Title: Detection of contaminated hazelnuts and ground red chili pepper flakes by multispectral imaging Authors
|Kalkan, H. -|
|Beriat, P. -|
|Yardimci, Y. -|
Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: March 20, 2011
Publication Date: June 1, 2011
Repository URL: http://handle.nal.usda.gov/10113/49537
Citation: Kalkan, H., Beriat, P., Pearson, T.C., Yardimci, Y. 2011. Detection of contaminated hazelnuts and ground red chili pepper flakes by multispectral imaging. Computers and Electronics in Agriculture. 77:28-34. Interpretive Summary: A method was developed to detect aflatoxin contaminated hazelnuts and chili pepper flakes. Color images were used as well as images of non-visible light in the near infrared region. The method utilizes a new feature selection algorithm that minimizes the number of near infrared images that must be acquired; thus making a potential system affordable and able to inspect large quantities of foods very quickly. The method developed identifies over 90% of the contaminated hazelnuts and 80% of the contaminated chili pepper flakes. The method developed should also find uses with other foods such as corn, wheat and other tree nuts for food safety inspection and sorting.
Technical Abstract: Mycotoxins are the toxic metabolites of certain filamentous fungi and have been demonstrated to cause various health problems in humans, including immunosuppression and cancer. Among them, the aflatoxins have received greater attention because they are potent carcinogens and are responsible for many human deaths per annum, mostly in non-industrialized countries. Various regulatory agencies have enforced limits on the concentrations of these toxins in foods and feeds involved in international commerce. Hyperspectral and multispectral imaging are becoming increasingly important for rapid and nondestructive testing for the presence of such contaminants. However, the high number of spectral bands needed may render such image acquisition systems too complex, expensive and slow. Moreover, they tend to generate too much data, making effective processing of this information in real time difficult. In this study, a two-dimensional local discriminant bases algorithm was developed to detect the location of the discriminative features in the multispectral data space. The algorithm identifies the optimal band pass width and center frequencies of optical filters to be used for a multispectral imaging system. This was applied to a multispectral imaging system used to detect aflatoxin-contaminated hazelnut kernels and red chili peppers. Classification accuracies of 92.3% and 80% were achieved for aflatoxin-contaminated and uncontaminated hazelnuts and red chili peppers, respectively. The aflatoxin concentrations are decreased from 608 ppb to 0.84 ppb for tested hazelnuts and from 38.26 ppb to 22.85 ppb for red chili peppers by removal of the nuts/peppers that are classified as aflatoxin-contaminated. The algorithm was also used to classify fungal contaminated and uncontaminated hazelnut kernels, and an accuracy of 97.4% was achieved for this broader classification.