Optimization of projective transformation matrix in image stitching based on chaotic genetic algorithm

Purpose: The purpose of this paper is to present weighted Euclidean distance for measuring whether the fitting of projective transformation matrix is more reliable in feature-based image stitching. Design/methodology/approach: The hybrid model of weighted Euclidean distance criterion and intelligent chaotic genetic algorithm (CGA) is established to achieve a more accurate matrix in image stitching. Feature-based image stitching is used in this paper for it can handle non-affine situations. Scale invariant feature transform is applied to extract the key points, and the false points are excluded using random sampling consistency (RANSAC) algorithm. Findings: This work improved GA by combination with chaos's ergodicity, so that it can be applied to search a better solution on the basis of the matrix solved by Levenberg-Marquardt. The addition of an external loop in RANSAC can help obtain more accurate matrix with large probability. Series of experimental results are presented to demonstrate the feasibility and effectiveness of the proposed approaches. Practical implications: The modified feature-based method proposed in this paper can be easily applied to practice and can obtain a better image stitching performance with a good robustness. Originality/value: A hybrid model of weighted Euclidean distance criterion and CGA is proposed for optimization of projective transformation matrix in image stitching. The authors introduce chaos theory into GA to modify its search strategy. © Emerald Group Publishing Limited.