Although several studies has been conducted
involving computer vision and some seed varieties other
than pepper, limited work has been reported on
classification of pepper seed varieties including computer
vision and neural networks. With this approach, the
objective of this study was to develop a computer vision
system based on neural networks and to determine the
best feature model, and neural network topology yielding
the best classification performance in recognizing pepper
seed varieties from one another. Since simple, effective,
and low cost image acquisition tools and techniques were used, this study was unique.