Two More Strategies to Speed Up Connected Components Labeling Algorithms

This paper presents two strategies that can be used to improve the speed of Connected Components Labeling algorithms. The first one operates on optimal decision trees considering image patterns occurrences, while the second one articulates how two scan algorithms can be parallelized using multi-threading. Experimental results demonstrate that the proposed methodologies reduce the total execution time of state-of-the-art two scan algorithms.

[1]  Anil K. Jain,et al.  Handbook of Fingerprint Recognition , 2005, Springer Professional Computing.

[2]  Andrew H. Beck,et al.  Computational Pathology to Discriminate Benign from Malignant Intraductal Proliferations of the Breast , 2014, PloS one.

[3]  Rita Cucchiara,et al.  3DPeS: 3D people dataset for surveillance and forensics , 2011, J-HGBU '11.

[4]  Kesheng Wu,et al.  Two Strategies to Speed up Connected Component Labeling Algorithms , 2005 .

[5]  Costantino Grana,et al.  Optimized Connected Components Labeling with Pixel Prediction , 2016, ACIVS.

[6]  Kesheng Wu,et al.  Optimizing two-pass connected-component labeling algorithms , 2009, Pattern Analysis and Applications.

[7]  R. M. Haralick.  Some Neighborhood Operators , 1981 .

[8]  Viktor K. Prasanna,et al.  Parallel Architectures and Algorithms for Image Component Labeling , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Kenneth C. Sevcik,et al.  The synthetic approach to decision table conversion , 1976, CACM.

[10]  Chun-Jen Chen,et al.  A linear-time component-labeling algorithm using contour tracing technique , 2004, Comput. Vis. Image Underst..

[11]  Lionel Lacassagne,et al.  Parallel light speed labeling: An efficient connected component labeling algorithm for multi-core processors , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[12]  Kenji Suzuki,et al.  A Linear-Time Two-Scan Labeling Algorithm , 2007, 2007 IEEE International Conference on Image Processing.

[13]  Kenji Suzuki,et al.  Configuration-Transition-Based Connected-Component Labeling , 2014, IEEE Transactions on Image Processing.

[14]  Shlomo Argamon,et al.  Building a test collection for complex document information processing , 2006, SIGIR.

[15]  Costantino Grana,et al.  Optimal decision trees for local image processing algorithms , 2012, Pattern Recognit. Lett..

[16]  Roberto Vezzani,et al.  YACCLAB - Yet Another Connected Components Labeling Benchmark , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[17]  Rita Cucchiara,et al.  Optimized Block-Based Connected Components Labeling With Decision Trees , 2010, IEEE Transactions on Image Processing.

[18]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .