Human face verification based on multidimensional Polynomial Powers of Sigmoid (PPS)

In this paper, we described how a multidimensional wavelet neural networks based on Polynomial Powers of Sigmoid (PPS) can be constructed, trained and applied in image processing tasks. In this sense, a novel and uniform framework for face verification is presented. The framework is based on a family of PPS wavelets,generated from linear combination of the sigmoid functions, and can be considered appearance based in that features are extracted from the face image. The feature vectors are then subjected to subspace projection of PPS-wavelet. The design of PPS-wavelet neural networks is also discussed, which is seldom reported in the literature. The Stirling Universitys face database were used to generate the results. Our method has achieved 92 % of correct detection and 5 % of false detection rate on the database.

Avaliação de parâmetros métricos oculares pela fotografia digital da face: uso do diâmetro da íris como unidade de referência

Purpose: To evaluate reproducibility and precision of ocular measurements by digital photograph analysis, in addition to the transformation of the measures according to the individual iris diameter as an oculometric reference. Methods: Twenty-four eyes have been digitally photographed in a standardized way at two distances. Two researchers have analyzed these printed images using a caliper and these digital forms by ImageJ 1.37 (TM). Several external ocular parameters were estimated (mm and as iris diameter) and methods of measurement compared regarding their precision, agreement and correlation. Results: Caliper and digital analysis of oculometric measures provided significant agreement and correlation, nevertheless the precision of digital measures was higher. The estimates of numeric transformation from oculometric measures according to individual iris diameter resulted in great correlation to caliper measures and high agreement when compared to different distances of taking the photographs. Conclusions: Facial digital photographs allowed oculometric precise and reproducible estimates, endorsing clinical research usefulness. Using iris diameter as individual oculometric reference disclosed high reproducibility when facial photographs were taken at different distances.

Infrared face recogniton by optimum-path forest

This paper presents a novel, fast and accurate appearance-based method for infrared face recognition. By introducing the Optimum-Path Forest classifier, our objective is to get good recognition rates and effectively reduce the computational effort. The feature extraction procedure is carried out by PCA, and the results are compared to two other well known supervised learning classifiers; Artificial Neural Networks and Support Vector Machines. The achieved performance asserts the promise of the proposed framework. ©2009 IEEE.

Retention and processing methods of nasal prosthesis

Patients with congenital malformations, traumatic or pathological mutilation and maxillofacial developmental disorders can be restored aesthetically and emotionally by the production and use of facial prostheses. The aim of this study was to review the literature about the retention and processing methods of facial prostheses, and discuss their characteristics. A literature review on Medline (PubMed) database was performed by using the keywords maxillofacial prosthesis, silicone, resin, pigment, cosmetic, prosthetic nose, based on articles published from 1956 to 2010. Several methods of retention, from adhesives to the placement of implants, and different processing methods such as laser, CAD/CAM and rapid prototyping technologies have been reported. There are advantages and disadvantages of each procedure, and none can be classified as better compared to others.