Abstract: The field of visual document understanding has witnessed a rapid growth in emerging challenges and powerful multi-modal strategies. However, they rely on an extensive amount of document data to learn their pretext objectives in a ``pre-train-then-fine-tune'' paradigm and thus, suffer a significant performance drop in real-world online industrial settings. One major reason is the over-reliance on OCR engines to extract local positional information within a document page. Therefore, this hinders the model's generalizability, flexibility and robustness due to the lack of capturing global information within a document image. We introduce TransferDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised fashion using three novel pretext objectives. TransferDoc learns richer semantic concepts by unifying language and visual representations, which enables the production of more transferable models. Besides, two novel downstream tasks have been introduced for a ``closer-to-real'' industrial evaluation scenario where TransferDoc outperforms other state-of-the-art approaches.

Abstract: Document Layout Analysis (DLA) is the process of automatically identifying and categorizing the structural components (e.g. Text, Figure, Table, etc.) within a document to extract meaningful content and establish the page's layout structure. It is a crucial stage in document parsing, contributing to their comprehension. However, traditional DLA approaches often demand a significant volume of labeled training data, and the labor-intensive task of generating high-quality annotated training data poses a substantial challenge. In order to address this challenge, we proposed a semi-supervised setting that aims to perform learning on limited annotated categories by eliminating exhaustive and expensive mask annotations. The proposed setting is expected to be generalizable to novel categories as it learns the underlying positional information through a support set and class information through Co-Occurrence that can be generalized from annotated categories to novel categories. Here, we first extract features from the input image and support set with a shared multi-scale feature acquisition backbone. Then, the extracted feature representation is fed to the transformer encoder as a query. Later on, we utilize a semantic embedding network before the decoder to capture the underlying semantic relationships and similarities between different instances, enabling the model to make accurate predictions or classifications with only a limited amount of labeled data. Extensive experimentation on competitive benchmarks like PRIMA, DocLayNet, and Historical Japanese (HJ) demonstrate that this generalized setup obtains significant performance compared to the conventional supervised approach.

Abstract: Text understanding in scene images has gained plenty of attention in the computer vision community and it is an important task in many applications as text carries semantically rich information about scene content and context. For instance, reading text in a scene can be applied to autonomous driving, scene understanding or assisting visually impaired people. The general aim of scene text understanding is to localize and recognize text in scene images. Text regions are first localized in the original image by a trained detector model and afterwards fed into a recognition module. The tasks of localization and recognition are highly correlated since an inaccurate localization can affect the recognition task.
The main purpose of this thesis is to devise efficient methods for scene text understanding. We investigate how the latest results on deep learning can advance text understanding pipelines. Recently, Fully Convolutional Networks (FCNs) and derived methods have achieved a significant performance on semantic segmentation and pixel level classification tasks. Therefore, we took benefit of the strengths of FCN approaches in order to detect text in natural scenes. In this thesis we have focused on two challenging tasks of scene text understanding which are Text Detection and Word Spotting. For the task of text detection, we have proposed an efficient text proposal technique in scene images. We have considered the Text Proposals method as the baseline which is an approach to reduce the search space of possible text regions in an image. In order to improve the Text Proposals method we combined it with Fully Convolutional Networks to efficiently reduce the number of proposals while maintaining the same level of accuracy and thus gaining a significant speed up. Our experiments demonstrate that this text proposal approach yields significantly higher recall rates than the line based text localization techniques, while also producing better-quality localization. We have also applied this technique on compressed images such as videos from wearable egocentric cameras. For the task of word spotting, we have introduced a novel mid-level word representation method. We have proposed a technique to create and exploit an intermediate representation of images based on text attributes which roughly correspond to character probability maps. Our representation extends the concept of Pyramidal Histogram Of Characters (PHOC) by exploiting Fully Convolutional Networks to derive a pixel-wise mapping of the character distribution within candidate word regions. We call this representation the Soft-PHOC. Furthermore, we show how to use Soft-PHOC descriptors for word spotting tasks through an efficient text line proposal algorithm. To evaluate the detected text, we propose a novel line based evaluation along with the classic bounding box based approach. We test our method on incidental scene text images which comprises real-life scenarios such as urban scenes. The importance of incidental scene text images is due to the complexity of backgrounds, perspective, variety of script and language, short text and little linguistic context. All of these factors together makes the incidental scene text images challenging.

Abstract: This paper presents a new model for the description and recognition of distorted shapes, where the image is represented by a pixel density distribution based on the Blurred Shape Model combined with a non-linear image deformation model. This leads to an adaptive structure able to capture elastic deformations in shapes. This method has been evaluated using thee different datasets where deformations are present, showing the robustness and good performance of the new model. Moreover, we show that incorporating deformation and flexibility, the new model outperforms the BSM approach when classifying shapes with high variability of appearance.

Abstract: The Bag-of-Visual-Words (BoVW) framework has gained popularity among the document image analysis community, specifically as a representation of handwritten words for recognition or spotting purposes. Although in the computer vision field the BoVW method has been greatly improved, most of the approaches in the document image analysis domain still rely on the basic implementation of the BoVW method disregarding such latest refinements. In this paper, we present a review of those improvements and its application to the keyword spotting task. We thoroughly evaluate their impact against a baseline system in the well-known George Washington dataset and compare the obtained results against nine state-of-the-art keyword spotting methods. In addition, we also compare both the baseline and improved systems with the methods presented at the Handwritten Keyword Spotting Competition 2014.