A method of image stitching with partition matching and direct detection for rotated image

•In the process of feature extraction and matching, we choose the half area instead of the entire image, which can avoid spending a lot of computation time in the invalid areas and can improve the efficiency of extraction and matching.•We take the four half areas of the target image as the partitions and perform feature extraction and matching on the reference image and those four partitions respectively. According to the part with the most matching feature points, the preliminary angle to be rotated can be determined.•We describe a direct detection method of matching pairs to adjust the rotation angle. Experiments show that, compared with the manual angle adjustment, our method can not only adaptively obtain a visually good stitching result, but also save a lot of calculation time. Aiming at the problem of stitching overlapped images taken under different rotation angles, we present an effective and adaptive method to rotate the image to an appropriate angle before stitching in this paper. Firstly, we take the upper half, lower half, left half, and right half of the target image as the four partitions to be matched. Then, we make feature extractions and match between the reference image and those four partitions of the target image respectively. According to the half part with the most matching pairs, the target image is rotated by a preliminary angle. At the same time, the distribution area of the matching points of the reference image is calculated as the overlapping area. After matching the overlapping areas of the reference image and the rotated target image, we propose a method to detect the direction of the matching pairs to adjust the rotation angle. Finally, the reference image and the rotated target image can be successfully stitched into a wider image. Experimental results show that our method can find a suitable angle to rotate the target image, and can achieve an effective and satisfactory stitching result.