BINARY MORPHOLOGICAL IMAGE PROCESSING ALGORITHM IN COMPUTER VISION APPLICATION

Abstract

Binary morphological image processing algorithm in computer vision application is reported.  The algorithm is simple in implementation and efficient in computation.  It is divided into two main parts, firstly method of enhancing occurring defects on the surface of manufactured product is introduced and secondly binary morphological filtering technique is developed to remove noise and other artifacts completely from the product binary images before feature extraction.  It has been shown that the algorithm produces good results when tested on a number of manufactured products.  The results presented in real images of a ceramic wall tile and biscuit shows the effectiveness of the algorithm.