Morphological Template Matching in Color Images

Sébastien Lefèvre (1) , Erchan Aptoula (2) , Benjamin Perret (3) , Jonathan Weber (4)

1 OBELIX - Environment observation with complex imagery
2 Okan University
3 LIGM - Laboratoire d'Informatique Gaspard-Monge
4 QGAR - Querying Graphics through Analysis and Recognition

Template matching is a fundamental problem in image analysis and computer vision. It has been addressed very early by Mathematical Morphology, through the well-known Hit-or-Miss Transform. In this chapter, we review most of the existing works on this morphological template matching operator, from the standard case of binary images to the (not so standard) case of grayscale images and the very recent extensions to color and multivariate data. We also discuss the issues raised by the application of the HMT operator to the context of template matching and provide guidelines to the interested reader. Various use cases in different application domains have been provided to illustrate the potential impact of this operator.

Mots clés: Mathematical morphology; Hit-or-miss transform; Template matching; Color image

Domaines: Traitement des images [eess.IV]

Sébastien Lefèvre, Erchan Aptoula, Benjamin Perret, Jonathan Weber. Morphological Template Matching in Color Images. Advances in Low-Level Color Image Processing, 11, Springer Netherlands, pp.241-277, 2014, Lecture Notes in Computational Vision and Biomechanics, 978-94-007-7583-1. ⟨10.1007/978-94-007-7584-8_8⟩. ⟨hal-01111954⟩