GA-based reconstruction of plane binary images

A GA-based technique for reconstructing plane binary images from four projection data is presented; its effectiveness is demonstrated by reconstructing two-dimensional objects from their one-dimensional coded images. The algorithm gets projection data from four different viewing angles. An initial population of matrices, each of which contains encodings of an image, is generated randomly. The typical as well as some new genetic operations are performed on every generation of population to produce a new one. The algorithm continues on spawning new matrices till a satisfactory one is obtained or a termination criterion is reached. Results obtained are compared to those obtained by the well-known iterative algebraic reconstruction technique (ART), and it was found that the GA-based method is superior to ART when the number of projection directions is limited to three or four