GA-Based Reconstruction of Plane Images from Projections
Zensho Nakao, Yen‐Wei Chen, Fath El Alem F. Ali · Industrial and Engineering Applications of Artificial Intelligence and Expert Systems · 2022
A GA-based technique for reconstructing plane binary images from a minimal number of projections is presented; its effectiveness is demonstrated by reconstructing two-dimensional objects from their one-dimensional coded images. The algorithm gets projection data from three different viewing angles. An initial population of strings, each of which contains encodings of an image, is generated randomly. Typical genetic operations are performed on every generation of population to produce a new generation, where a Laplacian type constraint term is included in the fitness ( cost ) function, and two--dimensional genetic operators are developed. Results obtained so far are fairly good although there is still some room for modification and improvement.