Spatial and spectral morphological template matching

Template matching is a very topical issue in a wide range of imaging applications. Mathematical morphology offers the hit-or-miss transform, an operator which has been successfully applied for template matching in binary images. More recently, it has been extended to grayscale images and even to multivariate images. Nevertheless, these extensions, despite being relevant from a theoretical point-of-view, might lack practical interest due to the inherent difficulty to set up correctly the transform and its parameters (e.g. the structuring functions). In this paper, we propose a new and more intuitive operator which allows for morphological template matching in multivariate images from both a spatial and spectral point of view. We illustrate the potential of this operator in the context of remote sensing.

[1]  Sébastien Lefèvre,et al.  A comparative study on multivariate mathematical morphology , 2007, Pattern Recognit..

[2]  Christophe Collet,et al.  A robust hit-or-miss transform for template matching applied to very noisy astronomical images , 2009, Pattern Recognit..

[3]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[4]  Sidharta Gautama,et al.  Optimisation of a coastline extraction algorithm for object-oriented matching of multisensor satellite imagery , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[5]  Nicolas Passat,et al.  Grey-level hit-or-miss transforms - Part I: Unified theory , 2007, Pattern Recognit..

[6]  Sébastien Lefèvre,et al.  A Multivariate Hit-or-Miss Transform for Conjoint Spatial and Spectral Template Matching , 2008, ICISP.

[7]  Pierre Soille,et al.  Advances in the Analysis of Topographic Features on Discrete Images , 2002, DGCI.

[8]  Pierre Gançarski,et al.  Interactive video segmentation based on quasi-flat zones , 2011, 2011 7th International Symposium on Image and Signal Processing and Analysis (ISPA).

[9]  Jesús Angulo,et al.  Hit-or-Miss Transform in Multivariate Images , 2010, ACIVS.

[10]  Sébastien Lefèvre,et al.  COASTLINE EXTRACTION IN VHR IMAGERY USING MATHEMATICAL MORPHOLOGY WITH SPATIAL AND SPECTRAL KNOWLEDGE , 2008 .

[11]  Cécile Barat,et al.  Virtual double-sided image probing: A unifying framework for non-linear grayscale pattern matching , 2010, Pattern Recognit..

[12]  C. Ronse,et al.  A Lattice-Theoretical Morphological View on Template Extraction in Images , 1996, J. Vis. Commun. Image Represent..

[13]  Uwe D. Hanebeck,et al.  Template matching using fast normalized cross correlation , 2001, SPIE Defense + Commercial Sensing.

[14]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[15]  Sébastien Lefèvre,et al.  A hit-or-miss transform for multivariate images , 2009, Pattern Recognit. Lett..

[16]  G. Matheron.  Random Sets and Integral Geometry , 1976 .

[17]  Ian L Turner,et al.  Shoreline Definition and Detection: A Review , 2005 .

[18]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .