Hybrid Diversification Operator-Based Evolutionary Approach Towards Tomographic Image Reconstruction

The proposed algorithm introduces a new and efficient hybrid diversification operator (HDO) in the evolution cycle to improve the tomographic image reconstruction and diversity in the population by using simulated annealing (SA), and the modified form of decreasing law of mutation probability. This evolutionary approach has been used for parallel-ray transmission tomography with the head and lung phantoms. The algorithm is designed to address the observation that the convergence of a genetic algorithm slows down as it evolves. The HDO is shown to yield a higher image quality as compared with the filtered back-projection (FBP), the multiscale wavelet transform, the SA, and the hybrid continuous genetic algorithm (HCGA) techniques. Various crossover operators including uniform, block, and image-row crossover operators have also been analyzed, and the latter has been generally found to give better image quality. The HDO is shown to yield improvements of up to 92% and 120% when compared with FBP in terms of PSNR, for 128 × 128 head and lung phantoms, respectively.