Differential Coding-Based Medical Image Compression

  • P. Chitra
  • M. Mary Shanthi RaniEmail author
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 31)


Modern trends of technology face the challenges of cost-effective massive data storage and transmission. Image compression is a master key for this issue. Basically, the process of image compression reduces redundant and irrelevant information from the original data resulting in reduced data file size. Vector quantization is a lossy image compression technique which helps to achieve higher compression with less computation complexity. The aim of the proposed work is to develop a novel medical image compression method that blends differential encoding and vector quantization (VQ). The basic idea is to transform the input image blocks into a set of difference vectors (difference between the each pixel intensity value and its respective mean). The difference vectors are normalized to preserve the sign and further quantized to generate the codebook. The algorithm is also investigated with other statistical moments like median and mode for finding the difference vectors. The experimental results with test medical images have demonstrated better performance of the proposed method when compared to similar methods.


  1. 1.
    Somasundaram K, Shanthi Rani MM (2011) Novel K-means algorithm for compressing images. Int J Comput Appl 18(8):9–13CrossRefGoogle Scholar
  2. 2.
    Somasundaram K, Shanthi Rani MM (2011) Mode based K-means algorithm with residual vector quantization for compressing images. In: International conference on “control, computation and information systems”. Springer CCIS 140, pp 105–112Google Scholar
  3. 3.
    Shanthi Rani MM, Chitra P, Vijayalakshmi R Image compression based on vector quantization using novel genetic algorithm for compressing medical images. Int J Comput Eng Appl XII(I):104–114Google Scholar
  4. 4.
    Chiranjeevi K, Jena U (2016) Fast vector quantization using a Bat algorithm for image compression. Eng Sci Technol Int J 19:769–781CrossRefGoogle Scholar
  5. 5.
    Sumalatha R, Subramanyam MV (2015) Hierarchical lossless image compression for telemedicine applications. In: Eleventh international multi-conference on information processing-2015 (IMCIP-2015). Procedia Comput Sci 54:838–848CrossRefGoogle Scholar
  6. 6.
    Huiyan J et al (2012) Medical image compression based on vector quantization with variable block sizes in wavelet domain. Hindawi Publishing Corporation. Comput Intell Neurosci 2012:3, Article ID 541890Google Scholar
  7. 7.
    Bhattacharyya et al (2014) Vector quantization based image compression using generalized improved fuzzy clustering. In: 2014 international conference on control, instrumentation, energy & communication (CIEC):662–666Google Scholar
  8. 8.
    Robert Y, Li et al (2002) Image compression using transformed vector quantization. Image Vis Comput Elsevier 20:37–45Google Scholar
  9. 9.
    Abouali AH (2015) Object-based VQ for image compression, Elsevier. Ain Shams Eng J 6:211–216CrossRefGoogle Scholar
  10. 10.
    Chitra P, Shanthi Rani MM (2018) Modified haar wavelet based method for compressing medical images. Int J Eng Techniq (IJET) 4(1)Google Scholar
  11. 11.
    Phanprasit Tanasak et al (2015) Medical image compression using vector quantization and system error compression. IEE J Trans Electr Electron Eng 10:554–566CrossRefGoogle Scholar
  12. 12.
    Shanthi Rani MM, Chitra P, Mahalakshmi K (2017) A novel approach of vector quantization using modified particle swarm optimization algorithm for generating efficient codebook. Int J Advanc Res Comput Sci 8(9)CrossRefGoogle Scholar
  13. 13.
    Shanthi Rani MM, Chitra P (2009) Adaptive classified pattern matching vector quantization approach for compressing images. In: 2009 international conference on image processing, computer vision & pattern recognition proceedings, Las Vegas, USA, pp 532–538Google Scholar
  14. 14.
    Shanthi Rani MM (2014) Residual vector quantization based iris image compression. Int J Comput Intell Stud 3(4):329–334, Inderscience PublishersCrossRefGoogle Scholar
  15. 15.
    Shanthi Rani MM, Chitra P (2016) Novel hybrid method of haar-wavelet and residual vector quantization for compressing medical images. In: 2016 IEEE conference on advances in computer applications (ICACA), vol 1, pp 321–326Google Scholar
  16. 16.
    Shanthi Rani MM, Chitra P (2018) A hybrid medical image coding method based on haar wavelet transform and particle swarm optimization technique. Int J Pure Appl Math 118(8):3056–3067Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science and ApplicationsThe Gandhigram Rural Institute - Deemed to be UniversityGandhigramIndia

Personalised recommendations