An Image Mapping Approach for Quick Dissimilarity Detection of Binary Images

Abstract

In this paper we present an approach for the quick detection of dissimilar and similar binary images. The approach conforms to the Probabilistic Matching Model for Binary Images (PMMBI) that ascertained that detecting dissimilarity between binary images can be done quickly by randomly examining a few points between two images. The approach is based on exploiting the 15 binary image mapping variations that are possible when mapping pixels between binary images and inspecting their tuple size. We call this approach the Dissimilar Detection via Mapping (DDM). We present tests with real images.