A novel, invariant elliptic Fourier coefficient based classification of cereal grains

An algorithm to classify cereal grains, namely: barley, oats, rye and wheat (Canada Western Amber Durum (CWAD) and Canada Western Red Spring (CWRS)) based on grain kernel shapes using invariant elliptic Fourier descriptors (IEFDs) was developed. Boundary contours were extracted from the digital images of kernels, expressed as chain-coded points and then approximated by 13 Fourier harmonics. After normalisation of the size, rotation and starting point of the contours, the IEFDs were determined. Based on the first three IEFDs, perfect classification was achieved for barley, CWAD, CWRS and rye. The classification accuracies of oats were 99.7% and 100% for the first three and five IEFDs, respectively.

► Novel algorithm to classify cereal grains based on invariant elliptic Fourier descriptors. ► Boundary contours extracted and approximated by 13 Fourier harmonics. ► Using the first three IEFDs, perfect classification for barley, CWAD, CWRS and rye. ► Classification accuracy better than available model with hundreds of kernel features.