Abstract: This chapter describes the most relevant approaches for the analysis of graphical documents. The graphics recognition pipeline can be splitted into three tasks. The low level or lexical task extracts the basic units composing the document. The syntactic level is focused on the structure, i.e., how graphical entities are constructed, and involves the location and classification of the symbols present in the document. The third level is a functional or semantic level, i.e., it models what the graphical symbols do and what they mean in the context where they appear. This chapter covers the lexical level, while the next two chapters are devoted to the syntactic and semantic level, respectively. The main problems reviewed in this chapter are raster-to-vector conversion (vectorization algorithms) and the separation of text and graphics components. The research and industrial communities have provided standard methods achieving reasonable performance levels. Hence, graphics recognition techniques can be considered to be in a mature state from a scientific point of view. Additionally this chapter provides insights on some related problems, namely, the extraction and recognition of dimensions in engineering drawings, and the recognition of hatched and tiled patterns. Both problems are usually associated, even integrated, in the vectorization process.

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: Moving cast shadows are a major concern in today’s performance from broad range of many vision-based surveillance applications because they highly difficult the object classification task. Several shadow detection methods have been reported in the literature during the last years. They are mainly divided into two domains. One usually works with static images, whereas the second one uses image sequences, namely video content. In spite of the fact that both cases can be analogously analyzed, there is a difference in the application field. The first case, shadow detection methods can be exploited in order to obtain additional geometric and semantic cues about shape and position of its casting object (‘shape from shadows’) as well as the localization of the light source. While in the second one, the main purpose is usually change detection, scene matching or surveillance (usually in a background subtraction context). Shadows can in fact modify in a negative way the shape and color of the target object and therefore affect the performance of scene analysis and interpretation in many applications. This chapter wills mainly reviews shadow detection methods as well as their taxonomies related with the second case, thus aiming at those shadows which are associated with moving objects (moving shadows).

Abstract: The importance of logos and trademarks in nowadays society is indisputable, variably seen under a positive light as a valuable service for consumers or a negative one as a catalyst of ever-increasing consumerism. This chapter discusses the technical approaches for enabling machines to work with logos, looking into the latest methodologies for logo detection, localization, representation, recognition, retrieval, and spotting in a variety of media. This analysis is presented in the context of three different applications covering the complete depth and breadth of state of the art techniques. These are trademark retrieval systems, logo recognition in document images, and logo detection and removal in images and videos. This chapter, due to the very nature of logos and trademarks, brings together various facets of document image analysis spanning graphical and textual content, while it links document image analysis to other computer vision domains, especially when it comes to the analysis of real-scene videos and images.

Abstract: Domain adaptation addresses the problem of accuracy drop that a classifier may suffer when the training data (source domain) and the testing data (target domain) are drawn from different distributions. In this work, we focus on domain adaptation for structured SVM (SSVM). We propose a cost-sensitive domain adaptation method for SSVM, namely COSS-SSVM. In particular, during the re-training of an adapted classifier based on target and source data, the idea that we explore consists in introducing a non-zero cost even for correctly classified source domain samples. Eventually, we aim to learn a more targetoriented classifier by not rewarding (zero loss) properly classified source-domain training samples. We assess the effectiveness of COSS-SSVM on multi-category object recognition.

Abstract: The performance of different action-recognition methods using skeleton joint locations have been recently studied by several computer vision researchers. However, the potential improvement in classification through classifier fusion by ensemble-based methods has remained unattended. In this work, we evaluate the performance of an ensemble of five action learning techniques, each performing the recognition task from a different perspective. The underlying rationale of the fusion approach is that different learners employ varying structures of input descriptors/features to be trained. These varying structures cannot be attached and used by a single learner. In addition, combining the outputs of several learners can reduce the risk of an unfortunate selection of a poorly performing learner. This leads to having a more robust and general-applicable framework. Also, we propose two simple, yet effective, action description techniques. In order to improve the recognition performance, a powerful combination strategy is utilized based on the Dempster-Shafer theory, which can effectively make use of diversity of base learners trained on different sources of information. The recognition results of the individual classifiers are compared with those obtained from fusing the classifiers' output, showing advanced performance of the proposed methodology.

Abstract: Recognizing human actions in still images is a challenging problem in computer vision due to significant amount of scale, illumination and pose variation. Given the bounding box of a person both at training and test time, the task is to classify the action associated with each bounding box in an image.
Most state-of-the-art methods use the bag-of-words paradigm for action recognition. The bag-of-words framework employing a dense multi-scale grid sampling strategy is the de facto standard for feature detection. This results in a scale invariant image representation where all the features at multiple-scales are binned in a single histogram. We argue that such a scale invariant
strategy is sub-optimal since it ignores the multi-scale information
available with each bounding box of a person.
This paper investigates alternative approaches to scale coding for action recognition in still images. We encode multi-scale information explicitly in three different histograms for small, medium and large scale visual-words. Our first approach exploits multi-scale information with respect to the image size. In our second approach, we encode multi-scale information relative to the size of the bounding box of a person instance. In each approach, the multi-scale histograms are then concatenated into a single representation for action classification. We validate our approaches on the Willow dataset which contains seven action categories: interacting with computer, photography, playing music,
riding bike, riding horse, running and walking. Our results clearly suggest that the proposed scale coding approaches outperform the conventional scale invariant technique. Moreover, we show that our approach obtains promising results compared to more complex state-of-the-art methods.

Abstract: Nowadays, classifiers play a core role in many computer vision tasks. The underlying assumption for learning classifiers is that the training set and the deployment environment (testing) follow the same probability distribution regarding the features used by the classifiers. However, in practice, there are different reasons that can break this constancy assumption. Accordingly, reusing existing classifiers by adapting them from the previous training environment (source domain) to the new testing one (target domain)
is an approach with increasing acceptance in the computer vision community. In this paper we focus on the domain adaptation of deformable part-based models (DPMs) for object detection. In particular, we focus on a relatively unexplored scenario, i.e. incremental domain adaptation for object detection assuming weak-labeling. Therefore, our algorithm is ready to improve existing source-oriented DPM-based detectors as soon as a little amount of labeled target-domain training data is available, and keeps improving as more of such data arrives in a continuous fashion. For achieving this, we follow a multiple
instance learning (MIL) paradigm that operates in an incremental per-image basis. As proof of concept, we address the challenging scenario of adapting a DPM-based pedestrian detector trained with synthetic pedestrians to operate in real-world scenarios. The obtained results show that our incremental adaptive models obtain equally good accuracy results as the batch learned models, while being more flexible for handling continuously arriving target-domain data.