Real Time Eye Detector with Cascaded Convolutional Neural Networks

An accurate and efficient eye detector is essential for many computer vision applications. In this paper, we present an efficient method to evaluate the eye location from facial images. First, a group of candidate regions with regional extreme points is quickly proposed; then, a set of convolution n...

Full description

Saved in:
Bibliographic Details
Main Authors: Bin Li, Hong Fu
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Applied Computational Intelligence and Soft Computing
Online Access:http://dx.doi.org/10.1155/2018/1439312
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850237062864699392
author Bin Li
Hong Fu
author_facet Bin Li
Hong Fu
author_sort Bin Li
collection DOAJ
description An accurate and efficient eye detector is essential for many computer vision applications. In this paper, we present an efficient method to evaluate the eye location from facial images. First, a group of candidate regions with regional extreme points is quickly proposed; then, a set of convolution neural networks (CNNs) is adopted to determine the most likely eye region and classify the region as left or right eye; finally, the center of the eye is located with other CNNs. In the experiments using GI4E, BioID, and our datasets, our method attained a detection accuracy which is comparable to existing state-of-the-art methods; meanwhile, our method was faster and adaptable to variations of the images, including external light changes, facial occlusion, and changes in image modality.
format Article
id doaj-art-02688de40b2e4d6b84378b11e8b8052e
institution OA Journals
issn 1687-9724
1687-9732
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Applied Computational Intelligence and Soft Computing
spelling doaj-art-02688de40b2e4d6b84378b11e8b8052e2025-08-20T02:01:49ZengWileyApplied Computational Intelligence and Soft Computing1687-97241687-97322018-01-01201810.1155/2018/14393121439312Real Time Eye Detector with Cascaded Convolutional Neural NetworksBin Li0Hong Fu1Xi’an Institute of Optics and Precision Mechanics of CAS, Xi’an 710119, ChinaChu Hai College of Higher Education, Tuen Mun, Hong KongAn accurate and efficient eye detector is essential for many computer vision applications. In this paper, we present an efficient method to evaluate the eye location from facial images. First, a group of candidate regions with regional extreme points is quickly proposed; then, a set of convolution neural networks (CNNs) is adopted to determine the most likely eye region and classify the region as left or right eye; finally, the center of the eye is located with other CNNs. In the experiments using GI4E, BioID, and our datasets, our method attained a detection accuracy which is comparable to existing state-of-the-art methods; meanwhile, our method was faster and adaptable to variations of the images, including external light changes, facial occlusion, and changes in image modality.http://dx.doi.org/10.1155/2018/1439312
spellingShingle Bin Li
Hong Fu
Real Time Eye Detector with Cascaded Convolutional Neural Networks
Applied Computational Intelligence and Soft Computing
title Real Time Eye Detector with Cascaded Convolutional Neural Networks
title_full Real Time Eye Detector with Cascaded Convolutional Neural Networks
title_fullStr Real Time Eye Detector with Cascaded Convolutional Neural Networks
title_full_unstemmed Real Time Eye Detector with Cascaded Convolutional Neural Networks
title_short Real Time Eye Detector with Cascaded Convolutional Neural Networks
title_sort real time eye detector with cascaded convolutional neural networks
url http://dx.doi.org/10.1155/2018/1439312
work_keys_str_mv AT binli realtimeeyedetectorwithcascadedconvolutionalneuralnetworks
AT hongfu realtimeeyedetectorwithcascadedconvolutionalneuralnetworks