Abstract: The first competition on music scores that was organized at ICDAR and GREC in 2011 awoke the interest of researchers, who participated in both staff removal and writer identification tasks. In this second edition, we focus on the staff removal task and simulate a real case scenario concerning old and degraded music scores. For this purpose, we have generated a new set of semi-synthetic images using two degradation models that we previously introduced: local noise and 3D distortions. In this extended paper we provide an extended description of the dataset, degradation models, evaluation metrics, the participant’s methods and the obtained results that could not be presented at ICDAR and GREC proceedings due to page limitations.

Abstract: Pedestrian Protection Systems (PPSs) are on-board systems aimed at detecting and tracking people in the surroundings of a vehicle in order to avoid potentially dangerous situations. These systems, together with other Advanced Driver Assistance Systems (ADAS) such as lane departure warning or adaptive cruise control, are one of the most promising ways to improve traffic safety. By the use of computer vision, cameras working either in the visible or infra-red spectra have been demonstrated as a reliable sensor to perform this task. Nevertheless, the variability of human’s appearance, not only in terms of clothing and sizes but also as a result of their dynamic shape, makes pedestrians one of the most complex classes even for computer vision. Moreover, the unstructured changing and unpredictable environment in which such on-board systems must work makes detection a difficult task to be carried out with the demanded robustness. In this brief, the state of the art in PPSs is introduced through the review of the most relevant papers of the last decade. A common computational architecture is presented as a framework to organize each method according to its main contribution. More than 300 papers are referenced, most of them addressing pedestrian detection and others corresponding to the descriptors (features), pedestrian models, and learning machines used. In addition, an overview of topics such as real-time aspects, systems benchmarking and future challenges of this research area are presented.

Abstract: This paper presents an effective unsupervised sparse feature learning algorithm to train deep convolutional networks on hyperspectral images. Deep convolutional hierarchical representations are learned and then used for pixel classification. Features in lower layers present less abstract representations of data, while higher layers represent more abstract and complex characteristics. We successfully illustrate the performance of the extracted representations in a challenging AVIRIS hyperspectral image classification problem, compared to standard dimensionality reduction methods like principal component analysis (PCA) and its kernel counterpart (kPCA). The proposed method largely outperforms the previous state-ofthe-art results on the same experimental setting. Results show that single layer networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels. Regarding the deep architecture, we can conclude that: (1) additional layers in a deep architecture significantly improve the performance w.r.t. single layer variants; (2) the max-pooling step in each layer is mandatory to achieve satisfactory results; and (3) the performance gain w.r.t. the number of layers is upper bounded, since the spatial resolution is reduced at each pooling, resulting in too spatially coarse output features.

Abstract: This manuscript addresses the cross-spectral stereo correspondence problem. It proposes the usage of a dense flow field based representation instead of the original cross-spectral images, which have a low correlation. In this way, working in the flow field space, classical cost functions can be used as similarity measures. Preliminary experimental results on urban environments have been obtained showing the validity of the proposed approach.

Abstract: In this paper, we present a page classification application in a banking workflow. The proposed architecture represents administrative document images by merging visual and textual descriptions. The visual description is based on a hierarchical representation of the pixel intensity distribution. The textual description uses latent semantic analysis to represent document content as a mixture of topics. Several off-the-shelf classifiers and different strategies for combining visual and textual cues have been evaluated. A final step uses an n-gram model of the page stream allowing a finer-grained classification of pages. The proposed method has been tested in a real large-scale environment and we report results on a dataset of 70,000 pages.

Abstract: We present ECOC-DRF, a framework where potential functions for Discriminative Random Fields are formulated as an ensemble of classifiers. We introduce the label trick, a technique to express transitions in the pairwise potential as meta-classes. This allows to independently learn any possible transition between labels without assuming any pre-defined model. The Error Correcting Output Codes matrix is used as ensemble framework for the combination of margin classifiers. We apply ECOC-DRF to a large set of classification problems, covering synthetic, natural and medical images for binary and multi-class cases, outperforming state-of-the art in almost all the experiments.

Abstract: The structure of document images plays a signicant role in document analysis thus considerable eorts have been made towards extracting and understanding document structure, usually in the form of layout analysis approaches. In this paper, we rst employ Distance Transform based MSER (DTMSER) to eciently extract stable document structural elements in terms of a dendrogram of key-regions. Then a fast structural matching method is proposed to query the structure of document (dendrogram) based on a spatial database which facilitates the formulation of advanced spatial queries. The experiments demonstrate a signicant improvement in a document retrieval scenario when compared to the use of typical Bag of Words (BoW) and pyramidal BoW descriptors.

Abstract: The accuracy of object classifiers can significantly drop when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, adapting the classifiers to the scenario in which they must operate is of paramount importance. We present novel domain adaptation (DA) methods for object detection. As proof of concept, we focus on adapting the state-of-the-art deformable part-based model (DPM) for pedestrian detection. We introduce an adaptive structural SVM (A-SSVM) that adapts a pre-learned classifier between different domains. By taking into account the inherent structure in feature space (e.g., the parts in a DPM), we propose a structure-aware A-SSVM (SA-SSVM). Neither A-SSVM nor SA-SSVM needs to revisit the source-domain training data to perform the adaptation. Rather, a low number of target-domain training examples (e.g., pedestrians) are used. To address the scenario where there are no target-domain annotated samples, we propose a self-adaptive DPM based on a self-paced learning (SPL) strategy and a Gaussian Process Regression (GPR). Two types of adaptation tasks are assessed: from both synthetic pedestrians and general persons (PASCAL VOC) to pedestrians imaged from an on-board camera. Results show that our proposals avoid accuracy drops as high as 15 points when comparing adapted and non-adapted detectors.