Image Processing Based Object Height Recovery to Reconstruct 3D Objects
Ali Abbar Khleif, Ahmed Abdulraheem Shnawa · American Scientific Research Journal for Engineering, Technology, and Sciences (Global Society of Scientific Research and Researchers) · 2018
An approach for automatic 3D object re-construction using object’s shadow. This research apply and utilize machine vision technology to develop a non-contact and rapid measurement system capable of measuring and reconstruct three-dimensional object attributes with an appropriate accuracy and to facilitating the possibility of reconstruction of three-dimensional objects by processing two-dimensional images. Machine vision consists of two main parts: the first part is eye in hand configuration that used to capture 2D image to the object from a top view with constant distance from the platform that carry the object. The second part is the light source which positioned at a predefined distance to generate shadow of object. To use this technology in an optimum way it needs image processing and computations in the form of a software that can meet our requirements of applying this technology. By using pixel by pixel scanning to extract image feature using MATLAB program and achieve image processing technique to get useful information from image very close to real measurements are gained. The technique is tested on three different objects that have different shape, size and material. The developed algorithm that make use of object height information for the directions associated with the incident light and the generated object shadows founded the maximum error in sample one is (0.0779) in length attribute and the minimum error that well be found (0.0543)in width attribute with sample two.