Firefly algorithm for optimized nonrigid demons registration

Videos have vital applications in numerous real-time aspects such as teaching, learning, communication, computer vision, and medicine. Typically, video registration is required to describe a part of the scene/object in the video frame or to localize an object in the frame relative to a fixed reference system. The semilocal transformation generated by the B-splines registration was solved using demons algorithm. Thus, the current study is concerned with demons algorithm–based image registration for a fully local transformation model. The demons registration is optimized using the firefly algorithm (FA) to optimize the velocity-smoothing kernels of the demons registration considering the correlation coefficient as a fitness function. Afterward, the proposed system performance using demons algorithm–based FA is compared to the particle swarm optimization (PSO). The experimental results proved that the proposed system-based FA achieved a correlation value of 0.6108 compared to demons registration with default parameters that provided 0.4468. Additionally, the FA-based optimization framework was more stable and produced superior results than the PSO-based optimization framework. In addition, the FA algorithm converged faster than the PSO one.

[1]  Fatiha Meskine,et al.  A Rigid Image Registration Based on the Nonsubsampled Contourlet Transform and Genetic Algorithms , 2010, Sensors.

[2]  Jean-Philippe Thirion,et al.  Image matching as a diffusion process: an analogy with Maxwell's demons , 1998, Medical Image Anal..

[3]  A. Ben Hamza,et al.  Medical image registration using stochastic optimization , 2010 .

[4]  Nilanjan Dey,et al.  Principal component analysis in medical image processing: a study , 2015 .

[5]  D. Hill,et al.  Non-rigid image registration: theory and practice. , 2004, The British journal of radiology.

[6]  S. S. Chaudhuri,et al.  Optical cup to disc ratio measurement for glaucoma diagnosis using harris corner , 2012, 2012 Third International Conference on Computing, Communication and Networking Technologies (ICCCNT'12).

[7]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[8]  Xin-She Yang,et al.  Nature-Inspired Metaheuristic Algorithms , 2008 .

[9]  Silviu-Ioan Bejinariu,et al.  Parallel image registration using bio-inspired computing , 2013, 2013 E-Health and Bioengineering Conference (EHB).

[10]  Xin-She Yang,et al.  Firefly Algorithm: Recent Advances and Applications , 2013, ArXiv.

[11]  A. Ben Hamza,et al.  An information-theoretic method for multimodality medical image registration , 2012, Expert Syst. Appl..

[12]  Denis Simakov,et al.  Feature-Based Sequence-to-Sequence Matching , 2006, International Journal of Computer Vision.

[13]  Nilanjan Dey,et al.  Video segmentation using minimum ratio similarity measurement , 2015 .

[14]  Josien P. W. Pluim,et al.  Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B-Splines , 2007, IEEE Transactions on Image Processing.

[15]  N. Dey,et al.  Adaptive thresholding: A comparative study , 2014, 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT).

[16]  Santhosh P. Mathew,et al.  A Content-based Image Retrieval System Based on Polar Raster Edge Sampling Signature , 2014 .

[17]  Christian Roux,et al.  Genetic algorithms for a robust 3-D MR-CT registration , 2000, IEEE Transactions on Information Technology in Biomedicine.

[18]  Jacek M. Zurada,et al.  An approach to multimodal biomedical image registration utilizing particle swarm optimization , 2004, IEEE Transactions on Evolutionary Computation.

[19]  Nilanjan Dey,et al.  Analysis of Photoplethysmographic Signals Modified by Reversible Watermarking Technique using Prediction-Error in Wireless Telecardiology , 2013 .

[20]  Mitko Gospodinov,et al.  Analysis of Heart Rate Variability by Applying Nonlinear Methods with Different Approaches for Graphical Representation of Results , 2015 .

[21]  Nilanjan Dey,et al.  A comparative approach of four different image registration techniques for quantitative assessment of coronary artery calcium lesions using intravascular ultrasound , 2015, Comput. Methods Programs Biomed..

[22]  Yen-Wei Chen,et al.  Multimodal Medical Image Registration Using Particle Swarm Optimization , 2008, 2008 Eighth International Conference on Intelligent Systems Design and Applications.

[23]  Jyoti Singhai,et al.  Registration of Satellite Imagery Using Genetic Algorithm , 2012 .

[24]  Tarun Kumar Sharma,et al.  Enhancing different phases of artificial bee colony for continuous global optimisation problems , 2013, Int. J. Adv. Intell. Paradigms.

[25]  K.M.M. Rao,et al.  Low cost medical image processing system for rural/semi urban healthcare , 2011, 2011 IEEE Recent Advances in Intelligent Computational Systems.

[26]  Anant Madabhushi,et al.  Anisotropic smoothing regularization (AnSR) in Thirion's Demons registration evaluates brain MRI tissue changes post-laser ablation , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[27]  Ruo-feng Tong,et al.  Image Registration Algorithm Using an Improved PSO Algorithm , 2011 .

[28]  Nilanjan Dey,et al.  Effect of demons registration on biomedical content watermarking , 2014, 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT).