Mario Hernández

Face recognition using independent component analysis and support vector machines

Support vector machines (SVM) and independent component analysis (ICA) are two powerful and relatively recent techniques. SVMs are classifiers which have demonstrated high generalization capabilities in many different tasks, including the object recognition problem. ICA is a feature extraction technique which can be considered a generalization of principal component analysis (PCA). ICA has been mainly used on the problem of blind signal separation. In this paper we combine these two techniques for the face recognition problem. Experiments were made on two different face databases, achieving very high recognition rates. As the results using the combination PCA/SVM were not very far from those obtained with ICA/SVM, our experiments suggest that SVMs are relatively insensitive to the representation space. Thus as the training time for ICA is much larger than that of PCA, this result indicates that the best practical combination is PCA with SVM.

Face Recognition Using Independent Component Analysis and Support Vector Machines

Support Vector Machines (SVM) and Independent Component Analysis (ICA) are two powerful and relatively recent techniques. SVMs are classifiers which have demonstrated high generalization capabilities in many different tasks, including the object recognition problem. ICA is a feature extraction technique which can be considered a generalization of Principal Component Analysis (PCA). ICA has been mainly used on the problem of blind signal separation. In this paper we combine these two techniques for the face recognition problem. Experiments were made on two different face databases, achieving very high recognition rates. As the results using the combination PCA/SVM were not very far from those obtained with ICA/SVM, our experiments suggest that SVMs are relatively insensitive to the representation space. Thus as the training time for ICA is much larger than that of PCA, this result indicates that the best practical combination is PCA with SVM.

DESEO: An Active Vision System for Detection, Tracking and Recognition

In this paper, a basic conceptual architecture aimed at the design of Computer Vision System is qualitatively described. The proposed architecture addresses the design of vision systems in a modular fashion using modules with three distinct units or components: a processing network or diagnostics unit, a control unit and a communications unit. The control of the system at the modules level is designed based on a Discrete Events Model. This basic methodology has been used to design a real-time active vision system for detection, tracking and recognition of people. It is made up of three functional modules aimed at the detection, tracking, recognition of moving individuals plus a supervision module. The detection module is devoted to the detection of moving targets, using optic flow computation and relevant areas extraction. The tracking module uses an adaptive correlation technique to fixate on moving objects. The objective of this module is to pursuit the object, centering it into a relocatable focus of attention window (FOAW) to obtain a good view of the object in order to recognize it. Several focus of attention can be tracked simultaneously. The recognition module is designed in an opportunistic style in order to identify the object whenever it is possible. A demonstration system has been developed to detect, track and identify walking people.

CASIMIRO: a robot head for human-computer interaction

The physical appearance and behavior of a robot is an important asset in terms of human-computer interaction. Multimodality is also fundamental, as we humans usually expect to interact in a natural way with voice, gestures, etc. people approach complex interaction devices with stances similar to those used in their interaction with other people. In this paper we describe a robot head, currently under development, that aims to be a multimodal (vision, voice, gestures, ...) perceptual user interface. Modules are described for face detection, tracking, facial movement, action selection and sound localization. Preliminary results indicate that the robot head can potentially achieve the goals we are interested in, namely human interaction and assistance.

An Incremental Learning Algorithm for Face Recognition

In face recognition, where high-dimensional representation spaces are generally used, it is very important to take advantage of all the available information. In particular, many labelled facial images will be accumulated while the recognition system is functioning, and due to practical reasons some of them are often discarded. In this paper, we propose an algorithm for using this information. The algorithm has the fundamental characteristic of being incremental. On the other hand, the algorithm makes use of a combination of classification results for the images in the input sequence. Experiments with sequences obtained with a real person detection and tracking system allow us to analyze the performance of the algorithm, as well as its potential improvements.

A MOPSO method for Direct Load Control in Smart Grid

We model electricity demand of a city in a complex way including appliances and users.We propose a scalable real time method for managing the demand.We implement this method using a multi-objective criteria optimisation algorithm.A solution for managing loads is found within the time requirements.Demand can be reduced up to 20% by controlling three types of appliances. In recent years, power grids have been evolving to decentralised production and control. Direct Load Control (DLC) methods are oriented to manage loads on the demand side. A DLC method based on Multi-Objective Particle Swarm Optimisation (MOPSO) algorithm is described. This method sets up the operation of the appliances when a power restriction must be accomplished. Since the method must operate in real-time, the calculations are distributed. The operation of appliances is obtained by dividing the power restriction among neighbourhoods and calculating multiple local optimisations. The method has been experimentally evaluated through simulations.

Design Space Exploration and Performance Analysis for the Modular Design of CVS in a Heterogeneous MPSoC

In this paper, we present the strategy for evaluating the performance of a variety of configurations of an architecture template for a computer vision system (CVS). For this study a generic model of an architecture is used to address the modular design of the CVS. This modular nature approach could be used to build a more complex system by integrating several applications which perform different kind of data processing issues but sharing a common architecture. In our current work, a visual tracking system with real-time behaviour (25 frames/sec) is modelled and mapped on the model of a pipelined multiprocessor platform. The tracking system performance and shared resource usage were analyzed to determine the real architecture capacity and also to find out possible bottlenecks in order to propose new solutions which allow more applications to be mapped on the platform template in the future.

An engineering approach to sociable robots

Robotics researchers and cognitive scientists are becoming more and more interested in so-called sociable robots. These machines normally have expressive power (facial features, voice, …) as well as abilities for locating, paying attention to, and addressing people. The design objective is to make robots which are able to sustain natural interactions with people. This capacity falls within the range classed as social intelligence in humans. This position paper argues that the reproduction of social intelligence, as opposed to other types of human ability, may lead to fragile performance, in the sense that tested cases may produce rather different performances to future (untested) cases and situations. This limitation stems from the fact that our social abilities, which appear early in life, are mainly unconscious in origin. This is in contrast with other human abilities that we carry out using conscious effort, and for which we can easily conceive algorithms and representations. This novel perspective is deemed useful for defining the obstacles and limitations of a field that is generating increasing interest. Taking into account the mentioned issues, a development approach suited to the problem is proposed. The use of this approach is demonstrated in the development of CASIMIRO, a robotic head with basic interaction abilities.

Computer vision based eyewear selector

The widespread availability of portable computing power and inexpensive digital cameras are opening up new possibilities for retailers in some markets. One example is in optical shops, where a number of systems exist that facilitate eyeglasses selection. These systems are now more necessary as the market is saturated with an increasingly complex array of lenses, frames, coatings, tints, photochromic and polarizing treatments, etc. Research challenges encompass Computer Vision, Multimedia and Human-Computer Interaction. Cost factors are also of importance for widespread product acceptance. This paper describes a low-cost system that allows the user to visualize different glasses models in live video. The user can also move the glasses to adjust its position on the face. The system, which runs at 9.5 frames/s on general-purpose hardware, has a homeostatic module that keeps image parameters controlled. This is achieved by using a camera with motorized zoom, iris, white balance, etc. This feature can be specially useful in environments with changing illumination and shadows, like in an optical shop. The system also includes a face and eye detection module and a glasses management module.

A new approach to the template update problem

Visual tracking based on pattern matching is a very used computer vision technique in a wide range of applications [4]. Updating the template of reference is a crucial aspect for a correct working of this kind of algorithms. This paper proposes a new approach to the updating problem in order to achieve a better performance and robustness of tracking. This is carried out using a representation technique based on second order isomorphisms. The proposed technique has been compared experimentally with other existing approaches with excellent results. The most important improvements of this approach is its parameter-free working, therefore no parameters have to be set up manually in order to tune the process. Besides, objects to be tracked can be rigid or deformable, the system is adapted automatic and robustly to any situation.