Mickaël Coustaty

Štěpán Šimsa, Milan Šulc, Michal Uřičář et al.

This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition. It contains 6.7k annotated business documents, 100k synthetically generated documents, and nearly~1M unlabeled documents for unsupervised pre-training. The dataset has been built with knowledge of domain- and task-specific aspects, resulting in the following key features: (i) annotations in 55 classes, which surpasses the granularity of previously published key information extraction datasets by a large margin; (ii) Line Item Recognition represents a highly practical information extraction task, where key information has to be assigned to items in a table; (iii) documents come from numerous layouts and the test set includes zero- and few-shot cases as well as layouts commonly seen in the training set. The benchmark comes with several baselines, including RoBERTa, LayoutLMv3 and DETR-based Table Transformer; applied to both tasks of the DocILE benchmark, with results shared in this paper, offering a quick starting point for future work. The dataset, baselines and supplementary material are available at https://github.com/rossumai/docile.

Souhail Bakkali, Zuheng Ming, Mickael Coustaty et al.

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem by learning cross-modal representations through language and vision cues, considering intra- and inter-modality relationships. Instead of merging features from different modalities into a joint representation space, the proposed method exploits high-level interactions and learns relevant semantic information from effective attention flows within and across modalities. The proposed learning objective is devised between intra- and inter-modality alignment tasks, where the similarity distribution per task is computed by contracting positive sample pairs while simultaneously contrasting negative ones in the joint representation space}. Extensive experiments on public document classification datasets demonstrate the effectiveness and the generality of our model on low-scale and large-scale datasets.

Arthur Hemmer, Mickaël Coustaty, Nicola Bartolo et al.

Optical Character Recognition (OCR) continues to face accuracy challenges that impact subsequent applications. To address these errors, we explore the utility of OCR confidence scores for enhancing post-OCR error detection. Our study involves analyzing the correlation between confidence scores and error rates across different OCR systems. We develop ConfBERT, a BERT-based model that incorporates OCR confidence scores into token embeddings and offers an optional pre-training phase for noise adjustment. Our experimental results demonstrate that integrating OCR confidence scores can enhance error detection capabilities. This work underscores the importance of OCR confidence scores in improving detection accuracy and reveals substantial disparities in performance between commercial and open-source OCR technologies.

Arthur Hemmer, Jérôme Brachat, Mickaël Coustaty et al.

Post-OCR processing has significantly improved over the past few years. However, these have been primarily beneficial for texts consisting of natural, alphabetical words, as opposed to documents of numerical nature such as invoices, payslips, medical certificates, etc. To evaluate the OCR post-processing difficulty of these datasets, we propose a method to estimate the denoising complexity of a text and evaluate it on several datasets of varying nature, and show that texts of numerical nature have a significant disadvantage. We evaluate the estimated complexity ranking with respect to the error rates of modern-day denoising approaches to show the validity of our estimator.

Souhail Bakkali, Sanket Biswas, Zuheng Ming et al.

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.

Arthur Hemmer, Mickaël Coustaty, Nicola Bartolo et al.

We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding methods search for constraint-satisfying label-assignments while maximizing the total probability. To do this, we evaluate several existing approaches, as well as propose a novel decoding method called Lazy-$k$. Our findings demonstrate that constrained decoding approaches can significantly improve the models' performances, especially when using smaller models. The Lazy-$k$ approach allows for more flexibility between decoding time and accuracy. The code for using Lazy-$k$ decoding can be found here: https://github.com/ArthurDevNL/lazyk.

Eliott Thomas, Mickael Coustaty, Aurelie Joseph et al.

Extracting tables from documents is a critical task across various industries, especially on business documents like invoices and reports. Existing systems based on DEtection TRansformer (DETR) such as TAble TRansformer (TATR), offer solutions for Table Detection (TD) and Table Structure Recognition (TSR) but face challenges with diverse table formats and common errors like incorrect area detection and overlapping columns. This research introduces RAPTOR, a modular post-processing system designed to enhance state-of-the-art models for improved table extraction, particularly for product tables. RAPTOR addresses recurrent TD and TSR issues, improving both precision and structural predictions. For TD, we use DETR (trained on ICDAR 2019) and TATR (trained on PubTables-1M and FinTabNet), while TSR only relies on TATR. A Genetic Algorithm is incorporated to optimize RAPTOR's module parameters, using a private dataset of product tables to align with industrial needs. We evaluate our method on two private datasets of product tables, the public DOCILE dataset (which contains tables similar to our target product tables), and the ICDAR 2013 and ICDAR 2019 datasets. The results demonstrate that while our approach excels at product tables, it also maintains reasonable performance across diverse table formats. An ablation study further validates the contribution of each module in our system.

Musab Al-Ghadi, Joris Voerman, Souhail Bakkali et al.

The increasing use of digital technologies and mobile-based registration procedures highlights the vital role of personal identity documents (IDs) in verifying users and safeguarding sensitive information. However, the rise in counterfeit ID production poses a significant challenge, necessitating the development of reliable and efficient automated verification methods. This paper introduces IDTrust, a deep-learning framework for assessing the quality of IDs. IDTrust is a system that enhances the quality of identification documents by using a deep learning-based approach. This method eliminates the need for relying on original document patterns for quality checks and pre-processing steps for alignment. As a result, it offers significant improvements in terms of dataset applicability. By utilizing a bandpass filtering-based method, the system aims to effectively detect and differentiate ID quality. Comprehensive experiments on the MIDV-2020 and L3i-ID datasets identify optimal parameters, significantly improving discrimination performance and effectively distinguishing between original and scanned ID documents.

Vannkinh Nom, Souhail Bakkali, Muhammad Muzzamil Luqman et al.

Text recognition is significantly influenced by font types, especially for complex scripts like Khmer. The variety of Khmer fonts, each with its unique character structure, presents challenges for optical character recognition (OCR) systems. In this study, we evaluate the impact of 19 randomly selected Khmer font types on text recognition accuracy using Pytesseract. The fonts include Angkor, Battambang, Bayon, Bokor, Chenla, Dangrek, Freehand, Kh Kompong Chhnang, Kh SN Kampongsom, Khmer, Khmer CN Stueng Songke, Khmer Savuth Pen, Metal, Moul, Odor MeanChey, Preah Vihear, Siemreap, Sithi Manuss, and iSeth First. Our comparison of OCR performance across these fonts reveals that Khmer, Odor MeanChey, Siemreap, Sithi Manuss, and Battambang achieve high accuracy, while iSeth First, Bayon, and Dangrek perform poorly. This study underscores the critical importance of font selection in optimizing Khmer text recognition and provides valuable insights for developing more robust OCR systems.

Vannkinh Nom, Souhail Bakkali, Muhammad Muzzamil Luqman et al.

Developing effective scene text detection and recognition models hinges on extensive training data, which can be both laborious and costly to obtain, especially for low-resourced languages. Conventional methods tailored for Latin characters often falter with non-Latin scripts due to challenges like character stacking, diacritics, and variable character widths without clear word boundaries. In this paper, we introduce the first Khmer scene-text dataset, featuring 1,544 expert-annotated images, including 997 indoor and 547 outdoor scenes. This diverse dataset includes flat text, raised text, poorly illuminated text, distant and partially obscured text. Annotations provide line-level text and polygonal bounding box coordinates for each scene. The benchmark includes baseline models for scene-text detection and recognition tasks, providing a robust starting point for future research endeavors. The KhmerST dataset is publicly accessible at https://gitlab.com/vannkinhnom123/khmerst.

Jordy Van Landeghem, Rubén Tito, Łukasz Borchmann et al.

We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research progress in understanding visually-rich documents (VRDs). We present a new dataset with novelties related to types of questions, answers, and document layouts based on multi-industry, multi-domain, and multi-page VRDs of various origins, and dates. Moreover, we are pushing the boundaries of current methods by creating multi-task and multi-domain evaluation setups that more accurately simulate real-world situations where powerful generalization and adaptation under low-resource settings are desired. DUDE aims to set a new standard as a more practical, long-standing benchmark for the community, and we hope that it will lead to future extensions and contributions that address real-world challenges. Finally, our work illustrates the importance of finding more efficient ways to model language, images, and layout in DocAI.

Souhail Bakkali, Ziheng Ming, Mickael Coustaty et al.

In the recent past, complex deep neural networks have received huge interest in various document understanding tasks such as document image classification and document retrieval. As many document types have a distinct visual style, learning only visual features with deep CNNs to classify document images have encountered the problem of low inter-class discrimination, and high intra-class structural variations between its categories. In parallel, text-level understanding jointly learned with the corresponding visual properties within a given document image has considerably improved the classification performance in terms of accuracy. In this paper, we design a self-attention-based fusion module that serves as a block in our ensemble trainable network. It allows to simultaneously learn the discriminant features of image and text modalities throughout the training stage. Besides, we encourage mutual learning by transferring the positive knowledge between image and text modalities during the training stage. This constraint is realized by adding a truncated-Kullback-Leibler divergence loss Tr-KLD-Reg as a new regularization term, to the conventional supervised setting. To the best of our knowledge, this is the first time to leverage a mutual learning approach along with a self-attention-based fusion module to perform document image classification. The experimental results illustrate the effectiveness of our approach in terms of accuracy for the single-modal and multi-modal modalities. Thus, the proposed ensemble self-attention-based mutual learning model outperforms the state-of-the-art classification results based on the benchmark RVL-CDIP and Tobacco-3482 datasets.

Joris Voerman, Aurelie Joseph, Mickael Coustaty et al.

One major drawback of state of the art Neural Networks (NN)-based approaches for document classification purposes is the large number of training samples required to obtain an efficient classification. The minimum required number is around one thousand annotated documents for each class. In many cases it is very difficult, if not impossible, to gather this number of samples in real industrial processes. In this paper, we analyse the efficiency of NN-based document classification systems in a sub-optimal training case, based on the situation of a company document stream. We evaluated three different approaches, one based on image content and two on textual content. The evaluation was divided into four parts: a reference case, to assess the performance of the system in the lab; two cases that each simulate a specific difficulty linked to document stream processing; and a realistic case that combined all of these difficulties. The realistic case highlighted the fact that there is a significant drop in the efficiency of NN-Based document classification systems. Although they remain efficient for well represented classes (with an over-fitting of the system for those classes), it is impossible for them to handle appropriately less well represented classes. NN-Based document classification systems need to be adapted to resolve these two problems before they can be considered for use in a company document stream.

Tanmoy Mondal, LE Thi Thuy Trang, Mickaël Coustaty et al.

There have been many work in the literature on generation of various kinds of images such as Hand-Written characters (MNIST dataset), scene images (CIFAR-10 dataset), various objects images (ImageNet dataset), road signboard images (SVHN dataset) etc. Unfortunately, there have been very limited amount of work done in the domain of document image processing. Automatic image generation can lead to the enormous increase of labeled datasets with the help of only limited amount of labeled data. Various kinds of Deep generative models can be primarily divided into two categories. First category is auto-encoder (AE) and the second one is Generative Adversarial Networks (GANs). In this paper, we have evaluated various kinds of AE as well as GANs and have compared their performances on hand-written digits dataset (MNIST) and also on historical hand-written character dataset of Indonesian BALI language. Moreover, these generated characters are recognized by using character recognition tool for calculating the statistical performance of these generated characters with respect to original character images.