Search for: All records

Aging or gender variation can affect the face recognition performance dramatically. While most of the face recognition studies are focused on the variation of pose, illumination and expression, it is important to consider the influence of gender effect and how to design an effective matching framework. In this paper, we address these problems on a very large longitudinal database MORPH-II which contains 55,134 face images of 13,617 individuals. First, we consider four comprehensive experiments with different combination of gender distribution and subset size, including: 1) equal gender distribution; 2) a large highly unbalanced gender distribution; 3) consider different gender combinations, such as male only, female only, or mixed gender; and 4) the effect of subset size in terms of number of individuals. Second, we consider eight nearest neighbor distance metrics and also Support Vector Machine (SVM) for classifiers and test the effect of different classifiers. Last, we consider different fusion techniques for an effective matching framework to improve the recognition performance. 

Abstract Though neural interface systems (NISs) can provide a potential solution for mitigating the effects of limb loss and central nervous system damage, the microelectrode array (MEA) component of NISs remains a significant limiting factor to their widespread clinical applications. Several strategies can be applied to MEA designs to increase their biocompatibility. Herein, an overview of NISs and their applications is provided, along with a detailed discussion of strategies for alleviating the foreign body response (FBR) and abnormalities seen at the interface of MEAs and the brain tissue following MEA implantation. Various surface modifications, including natural/synthetic surface coatings, hydrogels, and topography alterations, have shown to be highly successful in improving neural cell adhesion, reducing gliosis, and increasing MEA longevity. Different MEA surface geometries, such as those seen in the Utah and Michigan arrays, can help alleviate the resultant FBR by reducing insertion damage, while providing new avenues for improving MEA recording performance and resolution. Increasing overall flexibility of MEAs as well as reducing their stiffness is also shown to reduce MEA induced micromotion along with FBR severity. By combining multiple different properties into a single MEA, the severity and duration of an FBR postimplantation can be reduced substantially.