Marçal Rusiñol

Lei Kang, Pau Riba, Marçal Rusiñol et al.

Handwritten Text Recognition has achieved an impressive performance in public benchmarks. However, due to the high inter- and intra-class variability between handwriting styles, such recognizers need to be trained using huge volumes of manually labeled training data. To alleviate this labor-consuming problem, synthetic data produced with TrueType fonts has been often used in the training loop to gain volume and augment the handwriting style variability. However, there is a significant style bias between synthetic and real data which hinders the improvement of recognition performance. To deal with such limitations, we propose a generative method for handwritten text-line images, which is conditioned on both visual appearance and textual content. Our method is able to produce long text-line samples with diverse handwriting styles. Once properly trained, our method can also be adapted to new target data by only accessing unlabeled text-line images to mimic handwritten styles and produce images with any textual content. Extensive experiments have been done on making use of the generated samples to boost Handwritten Text Recognition performance. Both qualitative and quantitative results demonstrate that the proposed approach outperforms the current state of the art.

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.

Sergi Garcia-Bordils, Dimosthenis Karatzas, Marçal Rusiñol

We introduce the structured scene-text spotting task, which requires a scene-text OCR system to spot text in the wild according to a query regular expression. Contrary to generic scene text OCR, structured scene-text spotting seeks to dynamically condition both scene text detection and recognition on user-provided regular expressions. To tackle this task, we propose the Structured TExt sPotter (STEP), a model that exploits the provided text structure to guide the OCR process. STEP is able to deal with regular expressions that contain spaces and it is not bound to detection at the word-level granularity. Our approach enables accurate zero-shot structured text spotting in a wide variety of real-world reading scenarios and is solely trained on publicly available data. To demonstrate the effectiveness of our approach, we introduce a new challenging test dataset that contains several types of out-of-vocabulary structured text, reflecting important reading applications of fields such as prices, dates, serial numbers, license plates etc. We demonstrate that STEP can provide specialised OCR performance on demand in all tested scenarios.

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.

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.

Lluís Gómez, Ali Furkan Biten, Rubèn Tito et al.

This paper presents a new model for the task of scene text visual question answering, in which questions about a given image can only be answered by reading and understanding scene text that is present in it. The proposed model is based on an attention mechanism that attends to multi-modal features conditioned to the question, allowing it to reason jointly about the textual and visual modalities in the scene. The output weights of this attention module over the grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text the to the given question. Our experiments demonstrate competitive performance in two standard datasets. Furthermore, this paper provides a novel analysis of the ST-VQA dataset based on a human performance study.

Lei Kang, Pau Riba, Marçal Rusiñol et al.

The advent of recurrent neural networks for handwriting recognition marked an important milestone reaching impressive recognition accuracies despite the great variability that we observe across different writing styles. Sequential architectures are a perfect fit to model text lines, not only because of the inherent temporal aspect of text, but also to learn probability distributions over sequences of characters and words. However, using such recurrent paradigms comes at a cost at training stage, since their sequential pipelines prevent parallelization. In this work, we introduce a non-recurrent approach to recognize handwritten text by the use of transformer models. We propose a novel method that bypasses any recurrence. By using multi-head self-attention layers both at the visual and textual stages, we are able to tackle character recognition as well as to learn language-related dependencies of the character sequences to be decoded. Our model is unconstrained to any predefined vocabulary, being able to recognize out-of-vocabulary words, i.e. words that do not appear in the training vocabulary. We significantly advance over prior art and demonstrate that satisfactory recognition accuracies are yielded even in few-shot learning scenarios.

Lei Kang, Pau Riba, Yaxing Wang et al.

Although current image generation methods have reached impressive quality levels, they are still unable to produce plausible yet diverse images of handwritten words. On the contrary, when writing by hand, a great variability is observed across different writers, and even when analyzing words scribbled by the same individual, involuntary variations are conspicuous. In this work, we take a step closer to producing realistic and varied artificially rendered handwritten words. We propose a novel method that is able to produce credible handwritten word images by conditioning the generative process with both calligraphic style features and textual content. Our generator is guided by three complementary learning objectives: to produce realistic images, to imitate a certain handwriting style and to convey a specific textual content. Our model is unconstrained to any predefined vocabulary, being able to render whatever input word. Given a sample writer, it is also able to mimic its calligraphic features in a few-shot setup. We significantly advance over prior art and demonstrate with qualitative, quantitative and human-based evaluations the realistic aspect of our synthetically produced images.

Lei Kang, Pau Riba, Mauricio Villegas et al.

Sequence-to-sequence models have recently become very popular for tackling handwritten word recognition problems. However, how to effectively integrate an external language model into such recognizer is still a challenging problem. The main challenge faced when training a language model is to deal with the language model corpus which is usually different to the one used for training the handwritten word recognition system. Thus, the bias between both word corpora leads to incorrectness on the transcriptions, providing similar or even worse performances on the recognition task. In this work, we introduce Candidate Fusion, a novel way to integrate an external language model to a sequence-to-sequence architecture. Moreover, it provides suggestions from an external language knowledge, as a new input to the sequence-to-sequence recognizer. Hence, Candidate Fusion provides two improvements. On the one hand, the sequence-to-sequence recognizer has the flexibility not only to combine the information from itself and the language model, but also to choose the importance of the information provided by the language model. On the other hand, the external language model has the ability to adapt itself to the training corpus and even learn the most commonly errors produced from the recognizer. Finally, by conducting comprehensive experiments, the Candidate Fusion proves to outperform the state-of-the-art language models for handwritten word recognition tasks.

Lei Kang, Marçal Rusiñol, Alicia Fornés et al.

Handwritten Text Recognition (HTR) is still a challenging problem because it must deal with two important difficulties: the variability among writing styles, and the scarcity of labelled data. To alleviate such problems, synthetic data generation and data augmentation are typically used to train HTR systems. However, training with such data produces encouraging but still inaccurate transcriptions in real words. In this paper, we propose an unsupervised writer adaptation approach that is able to automatically adjust a generic handwritten word recognizer, fully trained with synthetic fonts, towards a new incoming writer. We have experimentally validated our proposal using five different datasets, covering several challenges (i) the document source: modern and historic samples, which may involve paper degradation problems; (ii) different handwriting styles: single and multiple writer collections; and (iii) language, which involves different character combinations. Across these challenging collections, we show that our system is able to maintain its performance, thus, it provides a practical and generic approach to deal with new document collections without requiring any expensive and tedious manual annotation step.

Ali Furkan Biten, Rubèn Tito, Andres Mafla et al.

This paper presents final results of ICDAR 2019 Scene Text Visual Question Answering competition (ST-VQA). ST-VQA introduces an important aspect that is not addressed by any Visual Question Answering system up to date, namely the incorporation of scene text to answer questions asked about an image. The competition introduces a new dataset comprising 23,038 images annotated with 31,791 question/answer pairs where the answer is always grounded on text instances present in the image. The images are taken from 7 different public computer vision datasets, covering a wide range of scenarios. The competition was structured in three tasks of increasing difficulty, that require reading the text in a scene and understanding it in the context of the scene, to correctly answer a given question. A novel evaluation metric is presented, which elegantly assesses both key capabilities expected from an optimal model: text recognition and image understanding. A detailed analysis of results from different participants is showcased, which provides insight into the current capabilities of VQA systems that can read. We firmly believe the dataset proposed in this challenge will be an important milestone to consider towards a path of more robust and general models that can exploit scene text to achieve holistic image understanding.

Raul Gomez, Ali Furkan Biten, Lluis Gomez et al.

This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions. Results on different text domains (scene text, machine printed text and handwritten text) and cross modal results demonstrate that this is feasible, and open different research lines. Furthermore, two architectures for selective style transfer, which means transferring style to only desired image pixels, are proposed. Finally, scene text selective style transfer is evaluated as a data augmentation technique to expand scene text detection datasets, resulting in a boost of text detectors performance. Our implementation of the described models is publicly available.

Ali Furkan Biten, Ruben Tito, Andres Mafla et al.

Current visual question answering datasets do not consider the rich semantic information conveyed by text within an image. In this work, we present a new dataset, ST-VQA, that aims to highlight the importance of exploiting high-level semantic information present in images as textual cues in the VQA process. We use this dataset to define a series of tasks of increasing difficulty for which reading the scene text in the context provided by the visual information is necessary to reason and generate an appropriate answer. We propose a new evaluation metric for these tasks to account both for reasoning errors as well as shortcomings of the text recognition module. In addition we put forward a series of baseline methods, which provide further insight to the newly released dataset, and set the scene for further research.

Ali Furkan Biten, Lluis Gomez, Marçal Rusiñol et al.

Current image captioning systems perform at a merely descriptive level, essentially enumerating the objects in the scene and their relations. Humans, on the contrary, interpret images by integrating several sources of prior knowledge of the world. In this work, we aim to take a step closer to producing captions that offer a plausible interpretation of the scene, by integrating such contextual information into the captioning pipeline. For this we focus on the captioning of images used to illustrate news articles. We propose a novel captioning method that is able to leverage contextual information provided by the text of news articles associated with an image. Our model is able to selectively draw information from the article guided by visual cues, and to dynamically extend the output dictionary to out-of-vocabulary named entities that appear in the context source. Furthermore we introduce `GoodNews', the largest news image captioning dataset in the literature and demonstrate state-of-the-art results.

Yash Patel, Lluis Gomez, Marçal Rusiñol et al.

Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a tremendous amount of human effort and, besides, their annotations are usually limited to discrete sets of popular visual classes that may not be representative of the richer semantics found on large-scale cross-modal retrieval datasets. In this paper, we present a self-supervised cross-modal retrieval framework that leverages as training data the correlations between images and text on the entire set of Wikipedia articles. Our method consists in training a CNN to predict: (1) the semantic context of the article in which an image is more probable to appear as an illustration (global context), and (2) the semantic context of its caption (local context). Our experiments demonstrate that the proposed method is not only capable of learning discriminative visual representations for solving vision tasks like image classification and object detection, but that the learned representations are better for cross-modal retrieval when compared to supervised pre-training of the network on the ImageNet dataset.

Lluís Gómez, Andrés Mafla, Marçal Rusiñol et al.

Textual information found in scene images provides high level semantic information about the image and its context and it can be leveraged for better scene understanding. In this paper we address the problem of scene text retrieval: given a text query, the system must return all images containing the queried text. The novelty of the proposed model consists in the usage of a single shot CNN architecture that predicts at the same time bounding boxes and a compact text representation of the words in them. In this way, the text based image retrieval task can be casted as a simple nearest neighbor search of the query text representation over the outputs of the CNN over the entire image database. Our experiments demonstrate that the proposed architecture outperforms previous state-of-the-art while it offers a significant increase in processing speed.

Yash Patel, Lluis Gomez, Raul Gomez et al.

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community. In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN. Our experiments demonstrate state-of-the-art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or naturally-supervised approaches.

Dimosthenis Karatzas, Lluis Gómez, Anguelos Nicolaou et al.

The ICDAR Robust Reading Competition (RRC), initiated in 2003 and re-established in 2011, has become a de-facto evaluation standard for robust reading systems and algorithms. Concurrent with its second incarnation in 2011, a continuous effort started to develop an on-line framework to facilitate the hosting and management of competitions. This paper outlines the Robust Reading Competition Annotation and Evaluation Platform, the backbone of the competitions. The RRC Annotation and Evaluation Platform is a modular framework, fully accessible through on-line interfaces. It comprises a collection of tools and services for managing all processes involved with defining and evaluating a research task, from dataset definition to annotation management, evaluation specification and results analysis. Although the framework has been designed with robust reading research in mind, many of the provided tools are generic by design. All aspects of the RRC Annotation and Evaluation Framework are available for research use.

Lluis Gomez, Yash Patel, Marçal Rusiñol et al.

End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches.