Efficient hierarchical graph partitioning for image segmentation by optimum oriented cuts

Abstract In this work, a hierarchical graph partitioning based on optimum cuts in graphs is proposed for unsupervised image segmentation, that can be tailored to the target group of objects, according to their boundary polarity, by extending Oriented Image Foresting Transform (OIFT). The proposed method, named UOIFT, theoretically encompasses as a particular case the single-linkage algorithm by minimum spanning tree (MST) and gives superior segmentation results compared to other approaches commonly used in the literature, usually requiring a lower number of image partitions to accurately isolate the desired regions of interest with known polarity. The method is supported by new theoretical results involving the usage of non-monotonic-incremental cost functions in directed graphs and exploits the local contrast of image regions, being robust in relation to illumination variations and inhomogeneity effects. UOIFT is demonstrated using a region adjacency graph of superpixels in medical and natural images.

[1]  Jorge Stolfi,et al.  The image foresting transform: theory, algorithms, and applications , 2004 .

[2]  Paulo André Vechiatto Miranda,et al.  Seed robustness of oriented relative fuzzy connectedness: core computation and its applications , 2017, Medical Imaging.

[3]  J. Siskind,et al.  Image segmentation with minimum mean cut , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[4]  Alexandre X. Falcão,et al.  An Iterative Spanning Forest Framework for Superpixel Segmentation , 2018, IEEE Transactions on Image Processing.

[5]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Paulo André Vechiatto Miranda,et al.  Seed Robustness of Oriented Image Foresting Transform: Core Computation and the Robustness Coefficient , 2017, ISMM.

[7]  Lucy A. C. Mansilla,et al.  Image Segmentation by Oriented Image Foresting Transform with Geodesic Star Convexity , 2013, CAIP.

[8]  Lucy A. C. Mansilla,et al.  Bandeirantes: A Graph-Based Approach for Curve Tracing and Boundary Tracking , 2017, ISMM.

[9]  Krzysztof Ciesielski,et al.  Graph-Based Segmentation with Local Band Constraints , 2019, DGCI.

[10]  Lucy A. C. Mansilla,et al.  Oriented Image Foresting Transform Segmentation by Seed Competition , 2014, IEEE Transactions on Image Processing.

[11]  Roberto de Alencar Lotufo,et al.  Seed-Relative Segmentation Robustness of Watershed and Fuzzy Connectedness Approaches , 2007 .

[12]  Lucy A. C. Mansilla,et al.  Oriented image foresting transform segmentation with connectivity constraints , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[13]  Jean Cousty,et al.  A Hierarchical Image Segmentation Algorithm Based on an Observation Scale , 2012, SSPR/SPR.

[14]  Lucy A. C. Mansilla,et al.  Image segmentation by oriented image foresting transform: Handling ties and colored images , 2013, 2013 18th International Conference on Digital Signal Processing (DSP).

[15]  Lucy A. C. Mansilla,et al.  Efficient Unsupervised Image Segmentation by Optimum Cuts in Graphs , 2018, CIARP.

[16]  Richard M. Leahy,et al.  An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Ming Zhang,et al.  Improving the Graph-Based Image Segmentation Method , 2006, 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06).

[18]  Jean Cousty,et al.  Incremental Algorithm for Hierarchical Minimum Spanning Forests and Saliency of Watershed Cuts , 2011, ISMM.

[19]  Hui Xiang,et al.  An Improved Graph-Based Image Segmentation Algorithm and Its GPU Acceleration , 2011, 2011 Workshop on Digital Media and Digital Content Management.

[20]  Jean Cousty,et al.  Hierarchical Segmentations with Graphs: Quasi-flat Zones, Minimum Spanning Trees, and Saliency Maps , 2018, Journal of Mathematical Imaging and Vision.

[21]  Krzysztof Ciesielski,et al.  Path-Value Functions for Which Dijkstra’s Algorithm Returns Optimal Mapping , 2018, Journal of Mathematical Imaging and Vision.

[22]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[23]  Jeffrey Mark Siskind,et al.  Image Segmentation with Ratio Cut , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Paulo André Vechiatto Miranda,et al.  Oriented relative fuzzy connectedness: theory, algorithms, and its applications in hybrid image segmentation methods , 2015, EURASIP J. Image Video Process..

[25]  Lucy A. C. Mansilla,et al.  Oriented Image Foresting Transform Segmentation: Connectivity Constraints with Adjustable Width , 2016, 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI).

[26]  Alexandre Gonçalves Silva,et al.  Efficient computation of new extinction values from extended component tree , 2011, Pattern Recognit. Lett..

[27]  Roberto de Alencar Lotufo,et al.  iamxt: Max-tree toolbox for image processing and analysis , 2017, SoftwareX.

[28]  Jitendra Malik,et al.  Normalized Cuts and Image Segmentation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Jayaram K. Udupa,et al.  A General and Balanced Region-Based Metric for Evaluating Medical Image Segmentation Algorithms , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[30]  Paulo André Vechiatto Miranda,et al.  Image segmentation by image foresting transform with geodesic band constraints , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[31]  Vladlen Koltun,et al.  Geodesic Object Proposals , 2014, ECCV.

[32]  Jean Cousty,et al.  Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity , 2017, Math. Morphol. Theory Appl..

[33]  Alexandre X. Falcão,et al.  IFT-SLIC: A General Framework for Superpixel Generation Based on Simple Linear Iterative Clustering and Image Foresting Transform , 2015, 2015 28th SIBGRAPI Conference on Graphics, Patterns and Images.