Oil Adulteration Identification by Hyperspectral Imaging Using QHM and ICA.

Zhongzhi Han,Limiao Deng,Kangwei Liu,Jianhua Wan,Adrian G Dyer

doi:10.1371/journal.pone.0146547

Abstract

To investigate the feasibility of identification of qualified and adulterated oil product using hyperspectral imaging(HIS) technique, a novel feature set based on quantized histogram matrix (QHM) and feature selection method using improved kernel independent component analysis (iKICA) is proposed for HSI. We use UV and Halogen excitations in this study. Region of interest(ROI) of hyperspectral images of 256 oil samples from four varieties are obtained within the spectral region of 400–720nm. Radiation indexes extracted from each ROI are used as feature vectors. These indexes are individual band radiation index (RI), difference of consecutive spectral band radiation index (DRI), ratio of consecutive spectral band radiation index (RRI) and normalized DRI (NDRI). Another set of features called quantized histogram matrix (QHM) are extracted by applying quantization on the image histogram from these features. Based on these feature sets, improved kernel independent component analysis (iKICA) is used to select significant features. For comparison, algorithms such as plus L reduce R (plusLrR), Fisher, multidimensional scaling (MDS), independent component analysis (ICA), and principle component analysis (PCA) are also used to select the most significant wavelengths or features. Support vector machine (SVM) is used as the classifier. Experimental results show that the proposed methods are able to obtain robust and better classification performance with fewer number of spectral bands and simplify the design of computer vision systems.

Highlights

With the development of the society and economy, oil products are becoming more and more important for automobile industry
This paper aims to evaluate the feasibility of identifying the qualified oil and the adulterated oil using hyperspectral imaging (HSI) with a spectral range of 400-720nm
A novel feature selection method has been proposed based on the maximum negentropy of independent components (ICs) separated by kernel independent component analysis

Summary

Introduction

With the development of the society and economy, oil products are becoming more and more important for automobile industry. Driven by the great economic benefit, some unscrupulous traders sold low-value or adulterated oil products instead of high-value oil products in recent years. Many oil refinery factories in China are producing adulterated oil to make more profits according to a report by China Central Television (CCTV) in its annual 3.15 Gala program[1]. They use 90# gasoline, naphtha, aromatics and other additives to produce 93# blend oil. Adulterated oil has damaged the consumers’ benefits, and threated people’s safety. To guarantee and promote oil products’ quality, the identification of the qualified oil products and adulterated oil products is extremely essential

Objectives

Methods

Results

Conclusion