A Machine Learning Algorithm for Image Compression with application to Big Data Architecture: A Comparative Study

Abstract Background and Objective: In this paper, our paradigm is based on the workflow proposed by Tchagna et al and we now propose a new compression scheme to implement in this step of the workflow. The goal of this study is to propose a new compression scheme, based on machine learning, for vector quantization and orthogonal transformation, and to propose a method to implement this compression for big data architectures. Methods: We propose developed a machine learning algorithm for the implementation of the compression step. The algorithm was developed in MATLAB. The proposed compression scheme performed in three main steps. First, an orthogonal transform (Walsh or Chebyshev) was applied to image blocks in order to reduce the range of image intensities. Second, a machine learning algorithm based on K-Means clustering and splitting method is utilized to cluster image pixels. Third, the cluster IDs for each pixel is encoded using Huffman coding. The different parameters used to evaluate the efficiency of the proposed algorithm are presented. We used Spark architecture with the compression algorithm for simultaneous image compression. We compared our obtained results with literature results. The comparison was based on three parameters, Peak Signal to Noise Ratio (PSNR), MSSIM and computation time. Results: We applied our compression scheme to medical imagery. The obtained results of parameters for the Mean Structural Similarity (MSSIM) Index and Compression Ratio (CR) averaged 0.975% and 99.75%, respectively, for a codebook size equal to 256 for all test images. In comparison, with codebook size equal to 256 or 512, our compression method outperforms the literature methods. The comparison suggests the efficiency of our compression method. Conclusion: The MSSIM showed that the compression and decompression operation performed without loss of information. The comparison demonstrates the effectiveness of the proposed scheme

[1]  Mislav Grgic,et al.  Performance analysis of image compression using wavelets , 2001, IEEE Trans. Ind. Electron..

[2]  Michael W. Marcellin,et al.  JPEG2000 - image compression fundamentals, standards and practice , 2002, The Kluwer International Series in Engineering and Computer Science.

[3]  Jianhua Chen,et al.  ECG compression using the context modeling arithmetic coding with dynamic learning vector-scalar quantization , 2013, Biomed. Signal Process. Control..

[4]  Thangavelu Kesavamurthy,et al.  Volumetric Color Medical Image Compression for PACS Implementation( Biosensors: Data Acquisition, Processing and Control) , 2009 .

[5]  M. Karagodin,et al.  Image compression by means of Walsh transform , 2002, Proceedings of the 8th International Scientific and Practical Conference of Students, Post-graduates and Young Scientists Modern Technique and Technologies, 2002. MTT 2002..

[6]  Chengan Guo,et al.  An adaptive vector quantization approach for image segmentation based on SOM network , 2015, Neurocomputing.

[7]  Chiranjeevi Karri,et al.  Fast vector quantization using a Bat algorithm for image compression , 2016 .

[8]  Tzu-Chuen Lu,et al.  A Survey of VQ Codebook Generation , 2010, J. Inf. Hiding Multim. Signal Process..

[9]  Paulo S. G. de Mattos Neto,et al.  Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design , 2016, Sensors.

[10]  Yang Hu,et al.  Medical Image Compression Based on Vector Quantization with Variable Block Sizes in Wavelet Domain , 2012, Comput. Intell. Neurosci..

[11]  Adelaide Nicole Kengnou Telem,et al.  A Machine Learning Algorithm for Biomedical Images Compression Using Orthogonal Transforms , 2018, International Journal of Image, Graphics and Signal Processing.

[12]  Xingyuan Wang,et al.  A 2-D ECG compression algorithm based on wavelet transform and vector quantization , 2008, Digit. Signal Process..

[13]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[14]  J. K. Mandal,et al.  Windowed Huffman Coding with Limited Distinct Symbols , 2012 .

[15]  Tanasak Phanprasit Non-member,et al.  Medical image compression using vector quantization and system error compression , 2015 .

[16]  G. Chirikjian,et al.  Engineering Applications of Noncommutative Harmonic Analysis: With Emphasis on Rotation and Motion Groups , 2000 .

[17]  M.N.S. Swamy,et al.  A Comparison of Integer Cosine and Tchebichef Transforms for Image Compression Using Variable Quantization , 2015 .

[18]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[19]  Subramanian Kartheeswaran,et al.  A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system , 2017 .

[20]  Djemel Ziou,et al.  Image Quality Metrics: PSNR vs. SSIM , 2010, 2010 20th International Conference on Pattern Recognition.

[21]  Baskar Subramanian,et al.  Evolutionary optimized discrete Tchebichef moments for image compression applications , 2016 .

[22]  Roman Starosolski,et al.  New simple and efficient color space transformations for lossless image compression , 2014, J. Vis. Commun. Image Represent..

[23]  T. A. A. Tosta,et al.  Segmentation methods of H&E-stained histological images of lymphoma: A review , 2017 .

[24]  Spiros Fotopoulos,et al.  A novel training scheme for neural-network-based vector quantizers and its application in image compression , 2004, Neurocomputing.

[26]  Guoyin Wang,et al.  Lossless image compression based on integer Discrete Tchebichef Transform , 2016, Neurocomputing.

[27]  Olli Nevalainen,et al.  On the splitting method for vector quantization codebook generation , 1997 .

[28]  Ahmad Reza Naghsh-Nilchi,et al.  Medical ultrasound image compression using contextual vector quantization , 2012, Comput. Biol. Medicine.

[29]  Nur Azman Abu,et al.  Fast and Efficient 4x4 Tchebichef Moment Image Compression , 2010 .

[30]  A. Bovik,et al.  A universal image quality index , 2002, IEEE Signal Processing Letters.

[31]  Michael W. Marcellin,et al.  The Current Role of Image Compression Standards in Medical Imaging , 2017, Inf..

[32]  Allen Gersho,et al.  On the structure of vector quantizers , 1982, IEEE Trans. Inf. Theory.

[33]  Abdellatief Hussein A Ali.  Object-based VQ for image compression , 2015 .

[34]  Ming-Huwi Horng,et al.  Vector quantization using the firefly algorithm for image compression , 2012, Expert Syst. Appl..

[35]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.

[36]  Pagavathigounder Balasubramaniam,et al.  A new image denoising method using interval-valued intuitionistic fuzzy sets for the removal of impulse noise , 2016, Signal Process..

[37]  Nur Azman Abu,et al.  Efficient Discrete Tchebichef on SpectrumAnalysis of Speech Recognition , 2011 .

[39]  Shishir Kumar,et al.  Mathematical transforms and image compression: A review , 2010 .

[40]  David A. Huffman,et al.  A method for the construction of minimum-redundancy codes , 1952, Proceedings of the IRE.

[41]  Mininath R. Bendre,et al.  Analytics, challenges and applications in big data environment: a survey , 2016 .

[42]  Uma Ranjan Jena,et al.  Image compression based on vector quantization using cuckoo search optimization technique , 2016, Ain Shams Engineering Journal.

[43]  Ramakrishnan Kannan,et al.  Lossy image compression based on prediction error and vector quantisation , 2017, EURASIP Journal on Image and Video Processing.

[44]  Ramakrishnan Mukundan.  Transform Coding Using Discrete Tchebichef Polynomials , 2006 .

[45]  Aurelle Tchagna Kouanou,et al.  An optimal big data workflow for biomedical image analysis , 2018 .