Welcome to the InfoSci Platform
Reference Hub1
A Modified Binary Descriptor for Object Detection

A Modified Binary Descriptor for Object Detection

Ritu Rani, Ravinder Kumar, Amit Prakash Singh
Copyright: © 2021 |Volume: 14 |Issue: 1 |Pages: 17
ISSN: 1938-7857|EISSN: 1938-7865|EISBN13: 9781799860006|DOI: 10.4018/JITR.2021010102
Cite Article Cite Article

MLA

Rani, Ritu, et al. "A Modified Binary Descriptor for Object Detection." JITR vol.14, no.1 2021: pp.20-36. http://doi.org/10.4018/JITR.2021010102

APA

Rani, R., Kumar, R., & Singh, A. P. (2021). A Modified Binary Descriptor for Object Detection. Journal of Information Technology Research (JITR), 14(1), 20-36. http://doi.org/10.4018/JITR.2021010102

Chicago

Rani, Ritu, Ravinder Kumar, and Amit Prakash Singh. "A Modified Binary Descriptor for Object Detection," Journal of Information Technology Research (JITR) 14, no.1: 20-36. http://doi.org/10.4018/JITR.2021010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The reliability of computer vision applications highly depends on the extraction of compact, fast, and accurate and robust feature description. This paper presents a better and modified binary descriptor based on ORB (oriented and rotated brief) with the SVM-RBF-RFE (support vector machine-radial basis function-recursive feature elimination) to achieve a better extraction and representation of local binary descriptors. This work presents the extensive comparison of the proposed modified descriptor with the state-of-the-art binary descriptors on various datasets. The results show that the proposed descriptor is highly distinctive and efficient as compared to the other state-of-the-art binary descriptors. The experiments were performed on the four benchmark datasets PASCAL, CALTECH, COIL, and OXFORD to demonstrate the robustness and effectiveness of the proposed descriptor. The robustness and effectiveness of the proposed descriptor is tested under the various transformations like scaling, rotation, noise, intensity variation.

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.