The document layout analysis (DLA) aims to decompose document images into high-level semantic areas (i.e., figures, tables, texts, and background). Creating a DLA framework with strong generalization capabilities is a challenge due to document objects are diversity in layout, size, aspect ratio, texture, etc. Many researchers devoted this challenge by synthesizing data to build large training sets. However, the synthetic training data has different styles and erratic quality. Besides, there is a large gap between the source data and the target data. In this paper, we propose an unsupervised cross-domain DLA framework based on document style guidance. We integrated the document quality assessment and the document cross-domain analysis into a unified framework. Our framework is composed of three components, Document Layout Generator (GLD), Document Elements Decorator(GED), and Document Style Discriminator(DSD). The GLD is used to document layout generates, the GED is used to document layout elements fill, and the DSD is used to document quality assessment and cross-domain guidance. First, we apply GLD to predict the positions of the generated document. Then, we design a novel algorithm based on aesthetic guidance to fill the document positions. Finally, we use contrastive learning to evaluate the quality assessment of the document. Besides, we design a new strategy to change the document quality assessment component into a document cross-domain style guide component. Our framework is an unsupervised document layout analysis framework. We have proved through numerous experiments that our proposed method has achieved remarkable performance.
Document layout analysis (DLA) plays an important role in information extraction and document understanding. At present, document layout analysis has reached a milestone achievement, however, document layout analysis of non-Manhattan is still a challenge. In this paper, we propose an image layer modeling method to tackle this challenge. To measure the proposed image layer modeling method, we propose a manually-labeled non-Manhattan layout fine-grained segmentation dataset named FPD. As far as we know, FPD is the first manually-labeled non-Manhattan layout fine-grained segmentation dataset. To effectively extract fine-grained features of documents, we propose an edge embedding network named L-E^3Net. Experimental results prove that our proposed image layer modeling method can better deal with the fine-grained segmented document of the non-Manhattan layout.
Document AI, or Document Intelligence, is a relatively new research topic that refers to the techniques for automatically reading, understanding, and analyzing business documents. It is an important research direction for natural language processing and computer vision. In recent years, the popularity of deep learning technology has greatly advanced the development of Document AI, such as document layout analysis, visual information extraction, document visual question answering, document image classification, etc. This paper briefly reviews some of the representative models, tasks, and benchmark datasets. Furthermore, we also introduce early-stage heuristic rule-based document analysis, statistical machine learning algorithms, and deep learning approaches especially pre-training methods. Finally, we look into future directions for Document AI research.
Documents often contain complex physical structures, which make the Document Layout Analysis (DLA) task challenging. As a pre-processing step for content extraction, DLA has the potential to capture rich information in historical or scientific documents on a large scale. Although many deep-learning-based methods from computer vision have already achieved excellent performance in detecting \emph{Figure} from documents, they are still unsatisfactory in recognizing the \emph{List}, \emph{Table}, \emph{Text} and \emph{Title} category blocks in DLA. This paper proposes a VTLayout model fusing the documents' deep visual, shallow visual, and text features to localize and identify different category blocks. The model mainly includes two stages, and the three feature extractors are built in the second stage. In the first stage, the Cascade Mask R-CNN model is applied directly to localize all category blocks of the documents. In the second stage, the deep visual, shallow visual, and text features are extracted for fusion to identify the category blocks of documents. As a result, we strengthen the classification power of different category blocks based on the existing localization technique. The experimental results show that the identification capability of the VTLayout is superior to the most advanced method of DLA based on the PubLayNet dataset, and the F1 score is as high as 0.9599.
Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dataset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectrum of document types. This first-ever large-scale dataset unleashes the power of deep neural networks for reading order detection. Specifically, our proposed LayoutReader captures the text and layout information for reading order prediction using the seq2seq model. It performs almost perfectly in reading order detection and significantly improves both open-source and commercial OCR engines in ordering text lines in their results in our experiments. We will release the dataset and model at \url{https://aka.ms/layoutreader}.
Document layout analysis (DLA) aims to divide a document image into different types of regions. DLA plays an important role in the document content understanding and information extraction systems. Exploring a method that can use less data for effective training contributes to the development of DLA. We consider a Human-in-the-loop (HITL) collaborative intelligence in the DLA. Our approach was inspired by the fact that the HITL push the model to learn from the unknown problems by adding a small amount of data based on knowledge. The HITL select key samples by using confidence. However, using confidence to find key samples is not suitable for DLA tasks. We propose the Key Samples Selection (KSS) method to find key samples in high-level tasks (semantic segmentation) more accurately through agent collaboration, effectively reducing costs. Once selected, these key samples are passed to human beings for active labeling, then the model will be updated with the labeled samples. Hence, we revisited the learning system from reinforcement learning and designed a sample-based agent update strategy, which effectively improves the agent's ability to accept new samples. It achieves significant improvement results in two benchmarks (DSSE-200 (from 77.1% to 86.3%) and CS-150 (from 88.0% to 95.6%)) by using 10% of labeled data.
Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to automatically synthesize document images based on a given layout. In this work, given a spatial layout (bounding boxes with object categories) as a reference by the user, our proposed DocSynth model learns to generate a set of realistic document images consistent with the defined layout. Also, this framework has been adapted to this work as a superior baseline model for creating synthetic document image datasets for augmenting real data during training for document layout analysis tasks. Different sets of learning objectives have been also used to improve the model performance. Quantitatively, we also compare the generated results of our model with real data using standard evaluation metrics. The results highlight that our model can successfully generate realistic and diverse document images with multiple objects. We also present a comprehensive qualitative analysis summary of the different scopes of synthetic image generation tasks. Lastly, to our knowledge this is the first work of its kind.
Automatically recognizing the layout of handwritten documents is an important step towards useful extraction of information from those documents. The most common application is to feed downstream applications such as automatic text recognition and keyword spotting; however, the recognition of the layout also helps to establish relationships between elements in the document which allows to enrich the information that can be extracted. Most of the modern document layout analysis systems are designed to address only one part of the document layout problem, namely: baseline detection or region segmentation. In contrast, we evaluate the effectiveness of the Mask-RCNN architecture to address the problem of baseline detection and region segmentation in an integrated manner. We present experimental results on two handwritten text datasets and one handwritten music dataset. The analyzed architecture yields promising results, outperforming state-of-the-art techniques in all three datasets.
We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first "tokenize" the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective is to recover the original visual tokens based on the corrupted image patches. After pre-training BEiT, we directly fine-tune the model parameters on downstream tasks by appending task layers upon the pretrained encoder. Experimental results on image classification and semantic segmentation show that our model achieves competitive results with previous pre-training methods. For example, base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%). The code and pretrained models are available at https://aka.ms/beit.
We present document domain randomization (DDR), the first successful transfer of convolutional neural networks (CNNs) trained only on graphically rendered pseudo-paper pages to real-world document segmentation. DDR renders pseudo-document pages by modeling randomized textual and non-textual contents of interest, with user-defined layout and font styles to support joint learning of fine-grained classes. We demonstrate competitive results using our DDR approach to extract nine document classes from the benchmark CS-150 and papers published in two domains, namely annual meetings of Association for Computational Linguistics (ACL) and IEEE Visualization (VIS). We compare DDR to conditions of style mismatch, fewer or more noisy samples that are more easily obtained in the real world. We show that high-fidelity semantic information is not necessary to label semantic classes but style mismatch between train and test can lower model accuracy. Using smaller training samples had a slightly detrimental effect. Finally, network models still achieved high test accuracy when correct labels are diluted towards confusing labels; this behavior hold across several classes.
This paper presents the final results of the ICDAR 2021 Competition on Historical Map Segmentation (MapSeg), encouraging research on a series of historical atlases of Paris, France, drawn at 1/5000 scale between 1894 and 1937. The competition featured three tasks, awarded separately. Task~1 consists in detecting building blocks and was won by the L3IRIS team using a DenseNet-121 network trained in a weakly supervised fashion. This task is evaluated on 3 large images containing hundreds of shapes to detect. Task~2 consists in segmenting map content from the larger map sheet, and was won by the UWB team using a U-Net-like FCN combined with a binarization method to increase detection edge accuracy. Task~3 consists in locating intersection points of geo-referencing lines, and was also won by the UWB team who used a dedicated pipeline combining binarization, line detection with Hough transform, candidate filtering, and template matching for intersection refinement. Tasks~2 and~3 are evaluated on 95 map sheets with complex content. Dataset, evaluation tools and results are available under permissive licensing at \url{https://icdar21-mapseg.github.io/}.
Document layout analysis is crucial for understanding document structures. On this task, vision and semantics of documents, and relations between layout components contribute to the understanding process. Though many works have been proposed to exploit the above information, they show unsatisfactory results. NLP-based methods model layout analysis as a sequence labeling task and show insufficient capabilities in layout modeling. CV-based methods model layout analysis as a detection or segmentation task, but bear limitations of inefficient modality fusion and lack of relation modeling between layout components. To address the above limitations, we propose a unified framework VSR for document layout analysis, combining vision, semantics and relations. VSR supports both NLP-based and CV-based methods. Specifically, we first introduce vision through document image and semantics through text embedding maps. Then, modality-specific visual and semantic features are extracted using a two-stream network, which are adaptively fused to make full use of complementary information. Finally, given component candidates, a relation module based on graph neural network is incorported to model relations between components and output final results. On three popular benchmarks, VSR outperforms previous models by large margins. Code will be released soon.
The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document retrieval. However, it is a challenge to build a DLA system because the training data is very limited and lacks an efficient model. In this paper, we propose an end-to-end united network named Dynamic Residual Fusion Network (DRFN) for the DLA task. Specifically, we design a dynamic residual feature fusion module which can fully utilize low-dimensional information and maintain high-dimensional category information. Besides, to deal with the model overfitting problem that is caused by lacking enough data, we propose the dynamic select mechanism for efficient fine-tuning in limited train data. We experiment with two challenging datasets and demonstrate the effectiveness of the proposed module.
Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents. We propose LayoutLMv2 architecture with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. Specifically, with a two-stream multi-modal Transformer encoder, LayoutLMv2 uses not only the existing masked visual-language modeling task but also the new text-image alignment and text-image matching tasks, which make it better capture the cross-modality interaction in the pre-training stage. Meanwhile, it also integrates a spatial-aware self-attention mechanism into the Transformer architecture so that the model can fully understand the relative positional relationship among different text blocks. Experiment results show that LayoutLMv2 outperforms LayoutLM by a large margin and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including FUNSD (0.7895 $\to$ 0.8420), CORD (0.9493 $\to$ 0.9601), SROIE (0.9524 $\to$ 0.9781), Kleister-NDA (0.8340 $\to$ 0.8520), RVL-CDIP (0.9443 $\to$ 0.9564), and DocVQA (0.7295 $\to$ 0.8672). We made our model and code publicly available at \url{https://aka.ms/layoutlmv2}.
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.
Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption. In this work, we produce a competitive convolution-free transformer by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data. More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.
We present docExtractor, a generic approach for extracting visual elements such as text lines or illustrations from historical documents without requiring any real data annotation. We demonstrate it provides high-quality performances as an off-the-shelf system across a wide variety of datasets and leads to results on par with state-of-the-art when fine-tuned. We argue that the performance obtained without fine-tuning on a specific dataset is critical for applications, in particular in digital humanities, and that the line-level page segmentation we address is the most relevant for a general purpose element extraction engine. We rely on a fast generator of rich synthetic documents and design a fully convolutional network, which we show to generalize better than a detection-based approach. Furthermore, we introduce a new public dataset dubbed IlluHisDoc dedicated to the fine evaluation of illustration segmentation in historical documents.
We present an approach for adapting convolutional neural networks for object recognition and classification to scientific literature layout detection (SLLD), a shared subtask of several information extraction problems. Scientific publications contain multiple types of information sought by researchers in various disciplines, organized into an abstract, bibliography, and sections documenting related work, experimental methods, and results; however, there is no effective way to extract this information due to their diverse layout. In this paper, we present a novel approach to developing an end-to-end learning framework to segment and classify major regions of a scientific document. We consider scientific document layout analysis as an object detection task over digital images, without any additional text features that need to be added into the network during the training process. Our technical objective is to implement transfer learning via fine-tuning of pre-trained networks and thereby demonstrate that this deep learning architecture is suitable for tasks that lack very large document corpora for training ab initio. As part of the experimental test bed for empirical evaluation of this approach, we created a merged multi-corpus data set for scientific publication layout detection tasks. Our results show good improvement with fine-tuning of a pre-trained base network using this merged data set, compared to the baseline convolutional neural network architecture.
We introduce a novel approach for scanned document representation to perform field extraction. It allows the simultaneous encoding of the textual, visual and layout information in a 3-axis tensor used as an input to a segmentation model. We improve the recent Chargrid and Wordgrid \cite{chargrid} models in several ways, first by taking into account the visual modality, then by boosting its robustness in regards to small datasets while keeping the inference time low. Our approach is tested on public and private document-image datasets, showing higher performances compared to the recent state-of-the-art methods.
Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainable deep network, (CDeC-Net) for detecting tables present in the documents. The proposed network consists of a multistage extension of Mask R-CNN with a dual backbone having deformable convolution for detecting tables varying in scale with high detection accuracy at higher IoU threshold. We empirically evaluate CDeC-Net on all the publicly available benchmark datasets - ICDAR-2013, ICDAR-2017, ICDAR-2019,UNLV, Marmot, PubLayNet, and TableBank - with extensive experiments. Our solution has three important properties: (i) a single trained model CDeC-Net{\ddag} performs well across all the popular benchmark datasets; (ii) we report excellent performances across multiple, including higher, thresholds of IoU; (iii) by following the same protocol of the recent papers for each of the benchmarks, we consistently demonstrate the superior quantitative performance. Our code and models will be publicly released for enabling the reproducibility of the results.