A review of recent advances in the hit-or-miss transform

The Hit-or-Miss Transform (HMT) is a well known morphological transform that is capable of identifying features in digital images. There has been significant interest in using and extending this transform since it was defined in the late sixties. A large number of authors have proposed extensions of the original binary HMT in order that it can be applied to greyscale data. Various researchers have also extended the HMT in different ways to make it more robust to noise. Other works describe extensions of the HMT which can be applied to colour images and 3D data. This paper reviews a number of these extensions with a particular focus on extensions of the HMT for processing greyscale data and for making the binary and greyscale HMTs more robust in the presence of noise. This paper takes the reader through 40 years of developments in the HMT before explaining the current state-of-the-art techniques in this interesting and topical area of research.