A new framework for measuring volume of axisymmetric food products using computer vision system based on cubic spline interpolation

Abstract

Volume is an important factor to determine the external quality of a food product. The volume measurement of food product is not a simple process if it is performed manually. For alternative, several volume measurement methods for food products have been proposed using 2D and 3D computer vision. Disk method and frustum cone method have been applied in many 2D computer visions to approximate the volume of axisymmetric food products. These methods were less in accuracy, since it used piecewise linear function to approximate the boundary of the object. This paper aims to propose a new framework for measuring the volume of axisymmetric food product based on cubic spline interpolation. Cubic spline interpolation is employed to construct a piecewise continuous polynomial of the boundary of object from captured image. The polynomial is then integrated to approximate the volume of the object. The simulation result shows that the proposed framework produced accurate volume measurement result.