Classification of Rusty and Non-Rusty Images: A Machine Learning Approach

Mridu Sahu, Tushar Jani, Maski Saijahnavi, Amrit Kumar, Upendra Chaurasiya and Samrudhi Mohdiwale
Additional contact information
Mridu Sahu: National Institute of Technology, Raipur, India
Tushar Jani: National Institute of Technology, Raipur, India
Maski Saijahnavi: National Institute of Technology, Raipur, India
Amrit Kumar: National Institute of Technology, Raipur, India
Upendra Chaurasiya: National Institute of Technology, Raipur, India
Samrudhi Mohdiwale: National Institute of Technology, Raipur, India

International Journal of Natural Computing Research (IJNCR), 2020, vol. 9, issue 4, 1-17

Abstract: Rust detection is necessary for proper working and maintenance of machines for security purposes. Images are one of the suggested platforms for rust detection in which rust can be detected even though the human can't reach to the area. However, there are a lack of online databases available that can provide a sizable dataset to identify the most suitable model that can be used further. This paper provides a data augmentation technique by using Perlin noise, and further, the generated images are tested on standard features (i.e., statistical values, entropy, along with SIFT and SURF methods). The two most generalized classifiers, naïve Bayes and support vector machine, are identified and tested to obtain the performance of classification of rusty and non-rusty images. The support vector machine provides better classification accuracy, which also suggests that that the combined features of statistics, SIFT, and SURF are able to differentiate the images. Hence, it can be further used to detect the rust in different parts of machines.

Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/IJNCR.2020100101 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jncr00:v:9:y:2020:i:4:p:1-17

Access Statistics for this article

International Journal of Natural Computing Research (IJNCR) is currently edited by Xuewen Xia

More articles in International Journal of Natural Computing Research (IJNCR) from IGI Global
Bibliographic data for series maintained by Journal Editor ().