Abstract: Image stitching effectively extends the field of view of a single lens by integrating images with overlapping regions to generate wide-angle panoramas. The typical as-projective-as-possible (APAP) image stitching algorithm achieves high alignment accuracy but suffers from low computational efficiency. To address this issue, an image stitching algorithm based on neighborhood feature search and local homography transformation was proposed to balance accuracy and efficiency. The source image was first divided uniformly into multiple rectangular grids, and feature pairs within the neighborhood of each grid center were obtained using a neighborhood feature search strategy. The local homography matrix for each grid was then calculated via the least squares method, and a smooth transition was achieved through linear weighting of global and local transformations. Subsequently, the alignment and overlay of the source and target images were realized through perspective transformation, and seam artifacts were eliminated using a distance transform-based feathering fusion method. To validate the feasibility of the proposed algorithm, computer simulations and multi-scene image stitching experiments were conducted. The results demonstrate that the proposed algorithm outperforms global homography transformation (GHT), adaptive as-natural-as-possible (AANAP), seam-guided local alignment and stitching (SLAS), and APAP algorithms in terms of noise resistance. Compared with APAP, the root mean square error is reduced by 8.9%, while the peak signal-to-noise ratio and structural similarity index are improved by 11.4% and 12.5%, respectively, with a 29.4% reduction in computational time. By simplifying the computation of the local homography matrix, computational efficiency is significantly enhanced while stitching quality is maintained, providing a new perspective for the development of image stitching technology.