Double-page text image recognition and location segmentation method based on special anchor points

Abstract

The invention belongs to the field of image processing, and specifically relates to a double-page text image recognition, positioning and segmentation method, system, and device based on a special anchor point, aiming to solve the problems of low accuracy and efficiency of existing double-page text image recognition and segmentation methods . The system method includes obtaining the text image to be recognized; extracting the contour line of the foreground area in the image; obtaining the minimum circumscribed rectangle corresponding to the contour line, and obtaining the two anchor points closest to the longitudinal central axis of the minimum circumscribed rectangle as special Anchor points obtain special anchor points; judge whether special anchor points are abnormal anchor points, judge whether the text image is a single-page or double-page text image according to the number of abnormal anchor points; also include obtaining double-page text images; obtain special anchor points; The anchor point determines the position of the dividing line, and the minimum circumscribed rectangle is divided to obtain the segmentation result. The invention improves the accuracy and efficiency of double-page text image recognition and segmentation.

Description

Technical field [0001] The present invention belongs to the field of image processing, and more particularly to a two-page text image recognition and positioning segmentation method, system, and device based on a particular anchor point. Background technique [0002] With the rapid development of the computer and computer network bandwidth, the propagation method of information is in the form of a binary image by the conventional text format. In the processing and application of the image, some parts or targets are sometimes often interested in the image, at which time, image recognition and segmentation techniques need to be used to distinguish the objects of interest to the background area to facilitate further research and analysis. Image identification and image division are the first step in image analysis, and is also one of the most difficult problems in image processing. It can be said that the image identification and image segmentation results are good and directly affe...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problems of low accuracy and low efficiency of double-page text image recognition and segmentation in existing double-page text image recognition and segmentation methods, the first aspect of the present invention proposes a A double-page text image recognition method based on special anchor points, the method includes:

Images