Image mosaic method and system for two-sided scanning

Abstract

The invention discloses an image mosaic method and a system for two-sided scanning. A feature database of scan files is built before the image mosaic method is applied. The image mosaic method includes obtaining scan images of scan files, wherein the scan images comprise front images and back images of the scan files; performing slant correction on the scan images; performing position segmentation and feature extraction on the scan images; performing direction judgment and direction correction on the scan images according to comparison of features of the extracted scan images with the feature data; and mosaicing the front images with the back images in the scan images. According to the image mosaic method and the system, two-sided scan operation of users is greatly facilitated, mosaic quality of the two-sided scan images is guaranteed, and the image mosaic method and the system can be widely applied to the image scan field.

Description

technical field [0001] The invention relates to an image stitching method, in particular to an image stitching method and system for double-sided scanning. Background technique [0002] Scanners are mainly based on the principle of photoelectric induction for image pickup, and are used to convert the contents of paper documents into electronic documents by scanning, so that users can disseminate, organize or save them. Ordinary scanners use an image sensor for single-sided scanning. However, for valuable securities materials such as ID cards and bills, they need to be scanned on both sides for preservation or use. For example, a double-sided scan of an ID card is often required for banking purposes. Generally, the front and back sides need to be scanned twice, and they need to be scanned on the same paper. The problem that often occurs is that the front and back images cannot be spliced ​​together, and are upside down and misplaced, which brings inconvenience to the appli...

AI Technical Summary

Problems solved by technology

The problem that often occurs is that the front and back images cannot be spliced ​​together, and they are upside down and misplaced, which brings inconvenience to the application; or the front and back images are scanned, and then the image adjustment and splicing are manually completed through image processing software, which brings inconvenience to the application

Even if a double-sided scanner is used, it is necessary to prevent errors such as image tilt, mirror position, or inversion when the front and back images are stitched together. At present, there is no corresponding method that can automatically complete the automatic stitching of scanned images.

Images