On using periocular biometric for gender classification in the wild

[EN]Gender information may serve to automatically modulate interaction to the user needs, among other applications. Within the Computer Vision community, gender classification (GC) has mainly been accomplished with the facial pattern. Periocular biometrics has recently attracted researchers attention with successful results in the context of identity recognition. But, there is a lack of experimental evaluation of the periocular pattern for GC in the wild. The aim of this paper is to study the performance of this specific facial area in the currently most challenging large dataset for the problem.

My mind, my self, my identity: a task-independent neural signature for biometric identification

Programa de doctorado: Sistemas Inteligentes y Aplicaciones Numéricas en Ingeniería

Optimización del cultivo de diatomeas bentónicas para el cultivo de post-larvas de abalón ("Haliotis tuberculata coccinea" Reeve, 1846)

[EN] Diatom cell quantity and their biochemical composition vary among species and are greatly affected by harvest stage or culture conditions. Biometric parameters, growth, attachment capacity and variations in biochemical composition of four species of benthic diatoms (Amphora sp., Navicula incerta, Nitzschia sp. and Proschkinia sp.) were studied. For biochemical analysis the diatoms were harvested at different stages, in log and stationary phase of growth. The culture conditions were identical for all the experiments, benthic diatoms were cultured during 7 days in F/2 medium at 28.5 ± 1.4 ºC, at different original inoculating densities (50000, 100000, and 250000 cell mL-1), under continuous light of 5403 ± 649 Lux provided by cool white fluorescent lighting. The cultures were neither aerated nor agitated. These results show that the specific density of 10000 cell mL-1 was the best for weekly production: Proschkinia sp. reached the highest cell density of 5.81 x 106 cells mL-1 and Amphora sp. had the highest cell attachment capacity with 12000 cell mm-2, in stationary phase of growth. Protein and lipid content were higher in log phase than in stationary phase for the four diatoms. Amphora sp. in log phase of growth had the highest lipid content of 9.74% dry weight (DW). Polyunsaturated fatty acid (PUFA) content ranged from 23.25% to 38.62% of the total fatty acids (TFA), and the four diatoms tested were richer in n-3 PUFA than in n-6 PUFA. All the diatoms had significant quantities of 20:5n-3 (EPA) ranging between 12.69% and 17.68% of TFA. Benthic diatoms play an important and critical role in abalone culture as they are the principal food source of abalone post-larvae. Therefore, it is necessary to improve diatom quantity and quality to optimize post-larval nutrition and the consistency of production, resulting in an increase in growth and survival of abalones.

Aspectos biológicos de Paromola cuvieri (Crustacea: Decapoda: Brachyura: Homolidae)

Máster en Gestión Sostenible de Recursos Pesqueros

Una metodología para el estudio de las fanerógamas marinas en Canarias

[ES]Se presenta una metodología para el estudio de las fanerógamas marinas en Canarias. Ésta se basa en la aplicación de técnicas cartográficas, mediante la utilización de la totografía aérea y de un sistema de cámara de televisión. Se explica el estudio de los principales parámetros biométricos de las plantas que sirven para la evaluación de las poblaciones.

People semantic description and re-identification from point cloud geometry

The automatic extraction of biometric descriptors of anonymous people is a challenging scenario in camera networks. This task is typically accomplished making use of visual information. Calibrated RGBD sensors make possible the extraction of point cloud information. We present a novel approach for people semantic description and re-identification using the individual point cloud information. The proposal combines the use of simple geometric features with point cloud features based on surface normals.

A study for the self similarity smile detection

[EN]This work makes an extensive experimental study of smile detection testing the Local Binary Patterns (LBP) combined with self similarity (LAC) as main descriptors of the image, along with the powerful Support Vector Machines classifier. Results show that error rates can be acceptable and the self similarity approach for the detection of smiles is suitable for real-time interaction, although there is still room for improvement.

Detection of frontal faces in video streams

[EN]This paper describes an approach for detection of frontal faces in real time (20-35Hz) for further processing. This approach makes use of a combination of previous detection tracking and color for selecting interest areas. On those areas, later facial features such as eyes, nose and mouth are searched based on geometric tests, appearance veri cation, temporal and spatial coherence. The system makes use of very simple techniques applied in a cascade approach, combined and coordinated with temporal information for improving performance. This module is a component of a complete system designed for detection, tracking and identi cation of individuals [1].

An incremental learning algorithm for face recognition

[EN]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.