Home | << 1 2 3 4 >> |
Records | |||||
---|---|---|---|---|---|
Author | Fernando Vilariño; Ludmila I. Kuncheva; Petia Radeva | ||||
Title | ROC curves and video analysis optimization in intestinal capsule endoscopy | Type | Journal Article | ||
Year | 2006 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 27 | Issue | 8 | Pages | 875–881 |
Keywords | ROC curves; Classification; Classifiers ensemble; Detection of intestinal contractions; Imbalanced classes; Wireless capsule endoscopy | ||||
Abstract | Wireless capsule endoscopy involves inspection of hours of video material by a highly qualified professional. Time episodes corresponding to intestinal contractions, which are of interest to the physician constitute about 1% of the video. The problem is to label automatically time episodes containing contractions so that only a fraction of the video needs inspection. As the classes of contraction and non-contraction images in the video are largely imbalanced, ROC curves are used to optimize the trade-off between false positive and false negative rates. Classifier ensemble methods and simple classifiers were examined. Our results reinforce the claims from recent literature that classifier ensemble methods specifically designed for imbalanced problems have substantial advantages over simple classifiers and standard classifier ensembles. By using ROC curves with the bagging ensemble method the inspection time can be drastically reduced at the expense of a small fraction of missed contractions. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | 800 | Expedition | Conference | ||
Notes | MILAB;MV;SIAI | Approved | no | ||
Call Number | BCNPCL @ bcnpcl @ VKR2006; IAM @ iam @ VKR2006 | Serial | 647 | ||
Permanent link to this record | |||||
Author | Albert Clapes; Miguel Reyes; Sergio Escalera | ||||
Title | Multi-modal User Identification and Object Recognition Surveillance System | Type | Journal Article | ||
Year | 2013 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 34 | Issue | 7 | Pages | 799-808 |
Keywords | Multi-modal RGB-Depth data analysis; User identification; Object recognition; Intelligent surveillance; Visual features; Statistical learning | ||||
Abstract | We propose an automatic surveillance system for user identification and object recognition based on multi-modal RGB-Depth data analysis. We model a RGBD environment learning a pixel-based background Gaussian distribution. Then, user and object candidate regions are detected and recognized using robust statistical approaches. The system robustly recognizes users and updates the system in an online way, identifying and detecting new actors in the scene. Moreover, segmented objects are described, matched, recognized, and updated online using view-point 3D descriptions, being robust to partial occlusions and local 3D viewpoint rotations. Finally, the system saves the historic of user–object assignments, being specially useful for surveillance scenarios. The system has been evaluated on a novel data set containing different indoor/outdoor scenarios, objects, and users, showing accurate recognition and better performance than standard state-of-the-art approaches. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | HUPBA; 600.046; 605.203;MILAB | Approved | no | ||
Call Number | Admin @ si @ CRE2013 | Serial | 2248 | ||
Permanent link to this record | |||||
Author | A. Pujol; Jordi Vitria; Felipe Lumbreras; Juan J. Villanueva | ||||
Title | Topological principal component analysis for face encoding and recognition | Type | Journal Article | ||
Year | 2001 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 22 | Issue | 6-7 | Pages | 769–776 |
Keywords | |||||
Abstract | IF: 0.552 | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | ADAS;OR;MV | Approved | no | ||
Call Number | ADAS @ adas @ PVL2001 | Serial | 155 | ||
Permanent link to this record | |||||
Author | A. Martinez; Jordi Vitria | ||||
Title | Learning mixture models using a genetic version of the EM algorithm. | Type | Journal Article | ||
Year | 2000 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 21 | Issue | 8 | Pages | 759–769 |
Keywords | |||||
Abstract | |||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | OR;MV | Approved | no | ||
Call Number | BCNPCL @ bcnpcl @ MVi2000 | Serial | 335 | ||
Permanent link to this record | |||||
Author | Jose Antonio Rodriguez; Florent Perronnin; Gemma Sanchez; Josep Llados | ||||
Title | Unsupervised writer adaptation of whole-word HMMs with application to word-spotting | Type | Journal Article | ||
Year | 2010 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 31 | Issue | 8 | Pages | 742–749 |
Keywords | Word-spotting; Handwriting recognition; Writer adaptation; Hidden Markov model; Document analysis | ||||
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. |
||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | DAG | Approved | no | ||
Call Number | DAG @ dag @ RPS2010 | Serial | 1290 | ||
Permanent link to this record | |||||
Author | Miguel Angel Bautista; Sergio Escalera; Xavier Baro; Petia Radeva; Jordi Vitria; Oriol Pujol | ||||
Title | Minimal Design of Error-Correcting Output Codes | Type | Journal Article | ||
Year | 2011 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 33 | Issue | 6 | Pages | 693-702 |
Keywords | Multi-class classification; Error-correcting output codes; Ensemble of classifiers | ||||
Abstract | IF JCR CCIA 1.303 2009 54/103
The classification of large number of object categories is a challenging trend in the pattern recognition field. In literature, this is often addressed using an ensemble of classifiers. In this scope, the Error-correcting output codes framework has demonstrated to be a powerful tool for combining classifiers. However, most state-of-the-art ECOC approaches use a linear or exponential number of classifiers, making the discrimination of a large number of classes unfeasible. In this paper, we explore and propose a minimal design of ECOC in terms of the number of classifiers. Evolutionary computation is used for tuning the parameters of the classifiers and looking for the best minimal ECOC code configuration. The results over several public UCI datasets and different multi-class computer vision problems show that the proposed methodology obtains comparable (even better) results than state-of-the-art ECOC methodologies with far less number of dichotomizers. |
||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 0167-8655 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | MILAB; OR;HuPBA;MV | Approved | no | ||
Call Number | Admin @ si @ BEB2011a | Serial | 1800 | ||
Permanent link to this record | |||||
Author | Oriol Ramos Terrades; Ernest Valveny | ||||
Title | A new use of the ridgelets transform for describing linear singularities in images | Type | Journal Article | ||
Year | 2006 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 27 | Issue | 6 | Pages | 587–596 |
Keywords | |||||
Abstract | |||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | DAG | Approved | no | ||
Call Number | DAG @ dag @ RaV2006a | Serial | 635 | ||
Permanent link to this record | |||||
Author | Miquel Ferrer; Ernest Valveny; F. Serratosa | ||||
Title | Median graph: A new exact algorithm using a distance based on the maximum common subgraph | Type | Journal Article | ||
Year | 2009 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 30 | Issue | 5 | Pages | 579–588 |
Keywords | |||||
Abstract | Median graphs have been presented as a useful tool for capturing the essential information of a set of graphs. Nevertheless, computation of optimal solutions is a very hard problem. In this work we present a new and more efficient optimal algorithm for the median graph computation. With the use of a particular cost function that permits the definition of the graph edit distance in terms of the maximum common subgraph, and a prediction function in the backtracking algorithm, we reduce the size of the search space, avoiding the evaluation of a great amount of states and still obtaining the exact median. We present a set of experiments comparing our new algorithm against the previous existing exact algorithm using synthetic data. In addition, we present the first application of the exact median graph computation to real data and we compare the results against an approximate algorithm based on genetic search. These experimental results show that our algorithm outperforms the previous existing exact algorithm and in addition show the potential applicability of the exact solutions to real problems. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier Science Inc. | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 0167-8655 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | DAG | Approved | no | ||
Call Number | DAG @ dag @ FVS2009a | Serial | 1114 | ||
Permanent link to this record | |||||
Author | Sergio Escalera; Oriol Pujol; Petia Radeva | ||||
Title | Re-coding ECOCs without retraining | Type | Journal Article | ||
Year | 2010 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 31 | Issue | 7 | Pages | 555–562 |
Keywords | |||||
Abstract | A standard way to deal with multi-class categorization problems is by the combination of binary classifiers in a pairwise voting procedure. Recently, this classical approach has been formalized in the Error-Correcting Output Codes (ECOC) framework. In the ECOC framework, the one-versus-one coding demonstrates to achieve higher performance than the rest of coding designs. The binary problems that we train in the one-versus-one strategy are significantly smaller than in the rest of designs, and usually easier to be learnt, taking into account the smaller overlapping between classes. However, a high percentage of the positions coded by zero of the coding matrix, which implies a high sparseness degree, does not codify meta-class membership information. In this paper, we show that using the training data we can redefine without re-training, in a problem-dependent way, the one-versus-one coding matrix so that the new coded information helps the system to increase its generalization capability. Moreover, the new re-coding strategy is generalized to be applied over any binary code. The results over several UCI Machine Learning repository data sets and two real multi-class problems show that performance improvements can be obtained re-coding the classical one-versus-one and Sparse random designs compared to different state-of-the-art ECOC configurations. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | MILAB;HUPBA | Approved | no | ||
Call Number | BCNPCL @ bcnpcl @ EPR2010e | Serial | 1338 | ||
Permanent link to this record | |||||
Author | Fadi Dornaika; Angel Sappa | ||||
Title | Instantaneous 3D motion from image derivatives using the Least Trimmed Square Regression | Type | Journal Article | ||
Year | 2009 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 30 | Issue | 5 | Pages | 535–543 |
Keywords | |||||
Abstract | This paper presents a new technique to the instantaneous 3D motion estimation. The main contributions are as follows. First, we show that the 3D camera or scene velocity can be retrieved from image derivatives only assuming that the scene contains a dominant plane. Second, we propose a new robust algorithm that simultaneously provides the Least Trimmed Square solution and the percentage of inliers-the non-contaminated data. Experiments on both synthetic and real image sequences demonstrated the effectiveness of the developed method. Those experiments show that the new robust approach can outperform classical robust schemes. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier Science Inc. | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 0167-8655 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | ADAS | Approved | no | ||
Call Number | ADAS @ adas @ DoS2009a | Serial | 1115 | ||
Permanent link to this record | |||||
Author | Sergio Escalera; David Masip; Eloi Puertas; Petia Radeva; Oriol Pujol | ||||
Title | Online Error-Correcting Output Codes | Type | Journal Article | ||
Year | 2011 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 32 | Issue | 3 | Pages | 458-467 |
Keywords | |||||
Abstract | IF JCR CCIA 1.303 2009 54/103
This article proposes a general extension of the error correcting output codes framework to the online learning scenario. As a result, the final classifier handles the addition of new classes independently of the base classifier used. In particular, this extension supports the use of both online example incremental and batch classifiers as base learners. The extension of the traditional problem independent codings one-versus-all and one-versus-one is introduced. Furthermore, two new codings are proposed, unbalanced online ECOC and a problem dependent online ECOC. This last online coding technique takes advantage of the problem data for minimizing the number of dichotomizers used in the ECOC framework while preserving a high accuracy. These techniques are validated on an online setting of 11 data sets from UCI database and applied to two real machine vision applications: traffic sign recognition and face recognition. As a result, the online ECOC techniques proposed provide a feasible and robust way for handling new classes using any base classifier. |
||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | North Holland | Editor | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 0167-8655 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | MILAB;OR;HuPBA;MV | Approved | no | ||
Call Number | Admin @ si @ EMP2011 | Serial | 1714 | ||
Permanent link to this record | |||||
Author | A. Sanfeliu; Juan J. Villanueva | ||||
Title | An approach of visual motion analysis | Type | Journal Article | ||
Year | 2005 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 26 | Issue | 3 | Pages | 355–368 |
Keywords | |||||
Abstract | IF: 1.138 | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | Approved | no | |||
Call Number | ISE @ ise @ SaV2005 | Serial | 561 | ||
Permanent link to this record | |||||
Author | Ivet Rafegas; Maria Vanrell; Luis A Alexandre; G. Arias | ||||
Title | Understanding trained CNNs by indexing neuron selectivity | Type | Journal Article | ||
Year | 2020 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 136 | Issue | Pages | 318-325 | |
Keywords | |||||
Abstract | The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these representations are organized. To help understanding these issues, we propose to describe the activity of individual neurons by their Neuron Feature visualization and quantify their inherent selectivity with two specific properties. We explore selectivity indexes for: an image feature (color); and an image label (class membership). Our contribution is a framework to seek or classify neurons by indexing on these selectivity properties. It helps to find color selective neurons, such as a red-mushroom neuron in layer Conv4 or class selective neurons such as dog-face neurons in layer Conv5 in VGG-M, and establishes a methodology to derive other selectivity properties. Indexing on neuron selectivity can statistically draw how features and classes are represented through layers in a moment when the size of trained nets is growing and automatic tools to index neurons can be helpful. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | CIC; 600.087; 600.140; 600.118 | Approved | no | ||
Call Number | Admin @ si @ RVL2019 | Serial | 3310 | ||
Permanent link to this record | |||||
Author | Sergio Escalera; Oriol Pujol; Petia Radeva | ||||
Title | Separability of Ternary Codes for Sparse Designs of Error-Correcting Output Codes | Type | Journal Article | ||
Year | 2009 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 30 | Issue | 3 | Pages | 285–297 |
Keywords | |||||
Abstract | Error Correcting Output Codes (ECOC) represent a successful framework to deal with multi-class categorization problems based on combining binary classifiers. In this paper, we present a new formulation of the ternary ECOC distance and the error-correcting capabilities in the ternary ECOC framework. Based on the new measure, we stress on how to design coding matrices preventing codification ambiguity and propose a new Sparse Random coding matrix with ternary distance maximization. The results on the UCI Repository and in a real speed traffic categorization problem show that when the coding design satisfies the new ternary measures, significant performance improvement is obtained independently of the decoding strategy applied. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | MILAB;HuPBA | Approved | no | ||
Call Number | BCNPCL @ bcnpcl @ EPR2009a | Serial | 1153 | ||
Permanent link to this record | |||||
Author | Lluis Gomez; Ali Furkan Biten; Ruben Tito; Andres Mafla; Marçal Rusiñol; Ernest Valveny; Dimosthenis Karatzas | ||||
Title | Multimodal grid features and cell pointers for scene text visual question answering | Type | Journal Article | ||
Year | 2021 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 150 | Issue | Pages | 242-249 | |
Keywords | |||||
Abstract | This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this is that it makes difficult for the model to reason jointly about both modalities. To fix this problem we propose a new model that is based on an single attention mechanism that attends to multi-modal features conditioned to the question. The output weights of this attention module over a grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text to the given question. Our experiments demonstrate competitive performance in two standard datasets with a model that is faster than previous methods at inference time. Furthermore, we also provide a novel analysis of the ST-VQA dataset based on a human performance study. Supplementary material, code, and data is made available through this link. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | DAG; 600.084; 600.121 | Approved | no | ||
Call Number | Admin @ si @ GBT2021 | Serial | 3620 | ||
Permanent link to this record |