Abstract: Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guiding content that should be employed to tackle a diversity of computer vision tasks such as image retrieval, fine-grained classification, and visual question answering. In this paper, we address the problem of fine-grained classification and image retrieval by leveraging textual information along with visual cues to comprehend the existing intrinsic relation between the two modalities. The novelty of the proposed model consists of the usage of a PHOC descriptor to construct a bag of textual words along with a Fisher Vector Encoding that captures the morphology of text. This approach provides a stronger multimodal representation for this task and as our experiments demonstrate, it achieves state-of-the-art results on two different tasks, fine-grained classification and image retrieval.

Abstract: In this work, we address the task of scene text retrieval: given a text query, the system returns all images containing the queried text. The proposed model uses a single shot CNN architecture that predicts bounding boxes and builds a compact representation of spotted words. In this way, this problem can be modeled as a nearest neighbor search of the textual representation of a query over the outputs of the CNN collected from the totality of an image database. Our experiments demonstrate that the proposed model outperforms previous state-of-the-art, while offering a significant increase in processing speed and unmatched expressiveness with samples never seen at training time. Several experiments to assess the generalization capability of the model are conducted in a multilingual dataset, as well as an application of real-time text spotting in videos.

Abstract: Until recently, most computer vision models remained illiterate, largely ignoring the semantically rich and explicit information contained in scene text. Recent progress in scene text detection and recognition has recently allowed exploring its role in a diverse set of open computer vision problems, e.g. image classification, image-text retrieval, image captioning, and visual question answering to name a few. The explicit semantics of scene text closely requires specific modeling similar to language. However, scene text is a particular signal that has to be interpreted according to a comprehensive perspective that encapsulates all the visual cues in an image. Incorporating this information is a straightforward task for humans, but if we are unfamiliar with a language or scripture, achieving a complete world understanding is impossible (e.a. visiting a foreign country with a different alphabet). Despite the importance of scene text, modeling it requires considering the several ways in which scene text interacts with an image, processing and fusing an additional modality. In this thesis, we mainly focus
on two tasks, scene text-based fine-grained image classification, and cross-modal retrieval. In both studied tasks we identify existing limitations in current approaches and propose plausible solutions. Concretely, in each chapter: i) We define a compact way to embed scene text that generalizes to unseen words at training time while performing in real-time. ii) We incorporate the previously learned scene text embedding to create an image-level descriptor that overcomes optical character recognition (OCR) errors which is well-suited to the fine-grained image classification task. iii) We design a region-level reasoning network that learns the interaction through semantics among salient visual regions and scene text instances. iv) We employ scene text information in image-text matching and introduce the Scene Text Aware Cross-Modal retrieval StacMR task. We gather a dataset that incorporates scene text and design a model suited for the newly studied modality. v) We identify the drawbacks of current retrieval metrics in cross-modal retrieval. An image captioning metric is proposed as a way of better evaluating semantics in retrieved results. Ample experimentation shows that incorporating such semantics into a model yields better semantic results while
requiring significantly less data to converge.

Abstract: Transcriptions of historical documents are a valuable source for extracting labeled handwriting images that can be used for training recognition systems. In this paper, we introduce the Saint Gall database that includes images as well as the transcription of a Latin manuscript from the 9th century written in Carolingian script. Although the available transcription is of high quality for a human reader, the spelling of the words is not accurate when compared with the handwriting image. Hence, the transcription poses several challenges for alignment regarding, e.g., line breaks, abbreviations, and capitalization. We propose an alignment system based on character Hidden Markov Models that can cope with these challenges and efficiently aligns complete document pages. On the Saint Gall database, we demonstrate that a considerable alignment accuracy can be achieved, even with weakly trained character models.

Abstract: Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection.