Image stitching method by multi‐feature constrained alignment and colour adjustment

Abstract

Image alignment and colour consistency are two challenging tasks for image stitching. Traditional point correspondence methods are difficult to achieve good alignments due to their insufficiency and unreliability. The results are prone to errors and distortions. On the other hand, the problem of colour inconsistency in overlapping area between image pairs is still difficult to solve, especially when the illumination difference between images is large. To solve these problems, the authors integrate point features and line features into a warping model through a designed energy function. Line features will provide geometric constraints for image stitching, and remedy the defect of point correspondences in low‐textured image stitching. A global colour consistency optimization method with colour mapping via a histogram extreme point‐matching algorithm is proposed. The colour characteristic of reference images will be transferred to the others to achieve a global colour consistency. The proposed method is evaluated on a series of images, and compared with other methods. The experiments demonstrate that the proposed method provides convincing stitching results and achieves satisfied colour consistency results.

Museum Relic Image Detection and Recognition Based on Deep Learning

“…First, feature map mapping is conducted. At this point, 1 × 1 convolution of three unshared weights is used to obtain the feature graph expressed as F Query , F Key , and F value , and then the self-attention graph is obtained through the first two feature graphs, and the specific formula of attention value is as follows [ 21 – 23 ]: and then the feature graph F org att with the mask is further obtained, and now it has to take the product of β i , j and F value , and the specific formula is as follows [ 24 ]: …”