Gender classification: a convolutional neural network approach

Abstract

An approach using a convolutional neural network (CNN) is proposed for real-time gender classification based on facial images. The proposed CNN architecture exhibits a much reduced design complexity when compared with other CNN solutions applied in pattern recognition. The number of processing layers in the CNN is reduced to only four by fusing the convolutional and subsampling layers. Unlike in conventional CNNs, we replace the convolution operation with cross-correlation, hence reducing the computational load. The network is trained using a second-order backpropagation learning algorithm with annealed global learning rates. Performance evaluation of the proposed CNN solution is conducted on two publicly available face databases of SUMS and AT&T. We achieve classification accuracies of 98.75% and 99.38% on the SUMS and AT&T databases, respectively. The neural network is able to process and classify a 32 × 32 pixel face image in less than 0.27 ms, which corresponds to a very high throughput of over 3700 images per second. Training converges within less than 20 epochs. These results correspond to a superior classification performance, verifying that the proposed CNN is an effective real-time solution for gender recognition.

Peer Review #1 of "Stochastic computing in convolutional neural network implementation: a review (v0.1)"

“…Moreover, multiplication and addition repeat until the model converges to the size of the desired class output. A simple LeNet-5 model (Liew et al, 2016) as depicted in Fig. 6(C) shows the end-to-end structure of a typical CNN, from the input image to output class.…”

Palmprint gender classification by convolutional neural network

“…Portions of the research in [45] 88.28% An un-published database of 3570 fingerprints, 1980 for male and 1590 for female. iris LBP [32] 91% UND iris database: it contains 750 females and 750 males, with 3000 images totally Iriscode [46] 89% Gender-From-Iris dataset for training: it contains 1200 distinct persons and 2400 images A self-collected dataset UND_V for validation, contains 972 persons face CNN [3] 98.75 and 99.38% on the SUMS and AT&T databases SUMS database: consists of 200 females and 200 male images AT&T database: contains 10 images of 40 subjects (36 males and 4 females)…”

A design of license plate recognition system using convolutional neural network

“…It combines compression (dimensionality reduction), feature extraction and classification processes in a single architecture. Until now, CNN has been applied to various applications such as face detection [5]- [10], face recognition [11]- [15], gender recognition [16]- [19], object classification and recognition [20]- [22], character recognition [23]- [25], texture recognition [26], finger-vein [27], etc. Despite the listed advantages, CNN has limitations in terms of cost and speed.…”