Investigation of In-Shell Seeds mmW Classification

The promising results obtained from using mmW imaging combined with machine learning (ML) tools for classification of soft fruits such apples and peaches, prompted us to evaluate the effectiveness of this approach on more difficult cases, namely specific types of in-shell seeds, such as almonds and walnuts. We propose two classification schemes, one based on images processing and the other on the direct exploitation of the real and imaginary parts of the measured <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$S_{11}$</tex>. The presence of the shell makes the problem more difficult than for soft fruits. This is reflected in the classification result, which drops from 100 % for soft fruits to 66 % for the nuts.