oalogo2  

AUTHOR(S):

Zlatin Zlatev, Eleonora Kirilova, Tsvetelina Georgieva, Plamen Daskalov

 

TITLE

Investigation of Possibilities for Prediction of Automobile Bio-Oils Parameters by Color Image Analysis

pdf PDF

ABSTRACT

Investigation of possibilities for predicting the physico-chemical parameters viscosity and density of automotive bio-oils using color image analysis is described in the paper. Data of bio oils is compared with those for standard engine oils. The results show that the oil density can be predicted with an accuracy of 85% and the viscosity at an accuracy of 57% with low error rates of 2-9% with R (RGB), G (RGB), V (HSV), L (Lab), L (LCH), and K (CMYK) color features. The results obtained can be used in the design of optical sensor devices operating in the visible area of the spectrum for rapid and non-destructive determination of physico-chemical parameters of automotive oils.

KEYWORDS

Image processing, Color features, Automotive oils, Partial least squares regression, Physico-chemical parameters, Classification

 

Cite this paper

Zlatin Zlatev, Eleonora Kirilova, Tsvetelina Georgieva, Plamen Daskalov. (2019) Investigation of Possibilities for Prediction of Automobile Bio-Oils Parameters by Color Image Analysis. International Journal of Chemistry and Chemical Engineering Systems, 4, 16-20

 

cc.png
Copyright © 2018 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0