2^B3^C: 2 Box 3 Crop of Facial Image for Gender Classification with Convolutional Networks

TL;DR

This paper presents a novel face cropping and classification method using CNNs that improves gender classification accuracy and operates in real-time on GPU, based on face detection, cropping schemes, and fine-tuning.

Contribution

The proposed 2^B3^C method introduces a new face cropping scheme combined with CNN fine-tuning, achieving high accuracy and real-time performance for gender classification.

Findings

Achieved 90.8% accuracy on Adience dataset.

Achieved 95.3% accuracy on LFW dataset.

Operates at 7-10 fps in real-time scenarios.

Abstract

In this paper, we tackle the classification of gender in facial images with deep learning. Our convolutional neural networks (CNN) use the VGG-16 architecture [1] and are pretrained on ImageNet for image classification. Our proposed method (2^B3^C) first detects the face in the facial image, increases the margin of a detected face by 50%, cropping the face with two boxes three crop schemes (Left, Middle, and Right crop) and extracts the CNN predictions on the cropped schemes. The CNNs of our method is fine-tuned on the Adience and LFW with gender annotations. We show the effectiveness of our method by achieving 90.8% classification on Adience and achieving competitive 95.3% classification accuracy on LFW dataset. In addition, to check the true ability of our method, our gender classification system has a frame rate of 7-10 fps (frames per seconds) on a GPU considering real-time scenarios.