A new approach to aflatoxin detection in chili pepper by machine vision

Date

2012-09-01

Author

ATAŞ, MUSA
Yardimci, Y.
Temizel, Alptekin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

89
views

0
downloads

Aflatoxins are the toxic metabolites of Aspergillus molds, especially by Aspergillus flavus and Aspergillus parasiticus. They have been studied extensively because of being associated with various chronic and acute diseases especially immunosuppression and cancer. Aflatoxin occurrence is influenced by certain environmental conditions such as drought seasons and agronomic practices. Chili pepper may also be contaminated by aflatoxins during harvesting, production and storage. Aflatoxin detection based on chemical methods is fairly accurate. However, they are time consuming, expensive and destructive. We use hyperspectral imaging as an alternative for detection of such contaminants in a rapid and nondestructive manner. In order to classify aflatoxin contaminated chili peppers from uncontaminated ones, a compact machine vision system based on hyperspectral imaging and machine learning is proposed. In this study, both UV and Halogen excitations are used. Energy values of individual spectral bands and also difference images of consecutive spectral bands were utilized as feature vectors. Another set of features were extracted from those features by applying quantization on the histogram of the images. Significant features were selected based on proposed method of hierarchical bottleneck backward elimination (HBBE), Guyon's SVM-RFE, classical Fisher discrimination power and Principal Component Analysis (PCA). Multi layer perceptrons (MLPs) and linear discriminant analysis (LDA) were used as the classifiers. It was observed that with the proposed features and selection methods, robust and higher classification performance was achieved with fewer numbers of spectral bands enabling the design of simpler machine vision systems.

Subject Keywords

Machine vision, Aflatoxin detection, Hyperspectral imaging, Food safety, Feature extraction, Feature subset selection

URI

https://hdl.handle.net/11511/30484

Journal

COMPUTERS AND ELECTRONICS IN AGRICULTURE

DOI

https://doi.org/10.1016/j.compag.2012.06.001

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Aflatoxin Contaminated Chili Pepper Detection by Hyperspectral Imaging and Machine Learning Ataş, Musa; Yardimci, Yasemin; Temizel, Alptekin (2011-04-27) Mycotoxins are toxic secondary metabolites produced by fungi. They have been demonstrated to cause various health problems in humans, including immunosuppression and cancer. A class of mycotoxins, aflatoxins, has been studied extensively because they have caused many deaths particularly in developing countries. Chili pepper is also prone to aflatoxin contamination during harvesting, production and storage periods. Chemical methods to detect aflatoxins are quite accurate but expensive and destructive in natu...
Characterization of proteome alterations in Phanerochaete chrysosporium in response to lead exposure Yildirim, Volkan; ÖZCAN, Servet; Becher, Doerte; Buettner, Knut; Hecker, Michael; Özcengiz, Gülay (Springer Science and Business Media LLC, 2011-03-09) Background: Total soluble proteome alterations of white rot fungus Phanerochaete chrysosporium in response to different doses (25, 50 and 100 mu M) of Pb (II) were characterized by 2DE in combination with MALDI-TOF-MS.
A new strategy for the synthesis of pyridines from N-propargylic beta-enaminothiones Kelgokmen, Yilmaz; Zora, Metin (Royal Society of Chemistry (RSC), 2019-03-07) A new method for the synthesis of 2,4,5-trisubstituted pyridines from N-propargylic beta-enaminothiones is reported. beta-Enaminothiones were prepared by thionation of the corresponding beta-enaminones with Lawesson's reagent. When treated with diisopropylamine in DMF at room temperature, N-propargylic beta-enaminothiones yielded 2,4,5-trisubstituted pyridines in moderate to high yields, along with small amounts of 2-methylene-2,3-dihydro-1,4-thiazepines. The reaction was found to be general for a broad ran...
A kinetic study on the decolorization of aqueous solutions of acid Red-151 by ozonation Ozbelge, TA; Erol, F; Ozbelge, O (Informa UK Limited, 2003-01-01) The ozonation kinetics of an azo dye, namely, Acid Red-151 was investigated. Effects of pH, initial ozone, and initial dye concentrations on the ozonation of the dye were studied. The reaction orders were found to be one with respect to both ozone and dye concentrations for the studied pH range of 2.5-10. The reaction rate constants were obtained as 125.8, 95.4, 87.9, and 129.9 L mmol(-1) min(-1) at the pH values of 2.5, 5, 7, and 10, respectively. The initial ozonation rate decreased with the increasing pH...
Microbial detoxification of groundnut meal naturally contaminated with aflatoxin using rhodococcus erythropolis Doğan, Önay Burak; Çekmecelioğlu, Deniz; Bozoğlu, Faruk; Department of Food Engineering (2015) Aflatoxins are highly mutagenic toxins with carcinogenic effects produced as secondary metabolites by fungal species Aspergillus flavus and Aspergillus parasiticus under certain conditions. Chronic or acute consumption of aflatoxins found in food and feed products possesses great health risks. It is particularly an important problem in animal feed from food waste and by-products. Therefore there is growing need to eliminate aflatoxins from contaminated products. In this study, first the optimum growth condi...

Citation Formats

M. ATAŞ, Y. Yardimci, and A. Temizel, “A new approach to aflatoxin detection in chili pepper by machine vision,” COMPUTERS AND ELECTRONICS IN AGRICULTURE, pp. 129–141, 2012, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/30484.