On using periocular biometric for gender classification in the wild

Castrillón-Santana, Modesto; Lorenzo-Navarro, Javier; Ramón-Balmaseda, Enrique

doi:10.1016/j.patrec.2015.09.014

Cited by 52 publications

(36 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reported results correspond to the 5-folds mean highest accuracy achieved, varying the cost and gamma parameters respectively within the intervals C = [0. 5,5] and gamma = [0.04, 0.15].…”

Section: Resultsmentioning

confidence: 99%

“…the interest for the GC problem of a proper combination of features and regions of interest. We start from a baseline, given by a state of the art facial based GC system [4], to later explore the fusion with features densely extracted from some specific areas of the inner face [5]. With this concept in mind, we have revisited the analysis of the human visual system for the GC problem using bubbles [13], where the authors argue that both the ocular and the mouth areas are discriminant for this task to the human system.…”

Section: Approachmentioning

confidence: 99%

“…An initial study of the integration of the periocular area [5] has already suggested that this approach may improve the GC performance up to 2 percentage points. Indeed, the use of components for facial analysis is a known idea.…”

Section: Approachmentioning

confidence: 99%

See 2 more Smart Citations

Fusion of Holistic and Part Based Features for Gender Classification in the Wild

Castrillón-Santana

Lorenzo-Navarro

Ramón-Balmaseda

2015

New Trends in Image Analysis and Processing -- ICIAP 2015 Workshops

Self Cite

View full text Add to dashboard Cite

Abstract. Gender classification (GC) in the wild is an active area of current research. In this paper, we focus on the combination of a holistic state of the art approach based on features extracted from the facial pattern, with patch based approaches that focus on inner facial areas. Those regions are selected for being relevant to the human system according to the psychophysics literature: the ocular and the mouth areas. The resulting proposed GC system outperforms previous approaches, reducing the classification error of the holistic approach roughly a 30%.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Approachmentioning

confidence: 99%

See 1 more Smart Citation

Fusion of Holistic and Part Based Features for Gender Classification in the Wild

Castrillón-Santana

Lorenzo-Navarro

Ramón-Balmaseda

2015

New Trends in Image Analysis and Processing -- ICIAP 2015 Workshops

Self Cite

View full text Add to dashboard Cite

show abstract

“…10. Wilcoxon matched-pairs signed-ranks tests indicate that Farett-Gender shows the highest learnability 17 , and KCAPTCHA shows the lowest 18 .…”

Section: Learnabilitymentioning

confidence: 98%

“…There is further evidence for the difference between humans and machines in recognizing gender: those faces that were misclassified [26] or excluded [79] in the studies could easily be classified by humans. On the one hand, some authors report recognition rates in excess of 90% [79] and recent studies show that for some real-world images, similar success rates are possible [17,86].…”

Section: Gender and Age Classification For Captchasmentioning

confidence: 99%

Development of two novel face-recognition CAPTCHAs: A security and usability study

Schryen

Wagner

Schlegel

2016

Computers & Security

View full text Add to dashboard Cite

CAPTCHAs are challenge-response tests that aim at preventing unwanted machines, including bots, from accessing web services while providing easy access for humans. Recent advances in artificial-intelligence based attacks show that the level of security provided by many state-ofthe-art text-based CAPTCHAs is declining. At the same time, techniques for distorting and obscuring the text, which are used to maintain the level of security, make text-based CAPTCHAs difficult to solve for humans, and thereby further degrade usability. The need for developing alternative types of CAPTCHAs which improve both, the current security and usability levels, has been emphasized by several researchers.With this study, we contribute to research through (1) the development of two new face recognition CAPTCHAs (Farett-Gender and FarettGender&Age), (2) the security analysis of both procedures, and (3) the provision of empirical evidence that one of the suggested CAPTCHAs (FarettGender) is similar to Google's reCAPTCHA and better than KCAPTCHA concerning effectiveness (error rates), superior to both regarding learnability and satisfaction but not efficiency.

show abstract