Super-Resolution via Particle Swarm Optimization Variants

  • Maria Aparecida de Jesus
  • Vania V. Estrela
  • Osamu Saotome
  • Dalmo Stutz
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 25)


Super-resolution (SR) reconstructs a high-resolution (HR) image from a set of low-resolution (LR) pictures and restores an HR video from a group of neighboring LR frames. Optimization tries to overcome the image acquisition limitations, the ill-posed nature of the SR problem, to facilitate content visualization and scene recognition. Particle swarm optimization (PSO) is a superb optimization algorithm used for all sorts of problems despite its tendency to be stuck in local minima. To handle ill-posedness, different PSO variants (hybrid versions) have been proposed trying to explore factors such as the initialization of the swarm, insertion of a constriction coefficient, mutation operators, and the use of an inertia weight. Hybridization involves combining two (or more) techniques wisely such that the resultant algorithm contains the good characteristics of both (or all) the methods. Interesting hybridization techniques include many local and global search approaches. Results for the SR reconstruction of still and video images are presented for the PSO and the HPSO algorithms.


Super-resolution Image registration Fusion Image restoration Mosaicking Motion estimation Particle swarm optimization High-resolution imaging High-resolution video 


  1. 1.
    Fernandes SR, Estrela VV, Magalhaes HA, Saotome O (2014) On improving sub-pixel accuracy by means of B-Spline, In: Proceedings of the 2014 IEEE international conference on imaging system and techniques (IST 2014), Santorini, Greece. doi: 10.1109/IST.2014.6958448
  2. 2.
    Katsaggelos AK, Molina R, Mateos J (2007) super resolution of images. Morgan & Claypool Publishers, USAGoogle Scholar
  3. 3.
    Rivera LA, Estrela VV, Carvalho PCP (2004) Oriented bounding boxes using multiresolution contours for fast interference detection of arbitrary geometry objects. In: Proceedings of 12-th international conference in central Europe on computer graphics, visualization and computer vision (WSCG 2004), Plzen, Czech RepublicGoogle Scholar
  4. 4.
    Su H, Wu Y, Zhou J (2012) Super-resolution without dense flow. IEEE Trans Image Process 21(4):1782–1795MathSciNetCrossRefGoogle Scholar
  5. 5.
    Irani M, Peleg S (1990) Super resolution from image sequences. In: Proceedings of the ICPR, vol 2, pp 115–120Google Scholar
  6. 6.
    Tsai RY, Huang TS (1984) Multiframe image restoration and registration. In: Advances in computer vision and image processing, vol 1, chap 7, pp 317–339, JAI Press, Greenwich, Conn, USAGoogle Scholar
  7. 7.
    Anitha J, Vijila CKS, Hemanth DJ (2011) An overview of computational intelligence techniques for retinal disease identification applications. Int J Rev Comput 5(1):29–46Google Scholar
  8. 8.
    Coelho AM, Estrela VV, do Carmo FP, Fernandes SR (2012) Error concealment by means of motion refinement and regularized bregman divergence. In: Proceedings of the 13th International conference on intelligent data engineering and automated learning (IDEAL’12), Natal, Brazil, pp 650–657. doi: 10.1007/978-3-642-32639-4_78
  9. 9.
    Anitha J, Vijila CKS, Hemanth DJ (2009) Comparative analysis of GA and PSO algorithms for abnormal retinal image classification. Int J Recent Trends Eng 2(3):143–145Google Scholar
  10. 10.
    Hemanth DJ, Anitha J (2013) Modified cross-over techniques in genetic algorithms for performance enhancement of retinal image classification system, In: Proceedings of the 3rd international conference on computational intelligence and information technology, pp 28–34, IET, Mumbai, India, doi:  10.1049/cp.2013.2587
  11. 11.
    Jestin VK, Anitha J, Hemanth DJ (2011) Genetic algorithm for retinal image analysis. Int J Comput Appl 1:48–52Google Scholar
  12. 12.
    Rouet IM, Jacq II, Roux C (2000) Genetic algorithms for a robust 3-D MR-CT registration. IEEE Trans Inf Tech Biomed 4(2):126–136CrossRefGoogle Scholar
  13. 13.
    Wyawahare MV, Patil PM, Abhyankar H (2009) Image registration techniques: an overview. Int J Sig Process Image Process Pattern Recogn 2:11–28Google Scholar
  14. 14.
    Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of the 1995 IEEE international conference on neural networks, IEEE, pp 1942–1948. doi: 10.1109/ICNN.1995.488968
  15. 15.
    Li Q, Sato I, Murakami Y (2007) Affine registration of multimodality images by optimization of mutual information using a stochastic gradient approximation technique. In: Proceedings of the 2007 IEEE international geoscience and remote sensing symposium (IGARSS 2007). doi: 10.1109/IGARSS.2007.4422814
  16. 16. Retrieved on 21 Nov 2016
  17. 17.
    Jesus MA, Estrela VV, Saotome O (2016) Super-resolution in a nutshell. In: Proceedings of the Brazilian technology symposium 2016 (BTSym 2016). ISSN 2447-8326. V. 1Google Scholar
  18. 18.
    Silva Filho P, Rodrigues M, Saotome O, Shiguemori EH (2014) Fuzzy-based automatic landmark recognition in aerial images using ORB for aerial auto-localization. In: Bebis G et al (eds) Advances in visual computing, vol 8887, LNCS, 467-476, Springer, BerlinGoogle Scholar
  19. 19.
    Feng K, Zhou T, Cui J, Tana J (2014) An example image super-resolution algorithm based on modified k-Means with hybrid particle swarm optimization. optoelectronic imaging and multimedia technology III. In: Dai Q, Shimura T (eds) Proceedings of SPIE ,vol 9273, 92731I. doi: 10.1117/12.2073216
  20. 20.
    Altunbasak Y, Patti AJ, Mersereau RM (2002) Super-resolution still and video reconstruction from MPEG-coded video. IEEE Trans Circuits Syst Video Tech 12:217–226Google Scholar
  21. 21.
    Singh P, Sharma J (2016) A review paper on image denoising by low rank matrix decomposition and genetic algorithm. Int J Eng Sci Res Technol 5, 7:166–681. doi: 10.5281/zenodo.56923
  22. 22.
    Reibman AR, Bell RM, Gray S (2006) Quality assessment for super-resolution image enhancement. In: Proceedings of IEEE international conference on image processing. USA, pp 2017–2020Google Scholar
  23. 23.
    Yang J, Wright J, Huang T, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873Google Scholar
  24. 24.
    Brandi F, de Queiroz RL, Mukherjee D (2008) Super-resolution of video using key frames and motion estimation. In: Proceedings of IEEE international conference on image processing, USA, pp 321–324Google Scholar
  25. 25.
    Al-Najjar YAY, Soong DC (2012) Comparison of image quality assessment: PSNR, HVS, SSIM, UIQI. Int J Sci Eng Res 3(8). ISSN 2229-5518Google Scholar
  26. 26.
    Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Proc 13(4):600–612CrossRefGoogle Scholar
  27. 27.
    Lukeš T, Hagen GM, Křížek P, Švindrych Z, Fliegel K, Klíma M (2014) Comparison of image reconstruction methods for structured illumination microscopy. In Proceedings of SPIE 9129Google Scholar
  28. 28.
    Imran M, Hashima R, Khalidb NEA (2013) An overview of particle swarm optimization variants. In: Proceedings of the 2012 Malaysian Technical Universities conference on engineering and technology (MUCET 2012), Part 4: information and communication technology, Procedia Eng 53:491–496Google Scholar
  29. 29.
    Holland JH (1992) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. University of Michigan Press, Ann Arbor, MIGoogle Scholar
  30. 30.
    Kirkpatrick S, Gelatt CD Jr, Vecchi MP (1983) Optimization by simulated annealing. Science 220(4598):671–680MathSciNetCrossRefzbMATHGoogle Scholar
  31. 31.
    Price K, Storn R (1995) Differential evolution—a simple and efficient adaptive scheme for global optimization over continuous spaces. Technical report, International Computer Science Institute, BerkleyGoogle Scholar
  32. 32.
    Fogel LJ, Owens AJ, Walsh MJ (1965) Artificial intelligence through a simulation of evolution. In: Maxfield M, Callahan A, Fogel LJ (eds) Biophysics and cybernetic systems, In: Proceedings of the 2nd cybernetic sciences symposium, pp 131–155Google Scholar
  33. 33.
    Timmis J, Neal M, Hunt J (2000) An artificial immune system for data analysis. BioSystems 55(1):143–150. doi: 10.1016/S0303-2647(99)00092-1
  34. 34.
    Dorigo M, Stutzle T (2004) Ant colony optimization (ACO)Google Scholar
  35. 35.
    Holden N, Freitas AA (2008) A hybrid PSO/ACO algorithm for discovering classification rules in data mining. J Artif Evol Appl 2008. doi: 10.1155/2008/316145
  36. 36.
    Anitha J, Vijila CKS, Selvakumar AI, Hemanth DJ (2012) Performance improved PSO based modified kohonen neural network for retinal image classification. J Chin Inst Eng 35(8):979–991CrossRefGoogle Scholar
  37. 37.
    Hemanth DJ, Vijila CKS, Anitha J (2010) Performance improved PSO based modified counter propagation neural network for abnormal mr brain image classification. Int J Adv Soft Comput Appl 2(1):65–84Google Scholar
  38. 38.
    Lin CL, Mimori A, Chen YW (2012) Hybrid particle swarm optimization and its application to multimodal 3D medical image registration. Comput Intell Neurosci 2012. doi: 10.1155/2012/561406
  39. 39.
    Thangaraj R, Pant M, Abraham A, Bouvry P (2011) Particle swarm optimization: hybridization perspectives and experimental illustrations. Appl Math Comput 217:5208–5226zbMATHGoogle Scholar
  40. 40.
    Costa GH, Bermudez J (2009) Registration errors: are they always bad for super-resolution? IEEE Trans Signal Proc 57(10):3815–3826MathSciNetCrossRefGoogle Scholar
  41. 41.
    Robinson D, Milanfar P (2006) Statistical performance analysis of super-resolution. IEEE Trans Image Process 15(6):1413–1428CrossRefGoogle Scholar
  42. 42.
    Tom BC, Galatsanos NP, Katsaggelos AK (2002) Reconstruction of a high resolution image from multiple low resolution images. In: Chaudhuri S (ed) Super-resolution imaging. Kluwer, NorwellGoogle Scholar
  43. 43.
    Coelho AM, Estrela VV (2012) EM-based mixture models applied to video event detection. In: Sanguansat P (ed) Principal component analysis—engineering applications, InTech open. doi: 10.5772/38129
  44. 44.
    Estrela VV, Magalhaes HA, Saotome O (2016) Total variation in computer vision. In: Kamila NK (ed) Handbook of research on emerging perspectives in intelligent pattern recognition, analysis, and image processing. doi: 10.4018/978-1-4666-8654-0.ch002

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Maria Aparecida de Jesus
    • 1
  • Vania V. Estrela
    • 1
  • Osamu Saotome
    • 2
  • Dalmo Stutz
    • 3
  1. 1.Telecommunications DepartmentUniversidade Federal Fluminense (UFF)Rio de JaneiroBrazil
  2. 2.Instituto Tecnologico de Aeronautica (ITA), CTA-ITA-IEEASao Jose dos CamposBrazil
  3. 3.Instituto Politecnico do Rio de Janeiro (IPRJ), UERJNova FriburgoBrazil

Personalised recommendations