Wheat is one of the main nutrients used
in the world. Consumption of foodstuff produced from quality wheat is of great
importance for healthy generations. It is necessary to separate the high and
low quality wheat. In this paper, a new recognition method for quality wheat
and unclassified wheat is presented. The most distinctive feature for
determination of wheat quality is its shape. In this study, objects are first
represented by a few descriptive points on their contours obtained from their
images. Neighboring points are connected by linear or conical curve fitting.
The objects are then represented by an attribute vector constructed from
parameters of the curves. Finally, these vectors are used to classify objects
(wheat) using support vector machines (svm). Performance is improved with cross
validation for each class.
Journal Section | Makaleler |
---|---|
Authors | |
Publication Date | October 10, 2019 |
Published in Issue | Year 2019 Volume: 3 Issue: 2 |