A novel geometric feature extraction method for ear recognition. (15th December 2016)

• Record Type: Journal Article
• Authors: Omara, Ibrahim; Li, Feng; Zhang, Hongzhi; Zuo, Wangmeng
• Is Part Of: Expert systems with applications. Volume 65(2016)
• Page Start: 127
• Page End: 135
• Publication Date: 2016-12-15
• Subjects: Ear recognition -- Feature extraction -- Geometric feature -- Edge detection; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2016.08.035
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: We proposed a novel geometric feature extraction approach for ear image. Both the maximum and the minimum ear height lines are used to characterize the contour of outer helix. Our method achieves recognition rate of 98.33 on the USTB subset1 and of 99.6 on the IIT Delhi database. Our geometric method can be combined with the appearance approaches to improve the recognition performance. Abstract: The discriminative ability of geometric features can be well supported by empirical studies in ear recognition. Recently, a number of methods have been suggested for geometric feature extraction from ear images. However, these methods usually have relatively high feature dimension or are sensitive to rotation and scale variations. In this paper, we propose a novel geometric feature extraction method to address these issues. First, our studies show that the minimum Ear Height Line (EHL) is also helpful to characterize the contour of outer helix, and the combination of maximal EHL and minimum EHL can achieve better recognition performance. Second, we further extract three ratio-based features which are robust to scale variation. Our method has the feature dimension of six, and thus is efficient in matching for real-time ear recognition. Experimental results on two popular databases, i.e. USTB subset1 and IIT Delhi, show that the proposed approach can achieve promising recognition rates of 98.33% and 99.60%, respectively.