A Fast Deep Convolutional Neural Network for Face Detection in Big Visual Data

Conference paper

DOI: 10.1007/978-3-319-47898-2_7

Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 529)
Cite this paper as:
Triantafyllidou D., Tefas A. (2017) A Fast Deep Convolutional Neural Network for Face Detection in Big Visual Data. In: Angelov P., Manolopoulos Y., Iliadis L., Roy A., Vellasco M. (eds) Advances in Big Data. INNS 2016. Advances in Intelligent Systems and Computing, vol 529. Springer, Cham

Abstract

Deep learning methods are powerful approaches but often require expensive computations and lead to models of high complexity which need to be trained with large amounts of data. In this paper, we consider the problem of face detection and we propose a light-weight deep convolutional neural network that achieves a state-of-the-art recall rate of 90 % at the challenging FDDB dataset. Our model is designed with a view to minimize both training and run time and outperforms the convolutional network used in [2] for the same task. Our model consists of only 76.554 free parameters whereas the previously proposed CNN for face detection had 60 million parameters. Our model also requires 250 times fewer floating point operations than AlexNet. We propose a new training method that gradually increases the difficulty of both negative and positive examples and has proved to drastically improve training speed and accuracy. The proposed method is able to detect faces under severe occlusion and unconstrained pose variation and meets the difficulties and the large variations of real-world face detection..

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Artificial Intelligence and Information Analysis Lab, Department of InformaticsAristotle University of ThessalonikiThessalonikiGreece

Personalised recommendations