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.

Gender dimorphism in skeletal muscle leptin receptors, serum leptin and insulin sensitivity

[EN] To determine if there is a gender dimorphism in the expression of leptin receptors (OB-R170, OB-R128 and OB-R98) and the protein suppressor of cytokine signaling 3 (SOCS3) in human skeletal muscle, the protein expression of OB-R, perilipin A, SOCS3 and alpha-tubulin was assessed by Western blot in muscle biopsies obtained from the m. vastus lateralis in thirty-four men (age = 27.1+/-6.8 yr) and thirty-three women (age = 26.7+/-6.7 yr). Basal serum insulin concentration and HOMA were similar in both genders. Serum leptin concentration was 3.4 times higher in women compared to men (P<0.05) and this difference remained significant after accounting for the differences in percentage of body fat or soluble leptin receptor. OB-R protein was 41% (OB-R170, P<0.05) and 163% (OB-R128, P<0.05) greater in women than men. There was no relationship between OB-R expression and the serum concentrations of leptin or 17beta-estradiol. In men, muscle OB-R128 protein was inversely related to serum free testosterone. In women, OB-R98 and OB-R128 were inversely related to total serum testosterone concentration, and OB-R128 to serum free testosterone concentration. SOCS3 protein expression was similar in men and women and was not related to OB-R. In women, there was an inverse relationship between the logarithm of free testosterone and SCOS3 protein content in skeletal muscle (r = -0.46, P<0.05). In summary, there is a gender dimorphism in skeletal muscle leptin receptors expression, which can be partly explained by the influence of testosterone. SOCS3 expression in skeletal muscle is not up-regulated in women, despite very high serum leptin concentrations compared to men. The circulating form of the leptin receptor can not be used as a surrogate measure of the amount of leptin receptors expressed in skeletal muscles.

A performance based study on gender recognition in large datasets

[EN]Gender recognition has achieved impressive results based on the face appearance in controlled datasets. Its application in the wild and large datasets is still a challenging task for researchers. In this paper, we make use of classical techniques to analyze their performance in controlled and uncontrolled condition respectively with the LFW and MORPH datasets. For both sets the benchmarking protocol follows the 5-fold cross-validation proposed by the BEFIT challenge.

Gender classification in large databases

[EN]In this paper, we address the challenge of gender classi - cation using large databases of images with two goals. The rst objective is to evaluate whether the error rate decreases compared to smaller databases. The second goal is to determine if the classi er that provides the best classi cation rate for one database, improves the classi cation results for other databases, that is, the cross-database performance.

Improving gender classification accuracy in the wild

[EN]In this paper, we focus on gender recognition in challenging large scale scenarios. Firstly, we review the literature results achieved for the problem in large datasets, and select the currently hardest dataset: The Images of Groups. Secondly, we study the extraction of features from the face and its local context to improve the recognition accuracy. Diff erent descriptors, resolutions and classfii ers are studied, overcoming previous literature results, reaching an accuracy of 89.8%.