Welcome to the InfoSci Platform
Reference Hub4
Center Symmetric Local Descriptors for Image Classification

Center Symmetric Local Descriptors for Image Classification

Vaasudev Narayanan, Bhargav Parsi
Copyright: © 2018 |Volume: 7 |Issue: 4 |Pages: 15
ISSN: 1947-928X|EISSN: 1947-9298|EISBN13: 9781522544838|DOI: 10.4018/IJNCR.2018100104
Cite Article Cite Article

MLA

Narayanan, Vaasudev, and Bhargav Parsi. "Center Symmetric Local Descriptors for Image Classification." IJNCR vol.7, no.4 2018: pp.56-70. http://doi.org/10.4018/IJNCR.2018100104

APA

Narayanan, V. & Parsi, B. (2018). Center Symmetric Local Descriptors for Image Classification. International Journal of Natural Computing Research (IJNCR), 7(4), 56-70. http://doi.org/10.4018/IJNCR.2018100104

Chicago

Narayanan, Vaasudev, and Bhargav Parsi. "Center Symmetric Local Descriptors for Image Classification," International Journal of Natural Computing Research (IJNCR) 7, no.4: 56-70. http://doi.org/10.4018/IJNCR.2018100104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Local feature description forms an integral part of texture classification, image recognition, and face recognition. In this paper, the authors propose Center Symmetric Local Ternary Mapped Patterns (CS-LTMP) and eXtended Center Symmetric Local Ternary Mapped Patterns (XCS-LTMP) for local description of images. They combine the strengths of Center Symmetric Local Ternary Pattern (CS-LTP) which uses ternary codes and Center Symmetric Local Mapped Pattern (CS-LMP) which captures the nuances between images to make the CS-LTMP. Similarly, the auhtors combined CS-LTP and eXtended Center Symmetric Local Mapped Pattern (XCS-LMP) to form eXtended Center Symmetric Local Ternary Mapped Pattern (XCS-LTMP). They have conducted their experiments on the CIFAR10 dataset and show that their proposed methods perform significantly better than their direct competitors.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.