S. Babazadeh; P. Ahmadi Moghaddam; A. Sabatyan; F. Sharifian
Abstract
The overall objective of this research is to check the abilities of two non-destructive techniques, the digital imaging (DI) and laser light backscattering imaging (LLBI), on detection of α-solanine toxicant in potatoes. Potato samples were classified in healthy and toxic categories based on the ...
Read More
The overall objective of this research is to check the abilities of two non-destructive techniques, the digital imaging (DI) and laser light backscattering imaging (LLBI), on detection of α-solanine toxicant in potatoes. Potato samples were classified in healthy and toxic categories based on the amount of α-solanine. For quantifying α-solanine in potato tubers, high-performance liquid chromatography (HPLC) has been used. The results of classification showed that single layer perceptron neural networks can classify potatoes with the accuracies of 94.28% and 98.66% by DI and LLBI systems (Donald cultivar), respectively. It can be said that LLBI systems might take precedent over DI systems due to their high accuracy, rapidity, and industrial capability.
