|
|
J. Garcia, J.M. Sanchez, X. Orriols, & X. Binefa. (2000). Chromatic aberration and depth extraction. In 15 th International Conference on Pattern Recognition (Vol. 1, pp. 762–765).
|
|
|
|
A. Martinez, & Jordi Vitria. (2000). Learning mixture models using a genetic version of the EM algorithm. PRL - Pattern Recognition Letters, 21(8), 759–769.
|
|
|
|
Sezer Karaoglu, Jan van Gemert, & Theo Gevers. (2013). Con-text: text detection using background connectivity for fine-grained object classification. In 21ST ACM International Conference on Multimedia (pp. 757–760).
|
|
|
|
Sergi Garcia Bordils, George Tom, Sangeeth Reddy, Minesh Mathew, Marçal Rusiñol, C.V. Jawahar, et al. (2022). Read While You Drive-Multilingual Text Tracking on the Road. In 15th IAPR International workshop on document analysis systems (Vol. 13237, 756–770). LNCS.
Abstract: Visual data obtained during driving scenarios usually contain large amounts of text that conveys semantic information necessary to analyse the urban environment and is integral to the traffic control plan. Yet, research on autonomous driving or driver assistance systems typically ignores this information. To advance research in this direction, we present RoadText-3K, a large driving video dataset with fully annotated text. RoadText-3K is three times bigger than its predecessor and contains data from varied geographical locations, unconstrained driving conditions and multiple languages and scripts. We offer a comprehensive analysis of tracking by detection and detection by tracking methods exploring the limits of state-of-the-art text detection. Finally, we propose a new end-to-end trainable tracking model that yields state-of-the-art results on this challenging dataset. Our experiments demonstrate the complexity and variability of RoadText-3K and establish a new, realistic benchmark for scene text tracking in the wild.
|
|
|
|
Ferran Poveda, Enric Marti, Debora Gil, Francesc Carreras, & Manel Ballester. (2012). Helical Structure of Ventricular Anatomy by Diffusion Tensor Cardiac MR Tractography. JACC - Journal of American College of Cardiology, 5(7), 754–755.
Abstract: It is widely accepted that myocardial fiber architecture plays a critical role in myocardial contractility and relaxation (1). However, there is a lack of consensus about the distribution of the myocardial fibers and their spatial arrangement in the left and right ventricles. An understanding of the cardiac architecture should benefit the ventricular functional assessment, left ventricular reconstructive surgery planning, or resynchronization therapy in heart failure. Researchers have proposed several conceptual models to describe the architecture of the heart, ranging from gross dissection to histological presentation. The cardiac mesh model (2) proposes that the myocytes are arranged longitudinally and radially change their angulation along the myocardial depth. By contrast, the helical ventricular myocardial model states that the ventricular myocardium is a continuous anatomical helical layout of myocardial fibers (1
|
|
|
|
Anjan Dutta, Josep Llados, & Umapada Pal. (2013). A symbol spotting approach in graphical documents by hashing serialized graphs. PR - Pattern Recognition, 46(3), 752–768.
Abstract: In this paper we propose a symbol spotting technique in graphical documents. Graphs are used to represent the documents and a (sub)graph matching technique is used to detect the symbols in them. We propose a graph serialization to reduce the usual computational complexity of graph matching. Serialization of graphs is performed by computing acyclic graph paths between each pair of connected nodes. Graph paths are one-dimensional structures of graphs which are less expensive in terms of computation. At the same time they enable robust localization even in the presence of noise and distortion. Indexing in large graph databases involves a computational burden as well. We propose a graph factorization approach to tackle this problem. Factorization is intended to create a unified indexed structure over the database of graphical documents. Once graph paths are extracted, the entire database of graphical documents is indexed in hash tables by locality sensitive hashing (LSH) of shape descriptors of the paths. The hashing data structure aims to execute an approximate k-NN search in a sub-linear time. We have performed detailed experiments with various datasets of line drawings and compared our method with the state-of-the-art works. The results demonstrate the effectiveness and efficiency of our technique.
Keywords: Symbol spotting; Graphics recognition; Graph matching; Graph serialization; Graph factorization; Graph paths; Hashing
|
|
|
|
Jose Carlos Rubio, Joan Serrat, & Antonio Lopez. (2012). Unsupervised co-segmentation through region matching. In 25th IEEE Conference on Computer Vision and Pattern Recognition (pp. 749–756). IEEE Xplore.
Abstract: Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiple-scale multiple-image generative model, which jointly estimates the foreground and background appearance distributions from several images, in a non-supervised manner. In contrast to other co-segmentation methods, our approach does not require the images to have similar foregrounds and different backgrounds to function properly. Region matching is applied to exploit inter-image information by establishing correspondences between the common objects that appear in the scene. Moreover, computing many-to-many associations of regions allow further applications, like recognition of object parts across images. We report results on iCoseg, a challenging dataset that presents extreme variability in camera viewpoint, illumination and object deformations and poses. We also show that our method is robust against large intra-class variability in the MSRC database.
|
|
|
|
Alicia Fornes, & Gemma Sanchez. (2014). Analysis and Recognition of Music Scores. In D. Doermann, & K. Tombre (Eds.), Handbook of Document Image Processing and Recognition (Vol. E, pp. 749–774). Springer London.
Abstract: The analysis and recognition of music scores has attracted the interest of researchers for decades. Optical Music Recognition (OMR) is a classical research field of Document Image Analysis and Recognition (DIAR), whose aim is to extract information from music scores. Music scores contain both graphical and textual information, and for this reason, techniques are closely related to graphics recognition and text recognition. Since music scores use a particular diagrammatic notation that follow the rules of music theory, many approaches make use of context information to guide the recognition and solve ambiguities. This chapter overviews the main Optical Music Recognition (OMR) approaches. Firstly, the different methods are grouped according to the OMR stages, namely, staff removal, music symbol recognition, and syntactical analysis. Secondly, specific approaches for old and handwritten music scores are reviewed. Finally, online approaches and commercial systems are also commented.
|
|
|
|
Mehdi Mirza-Mohammadi, Sergio Escalera, & Petia Radeva. (2009). Contextual-Guided Bag-of-Visual-Words Model for Multi-class Object Categorization. In 13th International Conference on Computer Analysis of Images and Patterns (Vol. 5702, 748–756). LNCS. Springer Berlin Heidelberg.
Abstract: Bag-of-words model (BOW) is inspired by the text classification problem, where a document is represented by an unsorted set of contained words. Analogously, in the object categorization problem, an image is represented by an unsorted set of discrete visual words (BOVW). In these models, relations among visual words are performed after dictionary construction. However, close object regions can have far descriptions in the feature space, being grouped as different visual words. In this paper, we present a method for considering geometrical information of visual words in the dictionary construction step. Object interest regions are obtained by means of the Harris-Affine detector and then described using the SIFT descriptor. Afterward, a contextual-space and a feature-space are defined, and a merging process is used to fuse feature words based on their proximity in the contextual-space. Moreover, we use the Error Correcting Output Codes framework to learn the new dictionary in order to perform multi-class classification. Results show significant classification improvements when spatial information is taken into account in the dictionary construction step.
|
|
|
|
Angel Sappa, David Geronimo, Fadi Dornaika, & Antonio Lopez. (2006). On-board camera extrinsic parameter estimation. EL - Electronics Letters, 42(13), 745–746.
Abstract: An efficient technique for real-time estimation of camera extrinsic parameters is presented. It is intended to be used on on-board vision systems for driving assistance applications. The proposed technique is based on the use of a commercial stereo vision system that does not need any visual feature extraction.
|
|
|
|
Marc Oliu, Javier Selva, & Sergio Escalera. (2018). Folded Recurrent Neural Networks for Future Video Prediction. In 15th European Conference on Computer Vision (Vol. 11218, pp. 745–761). LNCS.
Abstract: Future video prediction is an ill-posed Computer Vision problem that recently received much attention. Its main challenges are the high variability in video content, the propagation of errors through time, and the non-specificity of the future frames: given a sequence of past frames there is a continuous distribution of possible futures. This work introduces bijective Gated Recurrent Units, a double mapping between the input and output of a GRU layer. This allows for recurrent auto-encoders with state sharing between encoder and decoder, stratifying the sequence representation and helping to prevent capacity problems. We show how with this topology only the encoder or decoder needs to be applied for input encoding and prediction, respectively. This reduces the computational cost and avoids re-encoding the predictions when generating a sequence of frames, mitigating the propagation of errors. Furthermore, it is possible to remove layers from an already trained model, giving an insight to the role performed by each layer and making the model more explainable. We evaluate our approach on three video datasets, outperforming state of the art prediction results on MMNIST and UCF101, and obtaining competitive results on KTH with 2 and 3 times less memory usage and computational cost than the best scored approach.
|
|
|
|
Jose Antonio Rodriguez, Florent Perronnin, Gemma Sanchez, & Josep Llados. (2010). Unsupervised writer adaptation of whole-word HMMs with application to word-spotting. PRL - Pattern Recognition Letters, 31(8), 742–749.
Abstract: In this paper we propose a novel approach for writer adaptation in a handwritten word-spotting task. The method exploits the fact that the semi-continuous hidden Markov model separates the word model parameters into (i) a codebook of shapes and (ii) a set of word-specific parameters.
Our main contribution is to employ this property to derive writer-specific word models by statistically adapting an initial universal codebook to each document. This process is unsupervised and does not even require the appearance of the keyword(s) in the searched document. Experimental results show an increase in performance when this adaptation technique is applied. To the best of our knowledge, this is the first work dealing with adaptation for word-spotting. The preliminary version of this paper obtained an IBM Best Student Paper Award at the 19th International Conference on Pattern Recognition.
Keywords: Word-spotting; Handwriting recognition; Writer adaptation; Hidden Markov model; Document analysis
|
|
|
|
Xavier Otazu, Maria Vanrell, & C. Alejandro Parraga. (2008). Multiresolution Wavelet Framework Models Brightness Induction Effects. VR - Vision Research, 733–751.
|
|
|
|
Jaume Garcia, Debora Gil, Luis Badiella, Aura Hernandez-Sabate, Francesc Carreras, Sandra Pujades, et al. (2010). A Normalized Framework for the Design of Feature Spaces Assessing the Left Ventricular Function. TMI - IEEE Transactions on Medical Imaging, 29(3), 733–745.
Abstract: A through description of the left ventricle functionality requires combining complementary regional scores. A main limitation is the lack of multiparametric normality models oriented to the assessment of regional wall motion abnormalities (RWMA). This paper covers two main topics involved in RWMA assessment. We propose a general framework allowing the fusion and comparison across subjects of different regional scores. Our framework is used to explore which combination of regional scores (including 2-D motion and strains) is better suited for RWMA detection. Our statistical analysis indicates that for a proper (within interobserver variability) identification of RWMA, models should consider motion and extreme strains.
|
|
|
|
Bogdan Raducanu, & Fadi Dornaika. (2009). Natural Facial Expression Recognition Using Dynamic and Static Schemes. In 5th International Symposium on Visual Computing (Vol. 5875, 730–739). LNCS. Springer Berlin Heidelberg.
Abstract: Affective computing is at the core of a new paradigm in HCI and AI represented by human-centered computing. Within this paradigm, it is expected that machines will be enabled with perceiving capabilities, making them aware about users’ affective state. The current paper addresses the problem of facial expression recognition from monocular videos sequences. We propose a dynamic facial expression recognition scheme, which is proven to be very efficient. Furthermore, it is conveniently compared with several static-based systems adopting different magnitude of facial expression. We provide evaluations of performance using Linear Discriminant Analysis (LDA), Non parametric Discriminant Analysis (NDA), and Support Vector Machines (SVM). We also provide performance evaluations using arbitrary test video sequences.
|
|
