Abstract: This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this is that it makes difficult for the model to reason jointly about both modalities. To fix this problem we propose a new model that is based on an single attention mechanism that attends to multi-modal features conditioned to the question. The output weights of this attention module over a grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text to the given question. Our experiments demonstrate competitive performance in two standard datasets with a model that is faster than previous methods at inference time. Furthermore, we also provide a novel analysis of the ST-VQA dataset based on a human performance study. Supplementary material, code, and data is made available through this link.

Abstract: This thesis addresses the problem of automatic scene text understanding in unconstrained conditions. In particular, we tackle the tasks of multi-language and arbitrary-oriented text detection, tracking, and script identification in natural scenes.
For this we have developed a set of generic methods that build on top of the basic observation that text has always certain key visual and structural characteristics that are independent of the language or script in which it is written. Text instances in any
language or script are always formed as groups of similar atomic parts, being them either individual characters, small stroke parts, or even whole words in the case of cursive text. This holistic (sumof-parts) and recursive perspective has lead us to explore different variants of the “segmentation and grouping” paradigm of computer vision.
Scene text detection methodologies are usually based in classification of individual regions or patches, using a priory knowledge for a given script or language. Human perception of text, on the other hand, is based on perceptual organization through which
text emerges as a perceptually significant group of atomic objects.
In this thesis, we argue that the text detection problem must be posed as the detection of meaningful groups of regions. We address the problem of text detection in natural scenes from a hierarchical perspective, making explicit use of the recursive nature of text, aiming directly to the detection of region groupings corresponding to text within a hierarchy produced by an agglomerative similarity clustering process over individual regions. We propose an optimal way to construct such an hierarchy introducing a feature space designed to produce text group hypothese with high recall and a novel stopping rule combining a discriminative classifier and a probabilistic measure of group meaningfulness based in perceptual organization. Within this generic framework, we design a text-specific object proposals algorithm that, contrary to existing generic object proposals methods, aims directly to the detection of text regions groupings. For this, we abandon the rigid definition of “what is text” of traditional specialized text detectors, and move towards more fuzzy perspective of grouping-based object proposals methods.
Then, we present a hybrid algorithm for detection and tracking of scene text where the notion of region groupings plays also a central role. By leveraging the structural arrangement of text group components between consecutive frames we can improve
the overall tracking performance of the system.
Finally, since our generic detection framework is inherently designed for multi-language environments, we focus on the problem of script identification in order to build a multi-language end-toend reading system. Facing this problem with state of the art CNN classifiers is not straightforward, as they fail to address a key
characteristic of scene text instances: their extremely variable aspect ratio. Instead of resizing input images to a fixed size as in the typical use of holistic CNN classifiers, we propose a patch-based classification framework in order to preserve discriminative parts of the image that are characteristic of its class. We describe a novel method based on the use of ensembles of conjoined networks to jointly learn discriminative stroke-parts representations and their relative importance in a patch-based classification scheme.

Abstract: Reading text in the wild is gaining attention in the computer vision community. Images captured in the wild are almost always compressed to varying degrees, depending on application context, and this compression introduces artifacts
that distort image content into the captured images. In this paper we investigate the impact these compression artifacts have on text localization and recognition in the wild. We also propose a deep Convolutional Neural Network (CNN) that can eliminate text-specific compression artifacts and which leads to an improvement in text recognition. Experimental results on the ICDAR-Challenge4 dataset demonstrate that compression artifacts have a significant
impact on text localization and recognition and that our approach yields an improvement in both – especially at high compression rates.

Abstract: 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.

Abstract: Despite the latest transcription accuracies reached using deep neural network architectures, handwritten text recognition still remains a challenging problem, mainly because of the large inter-writer style variability. Both augmenting the training set with artificial samples using synthetic fonts, and writer adaptation techniques have been proposed to yield more generic approaches aimed at dodging style unevenness. In this work, we take a step closer to learn style independent features from handwritten word images. We propose a novel method that is able to disentangle the content and style aspects of input images by jointly optimizing a generative process and a handwritten
word recognizer. The generator is aimed at transferring writing style features from one sample to another in an image-to-image translation approach, thus leading to a learned content-centric features that shall be independent to writing style attributes.
Our proposed recognition model is able then to leverage such writer-agnostic features to reach better recognition performances. We advance over prior training strategies and demonstrate with qualitative and quantitative evaluations the performance of both
the generative process and the recognition efficiency in the IAM dataset.