On-line prediction of hazardous fungal contamination in stored maize by integrating Vis/NIR spectroscopy and computer vision

Fei Shen; Yi Huang; Xuesong Jiang; Yong Fang; Peng Li; Qin Liu; Qiuhui Hu; Xingquan Liu

doi:10.1016/j.saa.2019.118012

On-line prediction of hazardous fungal contamination in stored maize by integrating Vis/NIR spectroscopy and computer vision

Spectrochim Acta A Mol Biomol Spectrosc. 2020 Mar 15:229:118012. doi: 10.1016/j.saa.2019.118012. Epub 2019 Dec 30.

Authors

Fei Shen¹, Yi Huang¹, Xuesong Jiang², Yong Fang³, Peng Li¹, Qin Liu¹, Qiuhui Hu¹, Xingquan Liu⁴

Affiliations

¹ College of Food Science and Engineering, Nanjing University of Finance and Economics, Nanjing 210023, China; Collaborative Innovation Center for Modern Grain Circulation and Safety, Nanjing 210023, China.
² College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China.
³ College of Food Science and Engineering, Nanjing University of Finance and Economics, Nanjing 210023, China; Collaborative Innovation Center for Modern Grain Circulation and Safety, Nanjing 210023, China. Electronic address: fangyong10@nufe.edu.cn.
⁴ School of Agriculture and Food Science, Zhejiang A&F University, Hangzhou 311300, China.

PMID: 31927238
DOI: 10.1016/j.saa.2019.118012

Abstract

This work presents a fusion scheme to combine visible/near infrared spectroscopy and computer vision for on-line detection of Aspergillus spp. and Fusarium spp. contamination in stored maize. Spectroscopy and image information of 270 groups of maize kernels were collected at speed of 0.15 m/s. Principal component analysis indicated fungi growth on maize could be monitored by both techniques. Spectroscopy method was found sensitive for infection level identification, while computer vision was more effective for fungal strain recognition. Linear discriminant analysis based on fusion of spectral and image features provided 100% accuracy for discrimination of samples infected by different strains after stored for 12 d, which is at least 5.6% higher than single-type features. Classification rate of samples with different infection levels achieved 92.2%, also 5.5% and 10.0% higher than single technique. Moreover, data fusion improved colony counts prediction in samples by partial least squares regression, with root mean-square error of prediction value being reduced by 25.0% and 17.4%, respectively. This study demonstrated the superiority of data fusion for fungal detection in grain during on-line processing.

Keywords: Computer vision; Data fusion; Fungal contamination; Maize; On-line detection; Visible/near infrared spectroscopy.

MeSH terms

Aspergillus / growth & development
Aspergillus / isolation & purification*
Computer Simulation*
Discriminant Analysis
Food Contamination / analysis*
Food Microbiology
Fusarium / growth & development
Fusarium / isolation & purification*
Principal Component Analysis
Spectroscopy, Near-Infrared / methods*
Zea mays / microbiology*