|
Ali Furkan Biten. (2022). A Bitter-Sweet Symphony on Vision and Language: Bias and World Knowledge (Dimosthenis Karatzas, & Lluis Gomez, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: Vision and Language are broadly regarded as cornerstones of intelligence. Even though language and vision have different aims – language having the purpose of communication, transmission of information and vision having the purpose of constructing mental representations around us to navigate and interact with objects – they cooperate and depend on one another in many tasks we perform effortlessly. This reliance is actively being studied in various Computer Vision tasks, e.g. image captioning, visual question answering, image-sentence retrieval, phrase grounding, just to name a few. All of these tasks share the inherent difficulty of the aligning the two modalities, while being robust to language
priors and various biases existing in the datasets. One of the ultimate goal for vision and language research is to be able to inject world knowledge while getting rid of the biases that come with the datasets. In this thesis, we mainly focus on two vision and language tasks, namely Image Captioning and Scene-Text Visual Question Answering (STVQA).
In both domains, we start by defining a new task that requires the utilization of world knowledge and in both tasks, we find that the models commonly employed are prone to biases that exist in the data. Concretely, we introduce new tasks and discover several problems that impede performance at each level and provide remedies or possible solutions in each chapter: i) We define a new task to move beyond Image Captioning to Image Interpretation that can utilize Named Entities in the form of world knowledge. ii) We study the object hallucination problem in classic Image Captioning systems and develop an architecture-agnostic solution. iii) We define a sub-task of Visual Question Answering that requires reading the text in the image (STVQA), where we highlight the limitations of current models. iv) We propose an architecture for the STVQA task that can point to the answer in the image and show how to combine it with classic VQA models. v) We show how far language can get us in STVQA and discover yet another bias which causes the models to disregard the image while doing Visual Question Answering.
|
|
|
Andres Mafla. (2022). Leveraging Scene Text Information for Image Interpretation (Dimosthenis Karatzas, & Lluis Gomez, Eds.). Ph.D. thesis, IMPRIMA, .
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.
|
|
|
Mohamed Ali Souibgui. (2022). Document Image Enhancement and Recognition in Low Resource Scenarios: Application to Ciphers and Handwritten Text (Alicia Fornes, & Yousri Kessentini, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: In this thesis, we propose different contributions with the goal of enhancing and recognizing historical handwritten document images, especially the ones with rare scripts, such as cipher documents.
In the first part, some effective end-to-end models for Document Image Enhancement (DIE) using deep learning models were presented. First, Generative Adversarial Networks (cGAN) for different tasks (document clean-up, binarization, deblurring, and watermark removal) were explored. Next, we further improve the results by recovering the degraded document images into a clean and readable form by integrating a text recognizer into the cGAN model to promote the generated document image to be more readable. Afterward, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion.
The second part of the thesis addresses Handwritten Text Recognition (HTR) in low resource scenarios, i.e. when only few labeled training data is available. We propose novel methods for recognizing ciphers with rare scripts. First, a few-shot object detection based method was proposed. Then, we incorporate a progressive learning strategy that automatically assignspseudo-labels to a set of unlabeled data to reduce the human labor of annotating few pages while maintaining the good performance of the model. Secondly, a data generation technique based on Bayesian Program Learning (BPL) is proposed to overcome the lack of data in such rare scripts. Thirdly, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE). This latter self-supervised model is designed to tackle two tasks, text recognition and document image enhancement. The proposed model does not exhibit limitations of previous state-of-the-art methods based on contrastive losses, while at the same time, it requires substantially fewer data samples to converge.
In the third part of the thesis, we analyze, from the user perspective, the usage of HTR systems in low resource scenarios. This contrasts with the usual research on HTR, which often focuses on technical aspects only and rarely devotes efforts on implementing software tools for scholars in Humanities.
|
|
|
Utkarsh Porwal, Alicia Fornes, & Faisal Shafait (Eds.). (2022). Frontiers in Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition. 18th International Conference, ICFHR 2022 (Vol. 13639). LNCS. Springer.
|
|
|
Mickael Coustaty, & Alicia Fornes. (2023). Document Analysis and Recognition – ICDAR 2023 Workshops (Vol. 14194). LNCS.
|
|
|
Ruben Perez Tito. (2023). Exploring the role of Text in Visual Question Answering on Natural Scenes and Documents (Ernest Valveny, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: Visual Question Answering (VQA) is the task where given an image and a natural language question, the objective is to generate a natural language answer. At the intersection between computer vision and natural language processing, this task can be seen as a measure of image understanding capabilities, as it requires to reason about objects, actions, colors, positions, the relations between the different elements as well as commonsense reasoning, world knowledge, arithmetic skills and natural language understanding. However, even though the text present in the images conveys important semantically rich information that is explicit and not available in any other form, most VQA methods remained illiterate, largely
ignoring the text despite its potential significance. In this thesis, we set out on a journey to bring reading capabilities to computer vision models applied to the VQA task, creating new datasets and methods that can read, reason and integrate the text with other visual cues in natural scene images and documents.
In Chapter 3, we address the combination of scene text with visual information to fully understand all the nuances of natural scene images. To achieve this objective, we define a new sub-task of VQA that requires reading the text in the image, and highlight the limitations of the current methods. In addition, we propose a new architecture that integrates both modalities and jointly reasons about textual and visual features. In Chapter 5, we shift the domain of VQA with reading capabilities and apply it on scanned industry document images, providing a high-level end-purpose perspective to Document Understanding, which has been
primarily focused on digitizing the document’s contents and extracting key values without considering the ultimate purpose of the extracted information. For this, we create a dataset which requires methods to reason about the unique and challenging elements of documents, such as text, images, tables, graphs and complex layouts, to provide accurate answers in natural language. However, we observed that explicit visual features provide a slight contribution in the overall performance, since the main information is usually conveyed within the text and its position. In consequence, in Chapter 6, we propose VQA on infographic images, seeking for document images with more visually rich elements that require to fully exploit visual information in order to answer the questions. We show the performance gap of
different methods when used over industry scanned and infographic images, and propose a new method that integrates the visual features in early stages, which allows the transformer architecture to exploit the visual features during the self-attention operation. Instead, in Chapter 7, we apply VQA on a big collection of single-page documents, where the methods must find which documents are relevant to answer the question, and provide the answer itself. Finally, in Chapter 8, mimicking real-world application problems where systems must process documents with multiple pages, we address the multipage document visual question answering task. We demonstrate the limitations of existing methods, including models specifically designed to process long sequences. To overcome these limitations, we propose
a hierarchical architecture that can process long documents, answer questions, and provide the index of the page where the information to answer the question is located as an explainability measure.
|
|
|
Agnes Borras. (2009). Contributions to the Content-Based Image Retrieval Using Pictorial Queries (Josep Llados, Ed.). Ph.D. thesis, Ediciones Graficas Rey, Bellaterra.
Abstract: The broad access to digital cameras, personal computers and Internet, has lead to the generation of large volumes of data in digital form. If we want an effective usage of this huge amount of data, we need automatic tools to allow the retrieval of relevant information. Image data is a particular type of information that requires specific techniques of description and indexing. The computer vision field that studies these kind of techniques is called Content-Based Image Retrieval (CBIR). Instead of using text-based descriptions, a system of CBIR deals on properties that are inherent in the images themselves. Hence, the feature-based description provides a universal via of image expression in contrast with the more than 6000 languages spoken in the world.
Nowadays, the CBIR is a dynamic focus of research that has derived in important applications for many professional groups. The potential fields of application can be such diverse as: the medical domain, the crime prevention, the protection of the intel- lectual property, the journalism, the graphic design, the web search, the preservation of cultural heritage, etc.
The definition on the role of the user is a key point in the development of a CBIR application. The user is in charge to formulate the queries from which the images are retrieved. We have centered our attention on the image retrieval techniques that use queries based on pictorial information. We have identified a taxonomy composed by four main query paradigms: query-by-selection, query-by-iconic-composition, query- by-sketch and query-by-paint. Each one of these paradigms allows a different degree of user expressivity. From a simple image selection, to a complete painting of the query, the user takes control of the input in the CBIR system.
Along the chapters of this thesis we have analyzed the influence that each query paradigm imposes in the internal operations of a CBIR system. Moreover, we have proposed a set of contributions that we have exemplified in the context of a final application.
|
|
|
Arnau Baro. (2022). Reading Music Systems: From Deep Optical Music Recognition to Contextual Methods (Alicia Fornes, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: The transcription of sheet music into some machine-readable format can be carried out manually. However, the complexity of music notation inevitably leads to burdensome software for music score editing, which makes the whole process
very time-consuming and prone to errors. Consequently, automatic transcription
systems for musical documents represent interesting tools.
Document analysis is the subject that deals with the extraction and processing
of documents through image and pattern recognition. It is a branch of computer
vision. Taking music scores as source, the field devoted to address this task is
known as Optical Music Recognition (OMR). Typically, an OMR system takes an
image of a music score and automatically extracts its content into some symbolic
structure such as MEI or MusicXML.
In this dissertation, we have investigated different methods for recognizing a
single staff section (e.g. scores for violin, flute, etc.), much in the same way as most text recognition research focuses on recognizing words appearing in a given line image. These methods are based in two different methodologies. On the one hand, we present two methods based on Recurrent Neural Networks, in particular, the
Long Short-Term Memory Neural Network. On the other hand, a method based on Sequence to Sequence models is detailed.
Music context is needed to improve the OMR results, just like language models
and dictionaries help in handwriting recognition. For example, syntactical rules
and grammars could be easily defined to cope with the ambiguities in the rhythm.
In music theory, for example, the time signature defines the amount of beats per
bar unit. Thus, in the second part of this dissertation, different methodologies
have been investigated to improve the OMR recognition. We have explored three
different methods: (a) a graphic tree-structure representation, Dendrograms, that
joins, at each level, its primitives following a set of rules, (b) the incorporation of Language Models to model the probability of a sequence of tokens, and (c) graph neural networks to analyze the music scores to avoid meaningless relationships between music primitives.
Finally, to train all these methodologies, and given the method-specificity of
the datasets in the literature, we have created four different music datasets. Two of them are synthetic with a modern or old handwritten appearance, whereas the
other two are real handwritten scores, being one of them modern and the other
old.
|
|
|
Anjan Dutta. (2014). Inexact Subgraph Matching Applied to Symbol Spotting in Graphical Documents (Josep Llados, & Umapada Pal, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: There is a resurgence in the use of structural approaches in the usual object recognition and retrieval problem. Graph theory, in particular, graph matching plays a relevant role in that. Specifically, the detection of an object (or a part of that) in an image in terms of structural features can be formulated as a subgraph matching. Subgraph matching is a challenging task. Specially due to the presence of outliers most of the graph matching algorithms do not perform well in subgraph matching scenario. Also exact subgraph isomorphism has proven to be an NP-complete problem. So naturally, in graph matching community, there are lot of efforts addressing the problem of subgraph matching within suboptimal bound. Most of them work with approximate algorithms that try to get an inexact solution in estimated way. In addition, usual recognition must cope with distortion. Inexact graph matching consists in finding the best isomorphism under a similarity measure. Theoretically this thesis proposes algorithms for solving subgraph matching in an approximate and inexact way.
We consider the symbol spotting problem on graphical documents or line drawings from application point of view. This is a well known problem in the graphics recognition community. It can be further applied for indexing and classification of documents based on their contents. The structural nature of this kind of documents easily motivates one for giving a graph based representation. So the symbol spotting problem on graphical documents can be considered as a subgraph matching problem. The main challenges in this application domain is the noise and distortions that might come during the usage, digitalization and raster to vector conversion of those documents. Apart from that computer vision nowadays is not any more confined within a limited number of images. So dealing a huge number of images with graph based method is a further challenge.
In this thesis, on one hand, we have worked on efficient and robust graph representation to cope with the noise and distortions coming from documents. On the other hand, we have worked on different graph based methods and framework to solve the subgraph matching problem in a better approximated way, which can also deal with considerable number of images. Firstly, we propose a symbol spotting method by hashing serialized subgraphs. Graph serialization allows to create factorized substructures such as graph paths, which can be organized in hash tables depending on the structural similarities of the serialized subgraphs. The involvement of hashing techniques helps to reduce the search space substantially and speeds up the spotting procedure. Secondly, we introduce contextual similarities based on the walk based propagation on tensor product graph. These contextual similarities involve higher order information and more reliable than pairwise similarities. We use these higher order similarities to formulate subgraph matching as a node and edge selection problem in the tensor product graph. Thirdly, we propose near convex grouping to form near convex region adjacency graph which eliminates the limitations of traditional region adjacency graph representation for graphic recognition. Fourthly, we propose a hierarchical graph representation by simplifying/correcting the structural errors to create a hierarchical graph of the base graph. Later these hierarchical graph structures are matched with some graph matching methods. Apart from that, in this thesis we have provided an overall experimental comparison of all the methods and some of the state-of-the-art methods. Furthermore, some dataset models have also been proposed.
|
|
|
Antonio Clavelli. (2014). A computational model of eye guidance, searching for text in real scene images (Dimosthenis Karatzas, Giuseppe Boccignone, & Josep Llados, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Searching for text objects in real scene images is an open problem and a very active computer vision research area. A large number of methods have been proposed tackling the text search as extension of the ones from the document analysis field or inspired by general purpose object detection methods. However the general problem of object search in real scene images remains an extremely challenging problem due to the huge variability in object appearance. This thesis builds on top of the most recent findings in the visual attention literature presenting a novel computational model of eye guidance aiming to better describe text object search in real scene images.
First are presented the relevant state-of-the-art results from the visual attention literature regarding eye movements and visual search. Relevant models of attention are discussed and integrated with recent observations on the role of top-down constraints and the emerging need for a layered model of attention in which saliency is not the only factor guiding attention. Visual attention is then explained by the interaction of several modulating factors, such as objects, value, plans and saliency. Then we introduce our probabilistic formulation of attention deployment in real scene. The model is based on the rationale that oculomotor control depends on two interacting but distinct processes: an attentional process that assigns value to the sources of information and motor process that flexibly links information with action.
In such framework, the choice of where to look next is task-dependent and oriented to classes of objects embedded within pictures of complex scenes. The dependence on task is taken into account by exploiting the value and the reward of gazing at certain image patches or proto-objects that provide a sparse representation of the scene objects.
In the experimental section the model is tested in laboratory condition, comparing model simulations with data from eye tracking experiments. The comparison is qualitative in terms of observable scan paths and quantitative in terms of statistical similarity of gaze shift amplitude. Experiments are performed using eye tracking data from both a publicly available dataset of face and text and from newly performed eye-tracking experiments on a dataset of street view pictures containing text. The last part of this thesis is dedicated to study the extent to which the proposed model can account for human eye movements in a low constrained setting. We used a mobile eye tracking device and an ad-hoc developed methodology to compare model simulated eye data with the human eye data from mobile eye tracking recordings. Such setting allow to test the model in an incomplete visual information condition, reproducing a close to real-life search task.
|
|
|
Jon Almazan. (2014). Learning to Represent Handwritten Shapes and Words for Matching and Recognition (Ernest Valveny, & Alicia Fornes, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Writing is one of the most important forms of communication and for centuries, handwriting had been the most reliable way to preserve knowledge. However, despite the recent development of printing houses and electronic devices, handwriting is still broadly used for taking notes, doing annotations, or sketching ideas.
Transferring the ability of understanding handwritten text or recognizing handwritten shapes to computers has been the goal of many researches due to its huge importance for many different fields. However, designing good representations to deal with handwritten shapes, e.g. symbols or words, is a very challenging problem due to the large variability of these kinds of shapes. One of the consequences of working with handwritten shapes is that we need representations to be robust, i.e., able to adapt to large intra-class variability. We need representations to be discriminative, i.e., able to learn what are the differences between classes. And, we need representations to be efficient, i.e., able to be rapidly computed and compared. Unfortunately, current techniques of handwritten shape representation for matching and recognition do not fulfill some or all of these requirements.
Through this thesis we focus on the problem of learning to represent handwritten shapes aimed at retrieval and recognition tasks. Concretely, on the first part of the thesis, we focus on the general problem of representing any kind of handwritten shape. We first present a novel shape descriptor based on a deformable grid that deals with large deformations by adapting to the shape and where the cells of the grid can be used to extract different features. Then, we propose to use this descriptor to learn statistical models, based on the Active Appearance Model, that jointly learns the variability in structure and texture of a given class. Then, on the second part, we focus on a concrete application, the problem of representing handwritten words, for the tasks of word spotting, where the goal is to find all instances of a query word in a dataset of images, and recognition. First, we address the segmentation-free problem and propose an unsupervised, sliding-window-based approach that achieves state-of- the-art results in two public datasets. Second, we address the more challenging multi-writer problem, where the variability in words exponentially increases. We describe an approach in which both word images and text strings are embedded in a common vectorial subspace, and where those that represent the same word are close together. This is achieved by a combination of label embedding and attributes learning, and a common subspace regression. This leads to a low-dimensional, unified representation of word images and strings, resulting in a method that allows one to perform either image and text searches, as well as image transcription, in a unified framework. We evaluate our methods on different public datasets of both handwritten documents and natural images showing results comparable or better than the state-of-the-art on spotting and recognition tasks.
|
|
|
David Fernandez. (2014). Contextual Word Spotting in Historical Handwritten Documents (Josep Llados, & Alicia Fornes, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: There are countless collections of historical documents in archives and libraries that contain plenty of valuable information for historians and researchers. The extraction of this information has become a central task among the Document Analysis researches and practitioners.
There is an increasing interest to digital preserve and provide access to these kind of documents. But only the digitalization is not enough for the researchers. The extraction and/or indexation of information of this documents has had an increased interest among researchers. In many cases, and in particular in historical manuscripts, the full transcription of these documents is extremely dicult due the inherent deciencies: poor physical preservation, dierent writing styles, obsolete languages, etc. Word spotting has become a popular an ecient alternative to full transcription. It inherently involves a high level of degradation in the images. The search of words is holistically
formulated as a visual search of a given query shape in a larger image, instead of recognising the input text and searching the query word with an ascii string comparison. But the performance of classical word spotting approaches depend on the degradation level of the images being unacceptable in many cases . In this thesis we have proposed a novel paradigm called contextual word spotting method that uses the contextual/semantic information to achieve acceptable results whereas classical word spotting does not reach. The contextual word spotting framework proposed in this thesis is a segmentation-based word spotting approach, so an ecient word segmentation is needed. Historical handwritten
documents present some common diculties that can increase the diculties the extraction of the words. We have proposed a line segmentation approach that formulates the problem as nding the central part path in the area between two consecutive lines. This is solved as a graph traversal problem. A path nding algorithm is used to nd the optimal path in a graph, previously computed, between the text lines. Once the text lines are extracted, words are localized inside the text lines using a word segmentation technique from the state of the
art. Classical word spotting approaches can be improved using the contextual information of the documents. We have introduced a new framework, oriented to handwritten documents that present a highly structure, to extract information making use of context. The framework is an ecient tool for semi-automatic transcription that uses the contextual information to achieve better results than classical word spotting approaches. The contextual information is
automatically discovered by recognizing repetitive structures and categorizing all the words according to semantic classes. The most frequent words in each semantic cluster are extracted and the same text is used to transcribe all them. The experimental results achieved in this thesis outperform classical word spotting approaches demonstrating the suitability of the proposed ensemble architecture for spotting words in historical handwritten documents using contextual information.
|
|
|
Lluis Pere de las Heras. (2014). Relational Models for Visual Understanding of Graphical Documents. Application to Architectural Drawings. (Gemma Sanchez, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Graphical documents express complex concepts using a visual language. This language consists of a vocabulary (symbols) and a syntax (structural relations between symbols) that articulate a semantic meaning in a certain context. Therefore, the automatic interpretation by computers of these sort of documents entails three main steps: the detection of the symbols, the extraction of the structural relations between these symbols, and the modeling of the knowledge that permits the extraction of the semantics. Dierent domains in graphical documents include: architectural and engineering drawings, maps, owcharts, etc.
Graphics Recognition in particular and Document Image Analysis in general are
born from the industrial need of interpreting a massive amount of digitalized documents after the emergence of the scanner. Although many years have passed, the graphical document understanding problem still seems to be far from being solved. The main reason is that the vast majority of the systems in the literature focus on very specic problems, where the domain of the document dictates the implementation of the interpretation. As a result, it is dicult to reuse these strategies on dierent data and on dierent contexts, hindering thus the natural progress in the eld.
In this thesis, we face the graphical document understanding problem by proposing several relational models at dierent levels that are designed from a generic perspective. Firstly, we introduce three dierent strategies for the detection of symbols. The first method tackles the problem structurally, wherein general knowledge of the domain guides the detection. The second is a statistical method that learns the graphical appearance of the symbols and easily adapts to the big variability of the problem. The third method is a combination of the previous two methods that inherits their respective strengths, i.e. copes the big variability and does not need annotated data. Secondly, we present two relational strategies that tackle the problem of the visual context extraction. The first one is a full bottom up method that heuristically searches in a graph representation the contextual relations between symbols. Contrarily, the second is syntactic method that models probabilistically the structure of the documents. It automatically learns the model, which guides the inference algorithm to encounter the best structural representation for a given input. Finally, we construct a knowledge-based model consisting of an ontological denition of the domain and real data. This model permits to perform contextual reasoning and to detect semantic inconsistencies within the data. We evaluate the suitability of the proposed contributions in the framework of floor plan interpretation. Since there is no standard in the modeling of these documents there exists an enormous notation variability from plan to plan in terms of vocabulary and syntax. Therefore, floor plan interpretation is a relevant task in the graphical document understanding problem. It is also worth to mention that we make freely available all the resources used in this thesis {the data, the tool used to generate the data, and the evaluation scripts{ with the aim of fostering research in the graphical document understanding task.
|
|
|
Hongxing Gao. (2015). Focused Structural Document Image Retrieval in Digital Mailroom Applications (Josep Llados, Dimosthenis Karatzas, & Marçal Rusiñol, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: In this work, we develop a generic framework that is able to handle the document retrieval problem in various scenarios such as searching for full page matches or retrieving the counterparts for specific document areas, focusing on their structural similarity or letting their visual resemblance to play a dominant role. Based on the spatial indexing technique, we propose to search for matches of local key-region pairs carrying both structural and visual information from the collection while a scheme allowing to adjust the relative contribution of structural and visual similarity is presented.
Based on the fact that the structure of documents is tightly linked with the distance among their elements, we firstly introduce an efficient detector named Distance Transform based Maximally Stable Extremal Regions (DTMSER). We illustrate that this detector is able to efficiently extract the structure of a document image as a dendrogram (hierarchical tree) of multi-scale key-regions that roughly correspond to letters, words and paragraphs. We demonstrate that, without benefiting from the structure information, the key-regions extracted by the DTMSER algorithm achieve better results comparing with state-of-the-art methods while much less amount of key-regions are employed.
We subsequently propose a pair-wise Bag of Words (BoW) framework to efficiently embed the explicit structure extracted by the DTMSER algorithm. We represent each document as a list of key-region pairs that correspond to the edges in the dendrogram where inclusion relationship is encoded. By employing those structural key-region pairs as the pooling elements for generating the histogram of features, the proposed method is able to encode the explicit inclusion relations into a BoW representation. The experimental results illustrate that the pair-wise BoW, powered by the embedded structural information, achieves remarkable improvement over the conventional BoW and spatial pyramidal BoW methods.
To handle various retrieval scenarios in one framework, we propose to directly query a series of key-region pairs, carrying both structure and visual information, from the collection. We introduce the spatial indexing techniques to the document retrieval community to speed up the structural relationship computation for key-region pairs. We firstly test the proposed framework in a full page retrieval scenario where structurally similar matches are expected. In this case, the pair-wise querying method achieves notable improvement over the BoW and spatial pyramidal BoW frameworks. Furthermore, we illustrate that the proposed method is also able to handle focused retrieval situations where the queries are defined as a specific interesting partial areas of the images. We examine our method on two types of focused queries: structure-focused and exact queries. The experimental results show that, the proposed generic framework obtains nearly perfect precision on both types of focused queries while it is the first framework able to tackle structure-focused queries, setting a new state of the art in the field.
Besides, we introduce a line verification method to check the spatial consistency among the matched key-region pairs. We propose a computationally efficient version of line verification through a two step implementation. We first compute tentative localizations of the query and subsequently employ them to divide the matched key-region pairs into several groups, then line verification is performed within each group while more precise bounding boxes are computed. We demonstrate that, comparing with the standard approach (based on RANSAC), the line verification proposed generally achieves much higher recall with slight loss on precision on specific queries.
|
|
|
Dena Bazazian. (2018). Fully Convolutional Networks for Text Understanding in Scene Images (Dimosthenis Karatzas, & Andrew Bagdanov, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
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.
|
|