Abstract: Pattern recognition is the task that aims at distinguishing objects among different classes. When such a task wants to be solved in an automatic way a crucial step is how to formally represent such patterns to the computer. Based on the different representational formalisms, we may distinguish between statistical and structural pattern recognition. The former describes objects as a set of measurements arranged in the form of what is called a feature vector. The latter assumes that relations between parts of the underlying objects need to be explicitly represented and thus it uses relational structures such as graphs for encoding their inherent information. Vector spaces are a very flexible mathematical structure that has allowed to come up with several efficient ways for the analysis of patterns under the form of feature vectors. Nevertheless, such a representation cannot explicitly cope with binary relations between parts of the objects and it is restricted to measure the exact same number of features for each pattern under study regardless of their complexity. Graph-based representations present the contrary situation. They can easily adapt to the inherent complexity of the patterns but introduce a problem of high computational complexity, hindering the design of efficient tools to process and analyse patterns.
Solving this paradox is the main goal of this thesis. The ideal situation for solving pattern recognition problems would be to represent the patterns using relational structures such as graphs, and to be able to use the wealthy repository of data processing tools from the statistical pattern recognition domain. An elegant solution to this problem is to transform the graph domain into a vector domain where any processing algorithm can be applied. In other words, by mapping each graph to a point in a vector space we automatically get access to the rich set of algorithms from the statistical domain to be applied in the graph domain. Such methodology is called graph embedding.
In this thesis we propose to associate feature vectors to graphs in a simple and very efficient way by just putting attention on the labelling information that graphs store. In particular, we count frequencies of node labels and of edges between labels. Although their locality, these features are able to robustly represent structurally global properties of graphs, when considered together in the form of a vector. We initially deal with the case of discrete attributed graphs, where features are easy to compute. The continuous case is tackled as a natural generalization of the discrete one, where rather than counting node and edge labelling instances, we count statistics of some representatives of them. We encounter how the proposed vectorial representations of graphs suffer from high dimensionality and correlation among components and we face these problems by feature selection algorithms. We also explore how the diversity of different embedding representations can be exploited in order to boost the performance of base classifiers in a multiple classifier systems framework. An extensive experimental evaluation finally shows how the methodology we propose can be efficiently computed and compete with other graph matching and embedding methodologies.

Abstract: Perceiving text is crucial to understand semantics of outdoor scenes and hence is a critical requirement to build intelligent systems for driver assistance and self-driving. Most of the existing datasets for text detection and recognition comprise still images and are mostly compiled keeping text in mind. This paper introduces a new ”RoadText-1K” dataset for text in driving videos. The dataset is 20 times larger than the existing largest dataset for text in videos. Our dataset comprises 1000 video clips of driving without any bias towards text and with annotations for text bounding boxes and transcriptions in every frame. State of the art methods for text detection,
recognition and tracking are evaluated on the new dataset and the results signify the challenges in unconstrained driving videos compared to existing datasets. This suggests that RoadText-1K is suited for research and development of reading systems, robust enough to be incorporated into more complex downstream tasks like driver assistance and self-driving. The dataset can be found at http://cvit.iiit.ac.in/research/
projects/cvit-projects/roadtext-1k

Abstract: Pretraining has proven successful in Document Intelligence tasks where deluge of documents are used to pretrain the models only later to be finetuned on downstream tasks. One of the problems of the pretraining approaches is the inconsistent usage of pretraining data with different OCR engines leading to incomparable results between models. In other words, it is not obvious whether the performance gain is coming from diverse usage of amount of data and distinct OCR engines or from the proposed models. To remedy the problem, we make public the OCR annotations for IDL documents using commercial OCR engine given their superior performance over open source OCR models. The contributed dataset (OCR-IDL) has an estimated monetary value over 20K US$. It is our hope that OCR-IDL can be a starting point for future works on Document Intelligence. All of our data and its collection process with the annotations can be found in this https URL.

Abstract: Product graph has been shown as a way for matching subgraphs. This paper reports the extension of the product graph methodology for subgraph matching applied to symbol spotting in graphical documents. Here we focus on the two major limitations of the previous version of the algorithm: (1) spurious nodes and edges in the graph representation and (2) inefficient node and edge attributes. To deal with noisy information of vectorized graphical documents, we consider a dual edge graph representation on the original graph representing the graphical information and the product graph is computed between the dual edge graphs of the pattern graph and the target graph. The dual edge graph with redundant edges is helpful for efficient and tolerating encoding of the structural information of the graphical documents. The adjacency matrix of the product graph locates the pair of similar edges of two operand graphs and exponentiating the adjacency matrix finds similar random walks of greater lengths. Nodes joining similar random walks between two graphs are found by combining different weighted exponentials of adjacency matrices. An experimental investigation reveals that the recall obtained by this approach is quite encouraging.

Abstract: Psychophysical experiments were conducted to assess unique hues on a CRT display for a large sample of colour-normal observers (n 1⁄4 185). These data were then used to evaluate the most commonly used colour appear- ance model, CIECAM02, by transforming the CIEXYZ tris- timulus values of the unique hues to the CIECAM02 colour appearance attributes, lightness, chroma and hue angle. We report two findings: (1) the hue angles derived from our unique hue data are inconsistent with the commonly used Natural Color System hues that are incorporated in the CIECAM02 model. We argue that our predicted unique hue angles (derived from our large dataset) provide a more reliable standard for colour management applications when the precise specification of these salient colours is im- portant. (2) We test hue uniformity for CIECAM02 in all four unique hues and show significant disagreements for all hues, except for unique red which seems to be invariant under lightness changes. Our dataset is useful to improve the CIECAM02 model as it provides reliable data for benchmarking.