Wall Size Prediction from 2D Images with the Help of Reference Objects

Digital image processing has been widely used in many applications in various science domains. Detection, recognition, extraction and tracking of an object can be given as examples of such applications on 2D images. In this study, we present an approach to predict the size of a wall in terms of width and height, on 2D images by using a reference object. The size of the reference object is already known beforehand and its size gives us hints to predict the size of the wall, which is called target object. The proposed approach has been tested and evaluated on a real world images and the performance results are presented at the end of the paper.