Within- and cross- database evaluations for face gender classification via befit protocols

Abstract

Abstract-With its wide range of applicability, gender classification is an important task in face image analysis and it has drawn a great interest from the pattern recognition community. In this paper, we aim to deal with this problem using Local Binary Pattern Histogram Sequences as feature vectors in general. Differently from what has been done in similar studies, the algorithm parameters used in cropping and feature extraction steps are selected after an extensive grid search using BANCA and MOBIO databases. The final system which is evaluated on FERET, MORPH-II and LFW with gender balanced and imbalanced training sets is shown to achieve commensurate and better results compared to other state-of-the-art performances on those databases. The system is additionally tested for crossdatabase training in order to assess its accuracy in real world conditions. For LFW and MORPH-II, BeFIT protocols are used.

Multi-scale score level fusion of local descriptors for gender classification in the wild

“…Tapia et al [45] fused different LBPbased features, scales and mutual information measures, reporting for LFW an accuracy of 98%. A similar accuracy has been achieved by Ren and Li [40] and Erdogmus et al [18]. The former combining two types of local descriptors (gradient features and Gabor wavelets), and a linear SVM.…”

Descriptors and regions of interest fusion for in- and cross-database gender classification in the wild

“…In fact, previous state-of-the-art for cross-dataset with LFW has already reported 97%, but that was achieved training with 400,000 samples [11] or four millions [10] Here that accuracy is beaten, reaching 98%, and that is done with just a 7% of the training samples used by Antipov et al When training with MORPH GC rates are lower, 88%, but significantly better that recent reported results that reached 76% [4]. On the other side, GROUPS present larger difficulties, being extremely complex if training with MORPH, just 67%, and easier training with LFW.…”

Collecting large training dataset of actual facial images from facebook for developing a weighted bagging gender classifier

“…Especially, since correct gender recognition is very helpful in determining accurate situation in video surveillance applications [3], many studies on gender classifications B Yoo-Sung Kim yskim@inha.ac.kr 1 Department of Information and Communication Engineering, Inha University, Incheon 402-751, Korea are being conducted [4][5][6][7]. Facial images have been generally used to differentiate gender as face contains useful information such as shape of eyes, nose, lips, and so on.…”

“…However, accurate gender classification of facial images with uncontrolled background is hardly expected from current gender classifiers developed using training datasets with facial images obtained from controlled environments [4]. That is, gender classifiers developed through the controlled training datasets of facial images lack the ability to learn to differentiate various distinctions such as changes in facial angle, occlusion, illumination, or background complexity which can occur in uncontrolled environments.…”

“…The gender classifier was tested for its accuracy with the LFW dataset to obtain 89.77% in the accuracy rate. However, Nesli Erdogmus et al [4] and Erno Mäkinen et al [13] obtained classification accuracy rates of 90.68 and 93.33%, respectively, using facial images obtained from a controlled environment, FERET [14], for their training and test datasets. A gender classifier developed with an uncontrolled training dataset should be improved to obtain accuracy in performance similar to a classifier developed with a controlled training dataset.…”