Method and system for stitching text images

Abstract

The invention discloses a method and system for stitching text images. The method comprises the following steps: obtaining a template image; obtaining all the local text images; carrying out feature matching on one local image which is not processed and the template image to obtain a matching point pair; after matching is successful, computing a perspective transformation matrix between the corresponding local image and the template image through the matched features; then obtaining an image obtained after transforming the local image according to the transformation matrix; and stitching all the transformed text images according to the effective areas of the text images to obtain a stitched total graph. The method and system provided by the invention have the following beneficial effects:the shot local text images and the template image are subjected to feature matching; and by adopting the template image based feature matching method, not only can the matching speed be improved, butalso the accuracy of matching can be ensured, thus ensuring the perspective transformation matrix which is computed later to be more accurate.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image splicing method, in particular to a text image splicing method; meanwhile, the invention also relates to a text image splicing system. Background technique [0002] As more and more mobile phones integrate camera functions, the application software based on computer vision technology is gradually enriched on mobile phones. A typical application is to use the camera on the mobile phone to scan or take text images to realize the traditional scanner. Features. Since the mobile phone can be moved and carried and scanned with the camera on the mobile phone, it is also very convenient to use, so the scanner on the mobile phone is a very promising application. [0003] The scanner function on the current mobile phone is to first take a text picture with a camera, and then add some image preprocessing to get the final scanning result. This kind of mobile phone scanner s...

AI Technical Summary

Problems solved by technology

This shooting method with many restrictions is extremely inconvenient for mobile phone users

[0008] Another disadvantage: when splicing multiple flat document images, such as splicing the first and second images, it is necessary to determine a transformed reference plane. If the plane where the first text image is located is used as the reference plane

And because there is an error in the conversion from the second frame to the first frame, there is also an error in the conversion from the third frame to the second frame. When calculating the transformation from the third frame to the first frame, the cumulative error of the reference plane is relatively large at this time, so that The resulting full image of the document looks distorted

[0009] In order to solve the problem that the captured partial images do not have overlapping areas or the images cannot be spliced ​​together because the features of the overlapping areas are not obvious, and the reference planes are not uniform, resulting in cumulative errors, the applicant proposed a method based on template images. Text full-image mosaic method for feature matching

Images