Robust local oriented patterns for ear recognition

  • PDF / 5,565,434 Bytes
  • 22 Pages / 439.642 x 666.49 pts Page_size
  • 48 Downloads / 189 Views

DOWNLOAD

REPORT


Robust local oriented patterns for ear recognition M. Hassaballah1

· H. A. Alshazly2 · Abdelmgeid A. Ali3

Received: 14 May 2019 / Revised: 17 July 2020 / Accepted: 28 July 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020

Abstract Extraction and description of image features is an active research topic and important for several applications of computer vision field. This paper presents a new noise-tolerant and rotation-invariant local feature descriptor called robust local oriented patterns (RLOP). The proposed descriptor extracts local image structures utilizing edge directional information to provide rotation-invariant patterns and to be effective in noise and changing illumination situations. This is achieved by a non-linear amalgamation of two specific strategies; binarizing neighborhood pixels of a patch and assigning binomial weights in the same formula. In the encoding methodology, the neighboring pixels is binarized with respect to the mean value of pixels in an image patch of size 3 × 3 instead of the center pixel. Thus, the obtained codes are rotation-invariant and more robust against noise and other nonmonotonic grayscale variations. Ear recognition is considered as the representative problem, where the ear involves localized patterns and textures. The proposed descriptor encodes all images’ pixels and the resulting RLOP-encoded image is divided into several regions. Histograms of the regions are constructed to estimate the distribution of features. Then, all histograms are concatenated together to form the final descriptor. The robustness and effectiveness of the proposed descriptor are evaluated through conducting several identification and verification experiments on four different ear databases: IIT Delhi-I, IIT Delhi-II, AMI, and AWE. It is observed that the proposed descriptor outperforms the state-of-the-art texture based approaches achieving a recognition rate of 98% on the average providing the best performance among the tested descriptors. Keywords Biometrics · Ear recognition · Features extraction · Local image descriptors · Local binary patterns

1 Introduction Biometrics authentication systems nowadays are an integral part of modern societies and daily life due to its important and potential applications in security, law enforcement, foren-

 M. Hassaballah

[email protected]

Extended author information available on the last page of the article.

Multimedia Tools and Applications

sics, and surveillance [10, 58]. The biometric systems recognize individuals automatically based on their behavioral (e.g., gait, voice) or physical characteristics [54]. The most common used biometric systems are those utilize the physical characteristics such as face recognition systems [29, 37], fingerprint [8], and eye or iris [15]. However, other physical characteristics such as human ears, are also being elaborated as potential and alternative biometric cues for individuals recognition [1, 4, 49]. Unfortunately, to the best of our knowledge, there are very few commercial