Nicolas Perez de la Blanca

Nicolas Perez de la Blanca
University of Granada | UGR · Department of Computer Science and Artificial Intelligence

About

109
Publications
6,661
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,085
Citations
Citations since 2017
10 Research Items
457 Citations
2017201820192020202120222023020406080
2017201820192020202120222023020406080
2017201820192020202120222023020406080
2017201820192020202120222023020406080

Publications

Publications (109)
Article
Single Image Super-Resolution (SISR) is one of the low-level computer vision problems that has received increased attention in the last few years. Current approaches are primarily based on harnessing the power of deep learning models and optimization techniques to reverse the degradation model. Owing to its hardness, isotropic blurring or Gaussians...
Preprint
Single Image Super-Resolution (SISR) is one of the low-level computer vision problems that has received increased attention in the last few years. Current approaches are primarily based on harnessing the power of deep learning models and optimization techniques to reverse the degradation model. Owing to its hardness, isotropic blurring or Gaussians...
Article
Full-text available
People identification in video based on the way they walk (i.e., gait) is a relevant task in computer vision using a noninvasive approach. Standard and current approaches typically derive gait signatures from sequences of binary energy maps of subjects extracted from images, but this process introduces a large amount of non-stationary noise, thus c...
Chapter
Mitosis detection in hematoxylin and eosin (H&E) images is prone to error due to the unspecificity of the stain for this purpose. Alternatively, the inmunohistochemistry phospho-histone H3 (PHH3) stain has improved the task with a significant reduction of the false negatives. These facts point out on the interest in combining features from both sta...
Chapter
Mitosis detection in Hematoxylin and Eosin images and its quantification for mm\(^2\) is currently one of the most valuable prognostic indicators for some types of cancer and specifically for the breast cancer. In whole-slide images the main goal is to detect its presence on the full image. This paper makes several contributions to the mitosis dete...
Preprint
Full-text available
People identification in video based on the way they walk (i.e. gait) is a relevant task in computer vision using a non-invasive approach. Standard and current approaches typically derive gait signatures from sequences of binary energy maps of subjects extracted from images, but this process introduces a large amount of non-stationary noise, thus,...
Article
The detection and location of objects concealed under clothing is a very challenging task that has crucial applications in security. In this domain, passive millimeter-wave images (PMMWIs) can be used. However, the quality of the acquired images, and the unknown position, shape, and size of hidden objects render this task difficult. In this paper,...
Article
Passive Millimeter Wave Images (PMMWIs) can be used to detect and localize objects concealed under clothing. Unfortunately, the quality of the acquired images and the unknown position, shape, and size of the hidden objects render these tasks challenging. In this paper we discuss a deep learning approach to this detection/localization problem. The e...
Conference Paper
Full-text available
This work targets people identification in video based on the way they walk (i.e. gait) by using deep learning architectures. We explore the use of convolutional neural networks (CNN) for learning high-level descriptors from low-level motion features (i.e. optical flow components). The low number of training samples for each subject and the use of...
Conference Paper
This work targets people identification in video based on the way they walk (i.e. gait). While classical methods typically derive gait signatures from sequences of binary silhouettes, in this work we explore the use of convolutional neural networks (CNN) for learning high-level descriptors from low-level motion features (i.e. optical flow component...
Article
Full-text available
This work targets people identification in video based on the way they walk (i.e. gait). While classical methods typically derive gait signatures from sequences of binary silhouettes, in this work we explore the use of convolutional neural networks (CNN) for learning high-level descriptors from low-level motion features (i.e. optical flow component...
Article
This paper presents three observation models suitable for particle filter tracking, based on the optical flow of the sequence. Modern optical flow computation techniques can obtain in real time very accurate estimates, so we can use it as a source of evidence for higher level image processing. Our image motion-based models are based, respectively,...
Article
In this paper we utilize Bayesian modeling and inference to learn a softmax classification model which performs Supervised Classification and Active Learning. For p < 1, lp-priors are used to impose sparsity on the adaptive parameters. Using variational inference, all model parameters are estimated and the posterior probabilities of the classes giv...
Article
Human action recognition (HAR) from images is an important and challenging task for many current applications. In this context, designing discriminative action descriptors from simple features is a relevant task. In this paper we show that very good descriptors can be build from simple filter outputs when multilevel architectures and non-linear tra...
Article
Human Interaction Recognition (HIR) in uncontrolled TV video material is a very challenging problem because of the huge intra-class variability of the classes (due to large differences in the way actions are performed, lighting conditions and camera viewpoints, amongst others) as well as the existing small inter-class variability (e.g., the visual...
Article
Human motion recognition - action (HAR) or interaction (HIR) - in real video data is identified as a very challenging task. In the last few years models of increasing complexity have been proposed in order to improve the performance in the task. However, it still remains unclear whether it is the features or the models what deserves the increase in...
Conference Paper
Human Action Recognition (HAR) has centered the interest of much research in the last years. Most of this interest has been focused on recognizing motion behavior from a single person (run, jump, walk, hand-wave, etc). However, Human Interaction Recognition (HIR) focus on those cases where several people participate in the scene but the action is c...
Chapter
Full-text available
In this paper we present an example of a video surveillance application that exploits Multimodal Interactive (MI) technologies. The main objective of the so-called VID-Hum prototype was to develop a cognitive artificial system for both the detection and description of a particular set of human behaviours arising from real-world events. The main pro...
Chapter
A prototype to retrieve videos from non-annotated video databases is proposed. We focus on the problem of retrieving relevant videos from the audiovisual signal when the query is unknown for the system, since it is assumed that most of the available annotations are useless, as it is the case for most of the videos from common users in Internet. The...
Article
This paper addresses the human action recognition task from optical flow. This task is in itself an interesting problem, given the lack of accuracy and noisy characteristics of the optical flow estimation. Optical flow is one of the most popular descriptors characterizing motion, but due to its instability is usually used in combination with parame...
Conference Paper
This paper presents an evaluation of two multilevel architectures in the human action recognition (HAR) task. By combining low level features with multi-layer learning architectures, we infer discriminative semantic features that highly improve the classification performance. This approach eliminates the difficult process of selecting good mid-leve...
Article
This paper presents a multiple model real-time tracking technique for video sequences, based on the mean-shift algorithm. The proposed approach incorporates spatial information from several connected regions into the histogram-based representation model of the target, and enables multiple models to be used to represent the same object. The use of s...
Conference Paper
In this paper we evaluate the use of Restricted Bolzmann Machines (RBM) in the context of learning and recognizing human actions. The features used as basis are binary silhouettes of persons. We test the proposed approach on two datasets of human actions where binary silhouettes are available: ViHASi (synthetic data) and Weizmann (real data). In ad...
Conference Paper
The Product of Hidden Markov Models (PoHMM) is a mixed graphical model defining a probability distribution on a sequence space from the normalized product of several simple Hidden Markov Models (HMMs). Here, we use this model to approach the human action recognition task incorporating mixture-Gaussian output distributions. PoHMM allow us to consid...
Conference Paper
Full-text available
Graphical models have proved to be very efficient models for labeling image data. In this paper, the use of graphical models based on Decomposable Triangulated Graphs are applied for several still image databases landmark localization. We use a recently presented algorithm based on the Branch&Bound methodology, that is able to improve the state of...
Conference Paper
This paper addresses the human action recognition task from optical flow. We develop a non-parametric motion model using only the image region surrounding the actor making the action. For every two consecutive frames, a local motion descriptor is calculated from the optical flow orientation histograms collected from overlapping regions inside the b...
Article
Full-text available
This paper evaluates different Restricted Boltzmann Machines models in unsupervised, semi-supervised and supervised frameworks using information from human actions. After feeding these multilayer models with low level features, we infer high-level discriminating features that highly improve the classification performance. This approach eliminates t...
Conference Paper
Full-text available
Graphical models have proved to be very efficient models for labeling image data. In particular, they have been used to label data samples from human body images. In this paper, a DTG-based graphical model is studied for human-body landmark localization and tracking along the image sequence. Experimental results on human motion databases are shown.
Conference Paper
In this paper we approach the human action recognition task using the Product of Hidden Markov Models (PoHMM). This approach allow us to get large state-space models from the normalized product of several simple HMMs. We compare this mixed graphical model with other directed multi-chain models like Coupled Hidden Markov Model (CHMM) or Factorial Hi...
Conference Paper
Full-text available
Graphical models have proved to be very efficient models for labeling image data. In particular, they have been used to label data samples from human body images. In this paper, the use of graphical models is studied for human-body landmark localization. Here a new algorithm based on the Branch & Bound methodology, improving the state of the art, i...
Conference Paper
This paper presents comparative results of applying different architectures of generative classifiers (HMM, FHMM, CHMM, Multi-Stream HMM, Parallel HMM ) and discriminative classifier as Conditional Random Fields (CRFs) in human action sequence recognition. The models are fed with histogram of very informative features such as contours evolution and...
Conference Paper
Full-text available
In this paper we evaluate the performance of the two most successful state-of-the-art descriptors, applied to the task of visual ob- ject detection and localization in images. In the first experiment we use these descriptors, combined with binary classifiers, to test the pres- ence/absence of object in a target image. In the second experiment, we t...
Conference Paper
This paper describes an experimental study about a robust contour feature (shape-context) for using in action recognition based on continuous hidden Markov models (HMM). We ran different experimental setting using the KTH’s database of actions. The image contours are extracted using a standard algorithm. The shape-context feature vector is build fr...
Conference Paper
Full-text available
This paper presents a new,approach to the problem of si- multaneous location and segmentation of object in images. The main emphasis is done on the information provided by the contour fragments present in the image. Clusters of contour fragments are created in order to represent the labels deflning the difierent parts of the object. An un- ordered...
Conference Paper
Local space-time features can be used to detect and characterize motion events in video. Such features are valid for recognizing motion patterns, by defining a vocabulary of primitive features, and representing each video sequence by means of a histogram, in terms of such vocabulary. In this paper, we propose a supervised vocabulary computation tec...
Conference Paper
The goal of this paper is to study the set of features that is suitable for describing animals in images, and for being able to categorize them in natural scenes. We propose multi-scale features based on Gaussian derivatives functions, that show interesting invariance properties. In order to build an efficient system, we will use classifiers based...
Conference Paper
This paper presents a technique to enable deformable objects to be matched throughout video sequences based on the information provided by multi-scale Gaussian derivative filter banks. We show that this technique is robust enough for viewpoint changes, lighting changes, large motions of the matched object and small changes in rotation and scale. Un...
Conference Paper
The aim of this work is the evaluation of different multi-scale filter banks, mainly based on oriented Gaussian derivatives and Gabor functions, to be used in the generation of robust features for visual object categorization. In order to combine the responses obtained from several spatial scales, we use the biologically inspired HMAX model (Riesen...
Conference Paper
Full-text available
This paper presents a technique to enable deformable regions to be matched using image databases based on the information provided by the dif- ferential invariants of local histograms for the key-region. We shall show how this technique is robust enough to deal with local deformations, viewpoint changes, lighting changes, large motions of the track...
Conference Paper
Full-text available
Using Comaniciu et al.'s approach as a basis, (9), this paper presents a real-time tracking technique in which a multiple target model is used. The use of a multiple model shall enable us to provide the track- ing scheme with a greater robustness for tracking tasks on sequences in which there are changes in the lighting of the tracked object. In or...
Conference Paper
Full-text available
We study the use of optical flow as a characteristic for tracking. We analyze the behavior of three flow-based observation models for particle filter algorithms, and compare the results with those obtained using a well-known, gradient-based, observation model. Although in theory, optical flow could be used directly to displace an object model, in p...
Conference Paper
Full-text available
This paper presents a technique to enable deformable objects to be matched throughout video sequences based on the information provided by the multi-scale local histograms of the images. We shall show that this technique is robust enough for viewpoint changes, lighting changes, large motions of the matched object and small changes in rotation and s...
Article
The skeleton and its associated medial axis give a very compact representation of objects, even in the case of complex shapes and topologies. They are powerful shape descriptors, bridging the gap between low-level and high-level object representations. Surprisingly, skeletons have been used in a relatively small number of applications. This work de...
Conference Paper
Full-text available
This paper proposes an approach to estimate 3D rigid facial motions through a stereo image sequence. The approach uses a disparity space as the main space in order to represent all the 3D information. A robust algorithm based on the RANSAC approach is used to estimate the rigid motions through the image sequence. The disparity map is shown to be a...
Conference Paper
Full-text available
We present two observation models based on optical flow information to track objects using particle filter algorithms. Although, in principle, the optical flow information enables us to know the dis- placement of the objects present in a scene, it cannot be used directly to displace a model since flow estimation techniques lack the necessary precis...
Conference Paper
Full-text available
In this paper, we present an observation model based on the Lucas and Kanade algorithm for computing optical flow, to track objects using particle filter algorithms. Although optical flow information enables us to know the displacement of objects present in a scene, it cannot be used directly to displace an object model since flow calculation techn...
Conference Paper
Full-text available
In this paper, we define an observation model based on optical flow information to track objects using particle filter algorithms. Although the optical flow information enables us to know the displacement of objects present in a scene, it cannot be used directly to displace an object model since flow calculation techniques lack the necessary precis...
Conference Paper
Full-text available
This paper presents a general 2D object characterization and matching scheme based on the information provided by color and shape. We focus on matching objects from generic images with complex scenes. In order to identify the region associated to each object, we use an unsupervised segmentation process based on a hierarchical representation of the...
Conference Paper
Full-text available
In this paper, we present an observation model to track objects using particle filter algorithms based on matching techniques for computing optical flow. Although optical flow information enables us to know the displacement of objects present in a scene, it cannot be used directly to displace an object model since flow calculation techniques lack t...
Conference Paper
Full-text available
In this paper, we present an observation model based on the Lucas and Kanade algorithm for computing optical flow, to track objects using particle filter algorithms. Although optical flow information enables us to know the displacement of objects present in a scene, it cannot be used directly to displace an object model since flow calculation techn...
Conference Paper
Full-text available
In this paper, we present two new observation models based on optical flow information to track objects using particle filter algo- rithms. Although optical flow information enables us to know the dis- placement of objects present in a scene, it cannot be used directly to displace an object model since flow calculation techniques lack the nec- essa...
Conference Paper
Full-text available
This paper proposes a method for representing local temporal deformations of a 3D flexible surface in an orthogonal space from a sequence of stereo images. The approach uses a disparity space as the main space in order to represent all the 3D information. The local motions are estimated removing the rigid motions from the global motion in the dispa...
Conference Paper
The recovering of 3D shape from video sequences has been one of the most important computer vision problems in the last ten years. For the case of rigid scenes, linear and factorization approaches have been developed. However, for non-rigid scenes only factorization methods for parallel projection, based on the Tomasi-Kanade’s factorization method,...
Article
This paper presents a scheme of image retrieval from a database using queries prompted by the colour and the shape of the objects present in different scenes. Of the whole scheme of image retrieval, we will focus attention on the modules that allow feature extraction of the component objects from the scenes and the matching of the objects among the...
Article
Full-text available
In this paper we present a Content-Based Images Retrieval (CBIR) system which uses characteristics of a region occu-pied by a shape and the outer contours of the same. The CBIR system is a two-stage image retrieval system: it first extracts a subset of images which contains those shapes most similar to those contained in the query shape, based on t...
Article
This paper presents an automatic method, based on the deformable template approach, for cell image segmentation under severe noise conditions. We define a new methodology, dividing the process into three parts: (1) obtain evidence from the image about the location of the cells; (2) use this evidence to calculate an elliptical approximation of these...
Conference Paper
Full-text available
The skeleton and its associated medial axis give a very compact representation of objects, even in the case of complex shapes and topologies. They are powerful shape descriptors, bridging the gap between low-level and high-level object representations. Surprisingly, skeletons have been used in a relatively small number of applications. This work de...
Article
In this paper we describe a new approach for 2-D object segmentation using an automatic method applied on images with problems as partial information, overlapping objects, many objects in a single scene, severe noise conditions and locating objects with a very high degree of deformation. We use a physically-based shape model to obtain a deformable...
Article
In this paper we describe a new approach for 2-D object segmentation using an automatic method applied on images with problems as partial information, overlapping objects, many objects in a single scene, severe noise conditions and locating objects with a very high degree of deformation. We use a physically-based shape model to obtain a deformable...
Article
In this paper we intend to characterize boundaries using the Scale-space theory. The aim we try to achieve is the description of a boundary in relation to a subset of points—dominant points—that are obtained from a new multiscale representation of the boundary. Dominant points are characterized by a high curvature value (in the original or smoothed...
Article
This paper shows some combinations of classifiers that achieve high accuracy classifications. Traditionally the maximum likelihood classification is used as an initial classification for a contextual classifier. We show that by using different non-parametric spectral classifiers to obtain the initial classification, we can significatively improve t...
Conference Paper
This paper presents a new approach for 2D object segmentations using an automatic method applied on images with severe noise conditions and locating objects with a very high degree of deformation. We use a physically-based shape model to obtain a deformable template, which is defined on a canonical ortogonal coordinate system. The proposed methodol...
Article
Nearest Neighbor rules are widely used nonparametric classifiers in Pattern Recognition. The main drawbacks of these rules are related to the computational effort required. In that sense, some techniques have been proposed to select a reduced and representative reference set from the original training set. Adaptative learning techniques may be used...
Article
In this paper we show some alternative classifiers to the widely used maximum likelihood (ML) classifier in order to obtain high accuracy classifications. The ML classifier does not provide high accuracy classifications when the training sets are high-overlapping in the representation space due to the shape of the decision boundaries it imposes. In...
Article
Classification of very high dimensional images is of the almost interest in Remote Sensing applications. Storage space, and mainly the computational effort required for classifying this kind of images are the main drawbacks in practice. Moreover, it is well known that a number of spectral classifiers may not be useful-even not valid- in practice fo...
Article
Classification of very high dimensional images is of the almost interest in Remote Sensing applications. Storage space, and mainly the computational effort required for classifying this kind of images are the main drawbacks in practice. Classical spectral classifiers may not be useful-even not valid- in practice to be used for classifying very high...
Article
Classification of high-dimensional images is of the almost interest in Remote Sensing applications. Storage space, and specially the computational effort required for classifying this kind of images are the main drawbacks in practice. Moreover, it is well known that a number of spectral classifiers may not be useful-even not valid- in practice when...
Article
This paper shows some combinations of classifiers that achieve high accuracy classifications. Traditionally it is used the maximum likelihood classification as the initial classification for the contextual correction. We will show that using different non-parametric spectral classifiers to obtain the initial classification we can improve the accura...
Article
Nonparametric nearest neighbor classification and a post-classification contextual correction can be used successfully to classify multispectral images. Accuracy is similar to that of parametric quadratic discriminant classifiers if the training set is well-defined and much better if the training set is not well-defined. Before 1-NNR classification...
Article
Full-text available
In this work, we perform the automatic characterization of spiral and elliptical galaxies by extracting morphological features determining a galaxy. Taking into account that the appearance of spiral arms is enough to characterize the galaxy as belonging to the family of spiral galaxies, it will be possible to reduce the automatic characterization p...
Article
Full-text available
This paper presents a new edge-oriented approach for the problem of the 2-D shape's segmentation. We acomplish the edge detection getting a description of the signal changes in the given image by applying one operator in a proper scale to each of the regions with a homogeneous intensity change model. Once the obtained edges are linked, we have the...
Article
Full-text available
In this paper we present some results for automatic characterization of galaxies from digital images. In a first approach we try to characterize spirals and elliptical galaxies as realizations of MRF with different interaction parameters. In a second approach we attempt the characterization using some points on the galaxy contour that represent the...
Article
Full-text available
This paper presents a new approach for 2D object segmentations using an automatic method applied on images with severe non random noise conditions. Results from biomedical images (cytologies) are presented. The proposed methodology works from the output of an edge detector, which is processed to obtain an approximation of the shape of the object fr...
Article
In this work, we examine simple to complex methods proposed within the Bayesian paradigm to perform image restoration in astronomy. We start by describing the classical conditional and simultaneous autoregressions, then we move on to study how to incorporate smoothness constraints to the classical Richardson-Lucy restoration method and also how to...
Article
In this paper, a new approach to solve the problem of characterizing 2-D biomedical shapes is introduced. Two-dimensional biomedical contours are described through a 'degrees of smoothing' vector in which each component determines the proper degree of detail for representing each curve part isolating a single structure. A segmentation process is de...
Article
This paper introduces a new method for representing cartographic boundaries using autoregressive model parameters. An autoregressive model is presented to model a time series which describes the correlated shape variations determining the overall shape of the boundary. Such time series are obtained using an appropriate nonperiodic sampling sequence...