The Tree of Shapes Turned into a Max-Tree: A Simple and Efficient Linear Algorithm

The Tree of Shapes (ToS) is a morphological, tree-based representation of an image, translating the inclusion of its level lines. It features many invariants to image changes, which make it well-suited for many applications in image processing and pattern recognition. In this paper, we propose a way of turning a ToS computation into a Max-Tree computation. The latter has been widely studied, and many efficient algorithms (including parallel ones) have been developed. Furthermore, we develop a specific optimization to speed-up the common 2D case. It follows a simple and efficient algorithm, running in linear time with a low memory footprint, that outperforms other currently used algorithms. For Reproducible Research purpose, we distribute our code as free software.

[1]  Philippe Salembier,et al.  Antiextensive connected operators for image and sequence processing , 1998, IEEE Trans. Image Process..

[2]  Jon Atli Benediktsson,et al.  Region-based classification of remote sensing images with the morphological tree of shapes , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[3]  Laurent Najman,et al.  On Making nD Images Well-Composed by a Self-dual Local Interpolation , 2014, DGCI.

[4]  E. R. Urbach,et al.  Shape-only granulometries and gray-scale shape filters , 2002 .

[5]  Michael H. F. Wilkinson,et al.  Mask-Based Second-Generation Connectivity and Attribute Filters , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Michel Couprie,et al.  Building the Component Tree in Quasi-Linear Time , 2006, IEEE Transactions on Image Processing.

[7]  Yongchao Xu,et al.  Introducing the Dahu Pseudo-Distance , 2017, ISMM.

[8]  Ron Kimmel,et al.  Image editing using level set trees , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[9]  Laurent Najman,et al.  How to Make nD Functions Digitally Well-Composed in a Self-dual Way , 2015, ISMM.

[10]  Yuqing Song,et al.  A Topdown Algorithm for Computation of Level Line Trees , 2007, IEEE Transactions on Image Processing.

[11]  Julie Delon,et al.  Shape-based Invariant Texture Indexing , 2010, International Journal of Computer Vision.

[12]  Thierry Géraud,et al.  Planting, Growing, and Pruning Trees: Connected Filters Applied to Document Image Analysis , 2014, 2014 11th IAPR International Workshop on Document Analysis Systems.

[13]  Jean-Michel Morel,et al.  Topographic Maps and Local Contrast Changes in Natural Images , 1999, International Journal of Computer Vision.

[14]  Laurent Najman,et al.  A Quasi-linear Algorithm to Compute the Tree of Shapes of nD Images , 2013, ISMM.

[15]  Yongchao Xu,et al.  Salient level lines selection using the Mumford-Shah functional , 2013, 2013 IEEE International Conference on Image Processing.

[16]  Jon Atli Benediktsson,et al.  Remote Sensing Image Classification Using Attribute Filters Defined Over the Tree of Shapes , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Marcelo Bertalmío,et al.  Region Based Segmentation Using the Tree of Shapes , 2006, 2006 International Conference on Image Processing.

[18]  Pascal Monasse,et al.  Fast computation of a contrast-invariant image representation , 2000, IEEE Trans. Image Process..

[19]  Thierry Géraud,et al.  Self-duality and Digital Topology: Links Between the Morphological Tree of Shapes and Well-Composed Gray-Level Images , 2015, ISMM.

[20]  Jón Atli Benediktsson,et al.  Automatic Attribute Profiles , 2017, IEEE Transactions on Image Processing.

[21]  Raffay Hamid,et al.  Toward a Generalizable Image Representation for Large-Scale Change Detection: Application to Generic Damage Analysis , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Damien Garcia,et al.  Speckle spot detection in ultrasound images: Application to speckle reduction and speckle tracking , 2014, 2014 IEEE International Ultrasonics Symposium.

[23]  Ronald Jones,et al.  Connected Filtering and Segmentation Using Component Trees , 1999, Comput. Vis. Image Underst..

[24]  Thierry Géraud,et al.  MToS: A Tree of Shapes for Multivariate Images , 2015, IEEE Transactions on Image Processing.

[25]  V. Caselles,et al.  Geometric Description of Images as Topographic Maps , 2009 .

[26]  Thierry Géraud,et al.  Morphological object picking based on the color tree of shapes , 2015, 2015 International Conference on Image Processing Theory, Tools and Applications (IPTA).

[27]  Pascal Monasse,et al.  Constructing the Tree of Shapes of an Image by Fusion of the Trees of Connected Components of Upper and Lower Level Sets , 2008 .

[28]  Yongchao Xu,et al.  Connected Filtering on Tree-Based Shape-Spaces , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Ewa Kijak,et al.  Beyond MSER: Maximally Stable Regions using Tree of Shapes , 2015, BMVC.

[30]  Yongchao Xu,et al.  Hierarchical Segmentation Using Tree-Based Shape Spaces , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Matthias Book,et al.  Parallel Computation of Component Trees on Distributed Memory Machines , 2018, IEEE Transactions on Parallel and Distributed Systems.

[32]  Yongchao Xu,et al.  Hierarchical image simplification and segmentation based on Mumford-Shah-salient level line selection , 2016, Pattern Recognit. Lett..

[33]  Thierry Géraud,et al.  A Comparative Review of Component Tree Computation Algorithms , 2014, IEEE Transactions on Image Processing.

[34]  Thierry Géraud,et al.  A first parallel algorithm to compute the morphological tree of shapes of nD images , 2014, 2014 IEEE International Conference on Image Processing (ICIP).