Efficient document image binarization using heterogeneous computing and parameter tuning

In the context of historical document analysis, image binarization is a first important step, which separates foreground from background, despite common image degradations, such as faded ink, stains, or bleed-through. Fast binarization has great significance when analyzing vast archives of document images, since even small inefficiencies can quickly accumulate to years of wasted execution time. Therefore, efficient binarization is especially relevant to companies and government institutions, who want to analyze their large collections of document images. The main challenge with this is to speed up the execution performance without affecting the binarization performance. We modify a state-of-the-art binarization algorithm and achieve on average a 3.5 times faster execution performance by correctly mapping this algorithm to a heterogeneous platform, consisting of a CPU and a GPU. Our proposed parameter tuning algorithm additionally improves the execution time for parameter tuning by a factor of 1.7, compared to previous parameter tuning algorithms. We see that for the chosen algorithm, machine learning-based parameter tuning improves the execution performance more than heterogeneous computing, when comparing absolute execution times.

[1]  T. Hothorn,et al.  Simultaneous Inference in General Parametric Models , 2008, Biometrical journal. Biometrische Zeitschrift.

[2]  Clément Chatelain,et al.  Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition , 2015, Electronic Imaging.

[3]  Konstantinos Zagoris,et al.  ICFHR2016 Handwritten Document Image Binarization Contest (H-DIBCO 2016) , 2016, 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[4]  John E. Stone,et al.  OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems , 2010, Computing in Science & Engineering.

[5]  Nicholas R. Howe,et al.  Document binarization with automatic parameter tuning , 2013, International Journal on Document Analysis and Recognition (IJDAR).

[6]  Daniel Díaz-Pernil,et al.  A Parallel Implementation of the Thresholding Problem by Using Tissue-Like P Systems , 2011, CAIP.

[7]  D. Greig,et al.  Exact Maximum A Posteriori Estimation for Binary Images , 1989 .

[8]  Ioannis Pratikakis,et al.  DIBCO 2009: document image binarization contest , 2011, International Journal on Document Analysis and Recognition (IJDAR).

[9]  Ioannis Pratikakis,et al.  ICDAR 2013 Document Image Binarization Contest (DIBCO 2013) , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[10]  Thomas M. Breuel,et al.  Efficient implementation of local adaptive thresholding techniques using integral images , 2008, Electronic Imaging.

[11]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[12]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[13]  Nadine Eberhardt,et al.  Computer Organization And Design 2nd Edition , 2016 .

[14]  Li Chen,et al.  JF-Cut: A Parallel Graph Cut Approach for Large-Scale Image and Video , 2015, IEEE Transactions on Image Processing.

[15]  Wayne Niblack,et al.  An introduction to digital image processing , 1986 .

[16]  Richard J. Anderson,et al.  Goldberg's Algorithm for Maximum Flow in Perspective: A Computational Study , 1991, Network Flows And Matching.

[17]  Nobuyuki Otsu,et al.  ATlreshold Selection Method fromGray-Level Histograms , 1979 .

[18]  Mohamed Akil,et al.  GPU parallel implementation of the new hybrid binarization based on Kmeans method (HBK) , 2018, Journal of Real-Time Image Processing.

[19]  N. Lavesson,et al.  Efficient Binarization for Historical Document Analysis , 2016 .

[20]  Matti Pietikäinen,et al.  Adaptive document image binarization , 2000, Pattern Recognit..

[21]  Ramazan Savas Aygün,et al.  Super-Thresholding: Supervised Thresholding of Protein Crystal Images , 2017, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[22]  Rupinder Kaur,et al.  Review of Robust Document Image BINARIZATION Technique for Degraded Document Images , 2015 .

[23]  Ioannis Pratikakis,et al.  ICFHR2014 Competition on Handwritten Document Image Binarization (H-DIBCO 2014) , 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[24]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[25]  Ioannis Pratikakis,et al.  ICDAR 2011 Document Image Binarization Contest (DIBCO 2011) , 2011, 2011 International Conference on Document Analysis and Recognition.

[26]  Marcus Liwicki,et al.  Document Image Binarization using LSTM: A Sequence Learning Approach , 2015, HIP@ICDAR.

[27]  Udaya B. Kogalur,et al.  Random Survival Forests for R , 2007 .

[28]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  P. Kohli,et al.  Efficiently solving dynamic Markov random fields using graph cuts , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[30]  Richard Szeliski,et al.  A Comparative Study of Energy Minimization Methods for Markov Random Fields , 2006, ECCV.

[31]  Ingemar J. Cox,et al.  A maximum-flow formulation of the N-camera stereo correspondence problem , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[32]  Rae-Hong Park,et al.  Document image binarization based on topographic analysis using a water flow model , 2002, Pattern Recognit..

[33]  Nicholas R. Howe,et al.  A Laplacian Energy for Document Binarization , 2011, 2011 International Conference on Document Analysis and Recognition.

[34]  Rahul Sharma,et al.  Parallel Implementation of Niblack’s Binarization Approach on CUDA , 2011 .

[35]  Rahul Sharma,et al.  Parallel Implementation of Souvola’s Binarization Approach on GPU , 2011 .

[36]  Carlos A. B. Mello,et al.  Parameter tuning for document image binarization using a racing algorithm , 2015, Expert Syst. Appl..

[37]  Josep Lladós,et al.  Boosting the handwritten word spotting experience by including the user in the loop , 2014, Pattern Recognit..

[38]  Ioannis Pratikakis,et al.  H-DIBCO 2010 - Handwritten Document Image Binarization Competition , 2010, 2010 12th International Conference on Frontiers in Handwriting Recognition.

[39]  Brij Mohan Singh,et al.  Parallel Implementation of Otsu’s Binarization Approach on GPU , 2011 .

[40]  Xin Chen,et al.  CUDA-accelerated fast Sauvola’s method on Kepler architecture , 2014, Multimedia Tools and Applications.

[41]  P. J. Narayanan,et al.  CUDA cuts: Fast graph cuts on the GPU , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[42]  Hemant Ishwaran,et al.  Random Survival Forests , 2008, Wiley StatsRef: Statistics Reference Online.

[43]  Davi Geiger,et al.  Segmentation by grouping junctions , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[44]  Volkmar Frinken,et al.  Handwriting recognition in historical documents using very large vocabularies , 2013, HIP '13.

[45]  Ioannis Pratikakis,et al.  Adaptive degraded document image binarization , 2006, Pattern Recognit..

[46]  D. R. Fulkerson,et al.  Flows in Networks. , 1964 .

[47]  Mohamed Akil,et al.  A new hybrid binarization method based on Kmeans , 2014, 2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP).

[48]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[49]  Alicia Fornés,et al.  A Coarse-to-Fine Word Spotting Approach for Historical Handwritten Documents Based on Graph Embedding and Graph Edit Distance , 2014, 2014 22nd International Conference on Pattern Recognition.

[50]  Carlos A. B. Mello,et al.  A new thresholding algorithm for document images based on the perception of objects by distance , 2014, Integr. Comput. Aided Eng..

[51]  Mohamed Cheriet,et al.  A learning framework for the optimization and automation of document binarization methods , 2013, Comput. Vis. Image Underst..

[52]  Richard M. Karp,et al.  Theoretical Improvements in Algorithmic Efficiency for Network Flow Problems , 1972, Combinatorial Optimization.

[53]  Ioannis Pratikakis,et al.  ICFHR 2012 Competition on Handwritten Document Image Binarization (H-DIBCO 2012) , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.