FOURIER-BASED SEPARATION TECHNIQUE FOR SHAPE GRADING OF POTATOES USING MACHINE VISION

A Fourier-based shape separation method was developed for shape gradin g of potatoes using machine vision for automated inspection. The relat ionship between object shape and its boundary spectrum values in Fouri er domain was explored for shape extraction. A new and fast method of using Green's theorem and boundary Fourier coefficients was given for estimating elongation of an object. A shape separator based on harmoni cs of the transform was defined for potato shape separation. Tests sho wed the shape separator was effective and efficient for difficult shap e separation. The machine vision system developed has a great potentia l to assist humans for automated potato grading.