Welcome to the IKCEST

Pattern Recognition | Vol.61, Issue.0 | | Pages 417-432

Pattern Recognition

A variety of local structure patterns and their hybridization for accurate eye detection

Daijin Kim   Inho Choi  
Abstract

In this paper, existing local structure patterns (LSPs) are reviewed and categorized into two types: intensity-based LSPs (I-LSPs) and gradient-based LSPs (G-LSPs). I-LSPs include local binary pattern (LBP), modified census transform (MCT) and generalized binary pattern (GBP) methods that compare the intensities of differently selected neighboring pixels within a 3×3 neighborhood with differently-formed reference intensities, encoding 256, 511, and 19,162 binary patterns respectively. G-LSPs include local gradient pattern (LGP), modified gradient pattern (MGP), and generalized gradient pattern (GGP) methods that compare the gradient magnitudes of differently selected neighboring pixels within a 3×3 neighborhood with differently-formed reference gradients, encoding 256, 511, and 19,162 binary patterns respectively. We extend all these LSPs to multi-scale block LSPs (MB-LSPs) that concatenate multiple block-based LSPs. Finally, we propose several hybrid LSPs that combine I-LSPs and G-LSPs by means of the AdaBoost feature selection. In experiments using AR564, BioID, ColorFERET and LFW databases to evaluate the eye detection accuracy of the proposed LSPs, the I-LSPs were good for detecting the eyes in low quality images, the G-LSPs were good for detecting the eyes in high quality images, and the hybrid LSPs achieve state-of-the-art eye detection accuracy across image qualities.

Original Text (This is the original text for your reference.)

A variety of local structure patterns and their hybridization for accurate eye detection

In this paper, existing local structure patterns (LSPs) are reviewed and categorized into two types: intensity-based LSPs (I-LSPs) and gradient-based LSPs (G-LSPs). I-LSPs include local binary pattern (LBP), modified census transform (MCT) and generalized binary pattern (GBP) methods that compare the intensities of differently selected neighboring pixels within a 3×3 neighborhood with differently-formed reference intensities, encoding 256, 511, and 19,162 binary patterns respectively. G-LSPs include local gradient pattern (LGP), modified gradient pattern (MGP), and generalized gradient pattern (GGP) methods that compare the gradient magnitudes of differently selected neighboring pixels within a 3×3 neighborhood with differently-formed reference gradients, encoding 256, 511, and 19,162 binary patterns respectively. We extend all these LSPs to multi-scale block LSPs (MB-LSPs) that concatenate multiple block-based LSPs. Finally, we propose several hybrid LSPs that combine I-LSPs and G-LSPs by means of the AdaBoost feature selection. In experiments using AR564, BioID, ColorFERET and LFW databases to evaluate the eye detection accuracy of the proposed LSPs, the I-LSPs were good for detecting the eyes in low quality images, the G-LSPs were good for detecting the eyes in high quality images, and the hybrid LSPs achieve state-of-the-art eye detection accuracy across image qualities.

+More

Cite this article
APA

APA

MLA

Chicago

Daijin Kim,Inho Choi,.A variety of local structure patterns and their hybridization for accurate eye detection. 61 (0),417-432.

Disclaimer: The translated content is provided by third-party translation service providers, and IKCEST shall not assume any responsibility for the accuracy and legality of the content.
Translate engine
Article's language
English
中文
Pусск
Français
Español
العربية
Português
Kikongo
Dutch
kiswahili
هَوُسَ
IsiZulu
Action
Recommended articles

Report

Select your report category*



Reason*



By pressing send, your feedback will be used to improve IKCEST. Your privacy will be protected.

Submit
Cancel