J. F. Díez-Higuera

Real-time vision-based eye state detection for driver alertness monitoring

This paper presents a real-time vision-based system to detect the eye state. The system is implemented with a consumer-grade computer and an uncalibrated web camera with passive illumination. Previously established similarity measures between image regions, feature selection algorithms, and classifiers have been applied to achieve vision-based eye state detection without introducing a new methodology. From many different extracted data of 1,293 pair of eyes images and 2,322 individual eye images, such as histograms, projections, and contours, 186 similarity measures with three eye templates were computed. Two feature selection algorithms, the

Neural Network Model Based on Fuzzy ARTMAP for Forecasting of Highway Traffic Data

J_{5} (xi )

Computer vision architecture for real-time face and hand detection and tracking

criterion and sequential forward selection, and two classifiers, multi-layer perceptron and support vector machine, were intensively studied to select the best scheme for pair of eyes and individual eye state detection. The output of both the selected classifiers was combined to optimize eye state monitoring in video sequences. We tested the system with videos with different users, environments, and illumination. It achieved an overall accuracy of 96.22xa0%, which outperforms previously published approaches. The system runs at 40xa0fps and can be used to monitor driver alertness robustly.

Texture Classification of the Entire Brodatz Database through an Orientational-Invariant Neural Architecture

The aim of this paper is to outline a multiple scale neural model to recognise colour images of textured scenes. This model combines colour and textural information in order to recognise colour texture images through the operation of two main components: a segmentation component composed of the colour opponent system (COS) and the chromatic segmentation system (CSS); and a recognition component formed by an ARTMAP-based neural network with scale and orientation-invariance properties. Segmentation is achieved by perceptual contour extraction and diffusion processes on the colour opponent channels based on the human psychophysical theory of colour perception. This colour regions enhancement along with their local textural features constitutes the recognition pattern to be sent to the supervised neural classifier. The CSS accomplishes the colour region enhancement through a multiple scale loop of oriented filters and competition-cooperation mechanisms. Afterwards, the neural architecture performs an attentive recognition of the scene using those oriented filters responses and the chromatic diffusions. Some comparative tests with other models are included in order to prove the recognition capabilities of this neural architecture and how the use of colour information encourages the texture classification and the accuracy of the boundary detection.

Real-time nose detection and tracking based on AdaBoost and optical flow algorithms

In this chapter, a neural network model is presented for forecasting the average speed values at highway traffic detectors locations using the Fuzzy ARTMAP theory. The performance of the model is measured by the deviation between the speed values provided by the loop detectors and the predicted speed values. Different Fuzzy ARTMAP configuration cases are analysed in their training and testing phases. Some ad-hoc mechanisms added to the basic Fuzzy ARTMAP structure are also described to improve the entire model performance. The achieved results make this model suitable for being implemented on advanced traffic management systems (ATMS) and advanced traveller information system (ATIS).

Bio-inspired computer vision based on neural networks

In this paper, a marker-free computer vision system for cognitive rehabilitation tests monitoring is presented. The system monitors and analyzes the correct and incorrect realization of a set of psicomotricity exercises in which a hand has to touch a facial feature. The monitoring requires different human body parts detection and tracking. Detection of face, eyes, nose, and hands is achieved with a set of classifiers built independently based on the AdaBoost algorithm. Comparisons with other detection approaches, regarding performance and applicability to the monitoring system, are presented. Face and hands tracking is accomplished through the CAMShift algorithm with independent and adaptive two-dimensional histograms of the chromaticity components of the TSL color space for the pixels inside these three regions. The TSL color space was selected after a study of five color spaces regarding skin color characterization. The system is easily implemented with a consumer-grade computer and a camera, unconstrained background and illumination and runs at more than 23 frames per second. The system was tested and achieved a successful monitoring percentage of 97.62%. The automation of the human body parts motion monitoring, its analysis in relation to the psicomotricity exercise indicated to the patient and the storage of the result of the realization of a set of exercises free the rehabilitation experts of doing such demanding tasks. The vision-based system is potentially applicable to other human-computer interface tasks with minor changes.

Multiple scale neural architecture for face recognition

In this paper we present a computer vision architecture to detect and track the face and hands of a human being in real time from a video sequence captured by a webcam. The architecture has a first preprocessing stage, including a color filtering module, a motion filtering module, a color-based segmentation, a processing channels merge module and, finally, a contour search and discrimination module. The aim of the first stage is to discard the image regions which are highly unlikely to correspond with skin. Thus, the second stage of the architecture is a previously trained Fuzzy ARTMAP multiscale neural network module which only processes those image regions selected by the preprocessing stage, which are fully expected to be skin. The neural networks make the last decision about face and hand detection. After that, the architecture tracks the trajectories which face and hands follow.

Real-time system for elliptical-based face detection

This paper presents a supervised neural architecture, called SOON, for texture classification. Multi-scale Gabor filtering is used to extract the textural features which shape the input to a neural classifier with orientation invariance properties in order to accomplish the classification. Three increasing complexity tests over the well-known Brodatz database are performed to quantify its behavior. The test simulations, including the entire texture album classification, show the stability and robustness of the SOON response.