Browsing by Author "Alquézar Mancho, René"
Now showing items 1-20 of 43
-
A discrete labelling approach to attributed graph matching using SIFT features
(2010)
Conference report
Open AccessLocal invariant feature extraction methods are widely used for image-features matching. There exist a number of approaches aimed at the refinement of the matches between image-features. It is a common strategy among these ... -
A new graph matching method for point-set correspondence using the EM algorithm and Softassign
(2012)
Article
Restricted access - publisher's policyFinding correspondences between two point-sets is a common step in many vision applications (e.g., image matching or shape retrieval). We present a graph matching method to solve the point-set correspondence problem, which ... -
A sequential algorithm for feed-forward neural networks with optimal coefficients and interacting frequencies
(2005-10)
Research report
Open AccessAn algorithm for sequential approximation with optimal coefficients and interacting frequencies (SAOCIF) for feed-forward neural networks is presented. SAOCIF combines two key ideas. The first one is the optimization of ... -
Analysis of methods for playing human robot hide-and-seek in a simple real world urban environment
(Springer, 2013)
Conference report
Open AccessThe hide-and-seek game has many interesting aspects for studying cognitive functions in robots and the interactions between mobile robots and humans. Some MOMDP (Mixed Observable Markovian Decision Processes) models and a ... -
Attributed graph matching for image-features association using SIFT descriptors
(Springer, 2010)
Conference report
Open AccessImage-features matching based on SIFT descriptors is subject to the misplacement of certain matches due to the local nature of the SIFT representations. Some well-known outlier rejectors aim to remove those misplaced matches ... -
Augmented regular expressions: a formalism to describe, recognize, and learn a class of context-sensitive languages
(1995-01-01)
Research report
Open AccessIn order to extend the potential of application of the syntactic approach to pattern recognition, the efficient use of models capable of describing context-sensitive structural relationships is needed. Moreover, the ability ... -
Combining neural networks and clustering techniques for object recognition in indoor video sequences
(2006-06)
Research report
Open AccessThis paper presents the results obtained in a real experiment for object recognition in a sequence of images captured by a mobile robot in an indoor environment. Objects are simply represented as an unstructured set of ... -
Comparing error minimized extreme learning machines and support vector sequential feed-forward neural networks
(2010-06)
Research report
Open AccessRecently, error minimized extreme learning machines (EM-ELMs) have been proposed as a simple and efficient approach to build single-hidden-layer feed-forward networks (SLFNs) sequentially. They add random hidden nodes one ... -
Comparing error minimized extreme learning machines and support vector sequential feed-forward neural networks
(2012-01)
Article
Restricted access - publisher's policyRecently, error minimized extreme learning machines (EM-ELMs) have been proposed as a simple and efficient approach to build single-hidden-layer feed-forward networks (SLFNs) sequentially. They add random hidden nodes one ... -
Considering the anchoring problem in robotic intelligent bin picking
(IOS Press, 2018)
Conference report
Open AccessRandom Bin Picking means the selection by a robot of a particular item from a container (or bin) in which there are many items randomly distributed. Generalist robots and the Anchoring Problem should be considered if we ... -
Continuous real time POMCP to find-and-follow people by a humanoid service robot
(Institute of Electrical and Electronics Engineers (IEEE), 2014)
Conference report
Open Access -
Data mining of patients on weaning trials from mechanical ventilation using cluster analysis and neural networks
(2009)
Conference report
Open AccessThe process of weaning from mechanical ventilation is one of the challenges in intensive care. 149 patients under extubation process (T-tube test) were studied: 88 patients with successful trials (group S), 38 patients ... -
Distance-based kernels for dynamical movement primitives
(IOS Press, 2015)
Conference report
Open AccessIn the Anchoring Problem actions and objects must be anchored to symbols; and movement primitives as DMPs seems a good option to describe actions. In the bottom-up approach to anchoring, the recognition of an action is ... -
Experimental assessment of probabilistic integrated object recognition and tracking methods
(Springer Verlag, 2009)
Conference report
Open AccessThis paper presents a comparison of two classifiers that are used as a first step within a probabilistic object recognition and tracking framework called PIORT. This first step is a static recognition module that provides ... -
Exploratory visualization of misclassified GPCRs from their transformed unaligned sequences using manifold learning techniques
(Copicentro Granada, 2014)
Conference report
Open AccessClass C G-protein-coupled receptors (GPCRs) are cell membrane proteins of great relevance to biology and pharmacology. Previous research has revealed an upper boundary on the accuracy that can be achieved in their ... -
Finding class C GPCR subtype-discriminating n-grams through feature selection
(Springer International Publishing, 2014)
Conference report
Open AccessG protein-coupled receptors (GPCRs) are a large and heterogeneous superfamily of receptors that are key cell players for their role as extracellular signal transmitters. Class C GPCRs, in particular, are of great interest ... -
Fuzzy heterogeneous heurons for imprecise classification problems
(1998-06)
Research report
Open AccessIn the classical neuron model, inputs are continuous real-valued quantities. However, in many important domains from the real world, objects are described by a mixture of continuous and discrete variables, usually containing ... -
Fuzzy heterogeneous neural networks for signal forecasting
(Springer, 1998)
Conference report
Open AccessFuzzy heterogeneous neural networks are recently introduced models based on neurons accepting heterogeneous inputs (i.e. mixtures of numerical and non-numerical information possibly with missing data) with either crisp or ... -
Fuzzy heterogeneous neurons for imprecise classification problems
(Wiley, 2000-02)
Article
Open AccessIn the classical neuron model, inputs are continuous real-valued quantities. However, in many important domains from the real world, objects are described by a mixture of continuous and discrete variables, usually containing ... -
Graph matching using SIFT descriptors: an application to pose recovery of a mobile robot
(2010)
Conference report
Open AccessImage-feature matching based on Local Invariant Feature Extraction (LIFE) methods has proven to be successful, and SIFT is one of the most effective. SIFT matching uses only local texture information to compute the ...
