DIGITAL SPECKLE CORRELATION METHOD IMPROVED BY GENETIC ALGORITHM

The digital speckle correlation method is an important optical metrology for sur-face displacement and strain measurement.With this technique,the whole field deformation in-formation can be obtained by tracking the geometric points on the speckle images based on acorrelation-matching search technique.However,general search techniques suffer from great com-putational complexity in the processing of speckle images with large deformation and the largerandom errors in the processing of images of bad quality.In this paper,an advanced approachbased on genetic algorithms (GA) for correlation-matching search is developed.Benefiting fromthe abilities of global optimum and parallelism searching of GA,this new approach can completethe correlation-matching search with less computational consumption and at high accuracy.Twoexperimental results from the simulated speckle images have proved the efficiency of the newapproach.