance while learning on a limited amount of data. These data must be correctly chosen to obtain models that are still efficient. For this, the systems must be able to determine which data should be annotated to achieve the best results. In this paper, we propose four estimators to estimate the confidence of object detection predictions. The first two are based on Monte Carlo dropout, the third one on descriptive statistics and the last one on the detector posterior probabilities. In the active learning framework, the three first estimators show a significant improvement in performance for the detection of document physical pages and text lines compared to a random selection of images. We also show that the proposed estimator based on descriptive statistics can replace MC dropout, reducing the computational cost without compromising the performances.

Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper, we address the limitations that currently prevent people from building line segmentation models with a high generalization capacity. We present a study conducted using three state-of-the-art systems Doc-UFCN, dhSegment and ARU-Net and show that it is possible to build generic models trained on a wide variety of historical document datasets that can correctly segment diverse unseen pages. This paper also highlights the importance of the annotations used during training: each existing dataset is annotated differently. We present a unification of the annotations and show its positive impact on the final text recognition results. In this end, we present a complete evaluation strategy using standard pixel-level metrics, object-level ones and introducing goal-oriented metrics.

Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ 2016 dataset at page level, as well as double-page level with a CER of 3.43% and 3.70%, respectively. We also provide results for the RIMES 2009 dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN.

The segmentation of complex images into semantic regions has seen a growing interest these last years with the advent of Deep Learning. Until recently, most existing methods for Historical Document Analysis focused on the visual appearance of documents, ignoring the rich information that textual content can offer. However, the segmentation of complex documents into semantic regions is sometimes impossible relying only on visual features and recent models embed both visual and textual information. In this paper, we focus on the use of both visual and textual information for segmenting historical registers into structured and meaningful units such as acts. An act is a text recording containing valuable knowledge such as demographic information (baptism, marriage or death) or royal decisions (donation or pardon). We propose a simple pipeline to enrich document images with the position of text lines containing key-phrases and show that running a standard image-based layout analysis system on these images can lead to significant gains. Our experiments show that the detection of acts increases from 38 % of mAP to 74 % when adding textual information, in real use-case conditions where text lines positions and content are extracted with an automatic recognition system.

Unconstrained handwriting recognition is an essential task in document analysis. It is usually carried out in two steps. First, the document is segmented into text lines. Second, an Optical Character Recognition model is applied on these line images. We propose the Simple Predict & Align Network: an end-to-end recurrence-free Fully Convolutional Network performing OCR at paragraph level without any prior segmentation stage. The framework is as simple as the one used for the recognition of isolated lines and we achieve competitive results on three popular datasets: RIMES, IAM and READ 2016. The proposed model does not require any dataset adaptation, it can be trained from scratch, without segmentation labels, and it does not require line breaks in the transcription labels. Our code and trained model weights are available at https://github.com/FactoDeepLearning/SPAN.

In this paper, we introduce a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images, our method Doc-UFCN relies on a U-shaped model trained from scratch for detecting objects from historical documents. We consider the line segmentation task and more generally the layout analysis problem as a pixel-wise classification task then our model outputs a pixel-labeling of the input images. We show that Doc-UFCN outperforms state-of-the-art methods on various datasets and also demonstrate that the pre-trained parts on natural scene images are not required to reach good results. In addition, we show that pre-training on multiple document datasets can improve the performances. We evaluate the models using various metrics to have a fair and complete comparison between the methods.

Unconstrained handwritten text recognition remains an important challenge for deep neural networks. These last years, recurrent networks and more specifically Long Short-Term Memory networks have achieved state-of-the-art performance in this field. Nevertheless, they are made of a large number of trainable parameters and training recurrent neural networks does not support parallelism. This has a direct influence on the training time of such architectures, with also a direct consequence on the time required to explore various architectures. Recently, recurrence-free architectures such as Fully Convolutional Networks with gated mechanisms have been proposed as one possible alternative achieving competitive results. In this paper, we explore convolutional architectures and compare them to a CNN+BLSTM baseline. We propose an experimental study regarding different architectures on an offline handwriting recognition task using the RIMES dataset, and a modified version of it that consists of augmenting the images with notebook backgrounds that are printed grids.

Unconstrained handwritten text recognition is a major step in most document analysis tasks. This is generally processed by deep recurrent neural networks and more specifically with the use of Long Short-Term Memory cells. The main drawbacks of these components are the large number of parameters involved and their sequential execution during training and prediction. One alternative solution to using LSTM cells is to compensate the long time memory loss with an heavy use of convolutional layers whose operations can be executed in parallel and which imply fewer parameters. In this paper we present a Gated Fully Convolutional Network architecture that is a recurrence-free alternative to the well-known CNN+LSTM architectures. Our model is trained with the CTC loss and shows competitive results on both the RIMES and IAM datasets. We release all code to enable reproduction of our experiments: https://github.com/FactoDeepLearning/LinePytorchOCR.

Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propose a unified end-to-end model using hybrid attention to tackle this task. This model is designed to iteratively process a paragraph image line by line. It can be split into three modules. An encoder generates feature maps from the whole paragraph image. Then, an attention module recurrently generates a vertical weighted mask enabling to focus on the current text line features. This way, it performs a kind of implicit line segmentation. For each text line features, a decoder module recognizes the character sequence associated, leading to the recognition of a whole paragraph. We achieve state-of-the-art character error rate at paragraph level on three popular datasets: 1.91% for RIMES, 4.45% for IAM and 3.59% for READ 2016. Our code and trained model weights are available at https://github.com/FactoDeepLearning/VerticalAttentionOCR.

We report an extension of a Keras Model, called CTCModel, to perform the Connectionist Temporal Classification (CTC) in a transparent way. Combined with Recurrent Neural Networks, the Connectionist Temporal Classification is the reference method for dealing with unsegmented input sequences, i.e. with data that are a couple of observation and label sequences where each label is related to a subset of observation frames. CTCModel makes use of the CTC implementation in the Tensorflow backend for training and predicting sequences of labels using Keras. It consists of three branches made of Keras models: one for training, computing the CTC loss function; one for predicting, providing sequences of labels; and one for evaluating that returns standard metrics for analyzing sequences of predictions.

We address the design of a unified multilingual system for handwriting recognition. Most of multi- lingual systems rests on specialized models that are trained on a single language and one of them is selected at test time. While some recognition systems are based on a unified optical model, dealing with a unified language model remains a major issue, as traditional language models are generally trained on corpora composed of large word lexicons per language. Here, we bring a solution by con- sidering language models based on sub-lexical units, called multigrams. Dealing with multigrams strongly reduces the lexicon size and thus decreases the language model complexity. This makes pos- sible the design of an end-to-end unified multilingual recognition system where both a single optical model and a single language model are trained on all the languages. We discuss the impact of the language unification on each model and show that our system reaches state-of-the-art methods perfor- mance with a strong reduction of the complexity., Comment: preprint

In this paper, we introduce a new modeling approach of texts for handwriting recognition based on syllables. We propose a supervised syllabification approach for the French and English languages for building a vocabulary of syllables. Statistical n-gram language models of syllables are trained on French and English Wikipedia corpora. The handwriting recognition system, based on optical HMM context independent character models, performs a two pass decoding, integrating the proposed syllabic models. Evaluation is carried out on the French RIMES dataset and English IAM dataset by analyzing the performance for various coverage of the syllable models. We also compare the syllable models with lexicon and character n-gram models. The proposed approach reaches interesting performances thanks to its capacity to cover a large amount of out of vocabulary words working with a limited amount of syllables combined with statistical n-gram of reasonable order.

Offline handwritten text line recognition is a hard task that requires both an efficient optical character recognizer and language model. Handwriting recognition state of the art methods are based on Long Short Term Memory (LSTM) recurrent neural networks (RNN) coupled with the use of linguistic knowledge. Most of the proposed approaches in the literature focus on improving one of the two components and use constraint, dedicated to a database lexicon. However, state of the art performance is achieved by combining multiple optical models, and possibly multiple language models with the Recognizer Output Voting Error Reduction (ROVER) framework. Though handwritten line recognition with ROVER has been implemented by combining only few recognizers because training multiple complete recognizers is hard. In this paper we propose a Lexicon Verified ROVER: LV-ROVER, that has a reduce complexity compare to the original one and that can combine hundreds of recognizers without language models. We achieve state of the art for handwritten line text on the RIMES dataset., Comment: Submitted to Pattern Recognition Letters

State-of-the-art methods for handwriting recognition are based on Long Short Term Memory (LSTM) recurrent neural networks (RNN), which now provides very impressive character recognition performance. The character recognition is generally coupled with a lexicon driven decoding process which integrates dictionaries. Unfortunately these dictionaries are limited to hundred of thousands words for the best systems, which prevent from having a good language coverage, and therefore limit the global recognition performance. In this article, we propose an alternative to the lexicon driven decoding process based on a lexicon verification process, coupled with an original cascade architecture. The cascade is made of a large number of complementary networks extracted from a single training (called cohort), making the learning process very light. The proposed method achieves new state-of-the art word recognition performance on the Rimes and IAM databases. Dealing with gigantic lexicon of 3 millions words, the methods also demonstrates interesting performance with a fast decision stage., Comment: 31 pages, paper submitted to Pattern Recognition

Newspapers are documents made of news item and informative articles. They are not meant to be red iteratively: the reader can pick his items in any order he fancies. Ignoring this structural property, most digitized newspaper archives only offer access by issue or at best by page to their content. We have built a digitization workflow that automatically extracts newspaper articles from images, which allows indexing and retrieval of information at the article level. Our back-end system extracts the logical structure of the page to produce the informative units: the articles. Each image is labelled at the pixel level, through a machine learning based method, then the page logical structure is constructed up from there by the detection of structuring entities such as horizontal and vertical separators, titles and text lines. This logical structure is stored in a METS wrapper associated to the ALTO file produced by the system including the OCRed text. Our front-end system provides a web high definition visualisation of images, textual indexing and retrieval facilities, searching and reading at the article level. Articles transcriptions can be collaboratively corrected, which as a consequence allows for better indexing. We are currently testing our system on the archives of the Journal de Rouen, one of France eldest local newspaper. These 250 years of publication amount to 300 000 pages of very variable image quality and layout complexity. Test year 1808 can be consulted at plair.univ-rouen.fr., Comment: ACM Document Engineering, France (2012)