Papers by Juan Villanueva
Learning and caricaturing the face space using self-organization and Hebbian learning for face processing
Proceedings 11th International Conference on Image Analysis and Processing
Abstract This paper shows a self-organized system designed to obtain compressed representations o... more Abstract This paper shows a self-organized system designed to obtain compressed representations of instances of a population of visual forms. It is shown how, when applied to face shape information, the system evolves into a prototype of the population and induces ...
Colour normalisation based on background information
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)
This paper proposes an improvement on a well-known colour normalisation by the introduction of so... more This paper proposes an improvement on a well-known colour normalisation by the introduction of some knowledge on background. Comprehensive normalisation gives an invariant representation of the image colour. This invariant representation can be considered a canonical representation whenever image content is preserved and changes are only due to illuminant conditions. One of the steps of the normalisation is based on
Gaze control in a binocular robot systems
1999 7th IEEE International Conference on Emerging Technologies and Factory Automation. Proceedings ETFA '99 (Cat. No.99TH8467)
Page 1. GAZE CONTROL IN A BINOCULAR ROBOT SYSTEMS X. Roca, J. Vitrih, M. Vanrell, JJ Villanueva C... more Page 1. GAZE CONTROL IN A BINOCULAR ROBOT SYSTEMS X. Roca, J. Vitrih, M. Vanrell, JJ Villanueva Computer Vision Center / Dept. ... Solving the prob-lem for each camera the problem of smooth pursuit is also solved. ...
Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
In this paper we introduce a statistic snake that learns and tracks image features by means of st... more In this paper we introduce a statistic snake that learns and tracks image features by means of statistic learning techniques. Using probabilistic principal component analysis a feature description is obtained from a training set of object profiles. In our approach a sound statistical model is introduced to define a likelihood estimate of the grey-level local image profiles together with their local orientation. This likelihood estimate allows to define a probabilistic potential field of the snake where the elastic curve deforms to maximise the overall probability of detecting learned image features. To improve the convergence of snake deformation, we enhance the likelihood map by a physics-based model simulating a dipole-dipole interaction. A new extended local coherent interaction is introduced defined in terms of extended structure tensor of the image to give priority to parallel coherence vectors.
Efficient computation of face shape similarity using distance transform eigendecomposition and valleys
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001
This paper presents a face recognition system based on the use of image ridges and valleys as fac... more This paper presents a face recognition system based on the use of image ridges and valleys as face shape descriptors and a supervised Hausdorff based measure as similarity criteria. The proposed measure is designed to decrease the distance measured between images of the same subject. This measure is approximated using eigendecomposition in order to obtain a computationally efficient recognition method
Fusing Edge Cues to Handle Colour Problems in Image Segmentation
Lecture Notes in Computer Science
Page 1. Fusing Edge Cues to Handle Colour Problems in Image Segmentation I. Huerta1, A. Amato1, J... more Page 1. Fusing Edge Cues to Handle Colour Problems in Image Segmentation I. Huerta1, A. Amato1, J. Gonz`alez2, and JJ Villanueva1 1 Dept. ... LNCS, vol. 1843, pp. 751–767. Springer, Heidelberg (2000) 2. Gonz`alez, J.: Human Sequence Evaluation: the Key-frame Approach. ...
Polarization and Color Techniques in Industrial Inspection, 1999
In this paper we present the results of a preliminary computer vision system to classify the prod... more In this paper we present the results of a preliminary computer vision system to classify the production of a ceramic tile industry. We focus on the classification of a specific type of tiles whose production can be affected by external factors, such as humidity, temperature, origin of clays and pigments. Variations on these uncontrolled factors provoke small differences in the color and the texture of the tiles that force to classify all the production. A constant and non-subjective classification would allow avoiding devolution from customers and unnecessary stock fragmentation. The aim of this work is to simulate the human behavior on this classification task by extracting a set of features from tile images. These features are induced by definitions from experts. To compute them we need to mix color and texture information and to define global and local measures. In this work, we do not seek a general texture-color representation, we only deal with textures formed by non-oriented colored-blobs randomly distributed. New samples are classified using Discriminant Analysis functions derived from known class tile samples. The last part of the paper is devoted to explain the correction of acquired images in order to avoid time and geometry illumination changes.
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
In this paper we introduce a new deformable model, called eigensnake, for segmentation of elongat... more In this paper we introduce a new deformable model, called eigensnake, for segmentation of elongated structures in a probabilistic framework. Instead of snake attraction by specific image features extracted independently of the snake, our eigensnake learns an optimal object description and searches for such image feature in the target image. This is achieved applying principal component analysis on image responses of a bank of gaussian derivative filters. Therefore, attraction by eigensnakes is defined in terms of classification of image features. The potential energy for the snake is defined in terms of likelihood in the feature space and incorporated into a new energy minimising scheme. Hence, the snake deforms to minimise the mahalanobis distance in the feature space. A real application of segmenting and tracking coronary vessels in angiography is considered and the results are very encouraging.
Corresponding IVUS and angiogram image data
Computers in Cardiology 2001. Vol.28 (Cat. No.01CH37287)
The growing appreciation of the pathophysiological and prognostic importance of arterial morpholo... more The growing appreciation of the pathophysiological and prognostic importance of arterial morphology have led to the realization that angiograms are inherently limited in dejning the distribution and extension of coronary wall disease. By Intra Vascular UltraSound (IVUS) physicians have ...
iTrack: Image-based probabilistic tracking of people
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, 2000
Real applications on people tracking are usually based on image heuristics. Real approaches do no... more Real applications on people tracking are usually based on image heuristics. Real approaches do not use to apply recent prediction-estimation theoretical frameworks. These require the definition of complex dynamical and shape object models before the tracking process. We present a probablistic framework that takes profit of these theories adapting them to real applications. The key idea of this work is
Advances in Soft Computing, 2007
In this paper we propose a human detection framework based on an enhanced version of Histogram of... more In this paper we propose a human detection framework based on an enhanced version of Histogram of Oriented Gradients (HOG) features. These feature descriptors are computed with the help of a precalculated histogram of square-blocks. This novel method outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster. Using Adaboost for HOG feature selection and Support Vector Machine as weak classifier, we build up a real-time human classifier with an excellent detection rate.
Locating people in indoor scenes for real applications
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
... Albert Pujol, Felipe Lumbreras, Xavier Varona, Juan Jost Villanueva Computer Vision Center an... more ... Albert Pujol, Felipe Lumbreras, Xavier Varona, Juan Jost Villanueva Computer Vision Center and Departament d&amp;amp;amp;amp;amp;amp;#x27;lnformatica Edifici 0, Universitat Aut6noma de Barcelona 081 93 Cerdanyola ... This paper presents a robust architecture for solving this problem in static images. ...
Lecture Notes in Computer Science
Robust and accurate people tracking is a key task in many promising computer-vision applications.... more Robust and accurate people tracking is a key task in many promising computer-vision applications. One must deal with non-rigid targets in open-world scenarios, whose shape and appearance evolve over time. Targets may interact, causing partial or complete occlusions. This paper improves tracking by means of particle ltering, where occlusions are handled considering the target's predicted trajectories. Model drift is tackled by careful updating, based on the history o ikelihood measures. A colour-based likelihood, computed from histogram similarity, is used. Experiments are carried out using se quences from the CAVIAR database.
Computers in Cardiology 1998. Vol. 25 (Cat. No.98CH36292)
In this paper, we propose a physics-based model to segment and reconstruct coronary vessels from ... more In this paper, we propose a physics-based model to segment and reconstruct coronary vessels from biplane angiograms. We use the snake technique to model the vessel, the snake deforms in space to adjust its projections to the image data. In this way, segmentation and 3 0 reconstruction are unified into the same procedure assuring that only plausible vessel shapes will be detected. The method is general allowing to reconstruct the coronary tree from any angles and distances. The results are encouraging.
Retinal image registration using creases as anatomical landmarks
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
... David Lloret, Joan Serrat, Antonio M. Lopez, Andres Soler, Juan J. Villanueva Computer Vision... more ... David Lloret, Joan Serrat, Antonio M. Lopez, Andres Soler, Juan J. Villanueva Computer Vision Center and Departament d&amp;#x27;Inform ltica, Universitat ... sure the quality of the alignment is the correlation function CT = LXEf f(i!) . g(T(i!», where f and g are the ... [IJ J. Domingo, G. Ayala, A ...
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
Stent implantation for coronary disease treatment is a highly important minimally invasive techni... more Stent implantation for coronary disease treatment is a highly important minimally invasive technique that avoids surgery interventions. In order to assure the success of such an intervention, it is very important to determine the real length of the lesion as exactly as possible. Currently, lesion measures are performed directly from the angiography without considering the system projective parameters or, alternatively, from the 3D reconstruction obtained from a correspondence of points defined by the physicians. In this paper, we present a method for 3D vessel reconstruction from biplane images by means of deformable models. In particular, we study the known shortcoming of point-based 3D vessel reconstruction (no intersection of projective beams) and illustrate that using snakes the reconstruction error is minimal. We validate our method by a computer-generated phantom, a real phantom and coronary vessels.
Lecture Notes in Computer Science, 2005
Keeping track of a target by successive detections may not be feasible, whereas it can be accompl... more Keeping track of a target by successive detections may not be feasible, whereas it can be accomplished by using tracking techniques. Tracking can be addressed by means of particle filtering. We have developed a new algorithm which aims to deal with some particle-filter related problems while coping with expected difficulties. In this paper, we present a novel approach to handling complete occlusions. We focus also on the target-model update conditions, ensuring proper tracking. The proposal has been successfully tested in sequences involving multiple targets, whose dynamics are highly non-linear, moving over clutter.
Lecture Notes in Computer Science, 2006
This work presents two main contributions to achieve robust multiple-target tracking in uncontrol... more This work presents two main contributions to achieve robust multiple-target tracking in uncontrolled scenarios. A novel system which consists on a hierarchical architecture is proposed. Each level is devoted to one of the main tracking functionalities: target detection, low-level tracking, and high-level tasks such as target-appearance representation, or event management. Secondly, tracking performances are enhanced by on-line building and updating multiple appearance models. Successful experimental results are accomplished on sequences with significant illumination changes, grouping, splitting and occlusion events.
Automatic Keyframing of Human Actions for Computer Animation
Lecture Notes in Computer Science, 2003
This paper presents a novel human action model based on key-frames which is suitable for animatio... more This paper presents a novel human action model based on key-frames which is suitable for animation purposes. By defining an action as a sequence of time-ordered body posture configurations, we consider that the most characteristic postures (called key-frames) are enough for modeling such an action. As characteristic postures are found to correspond to low likelihood values, we build a human
<title>Neurofilters: neural networks for image processing</title>
New Image Processing Techniques and Applications: Algorithms, Methods, and Components II, 1997
In this paper, we will study the application of neural networks as filters for image processing t... more In this paper, we will study the application of neural networks as filters for image processing tasks. Also, we develop a methodology to apply the neural networks as image filters. We use this methodology to develop image filters based on neural networks that we called neurofilters. We apply neurofilters to some image processing tasks such as edge detection, image restoration and image segmentation. Finally, we compare the neurofilter results with other traditional image operators.
Uploads
Papers by Juan Villanueva