Rectangle detecting method and device for stamp images

Abstract

The invention discloses a rectangle detecting method and device for stamp images. The method comprises the following steps of: judging whether the color of each pixel point in an original image is consistent with the color of an appointed stamp in sequence, thus generating a binary image of the original image, and further, generating a boundary binary image according to the binary image; carrying out Hough vote on the boundary binary image, and extracting two peak straight lines which are judged as the two long edges of a stamp; and further, carrying out Hough vote in the vertical direction of the two long edges between the two long edges, and further judging extracted two peak straight lines as the two short edges of the stamp. According to the rectangle detecting method and device, some characteristics of the stamp images are considered, the conventional method that four peak values are selected from one Hough vote is improved to that peak values are selected in different steps by the divided Hough vote, and thus the accuracy on detection of rectangular stamps is improved in practical application.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method and device for detecting a rectangle of a stamp image. Background technique [0002] There will be stamps of various shapes and sizes in the voucher image. In the processing of the voucher image, it is necessary to use various shape detection methods to detect whether there is a stamp of a specified shape in the voucher image. In addition, while detecting, it needs to be distinguished from seals of other shapes. Among them, the rectangular seal is difficult to detect because of the uncertain rotation angle when stamping. [0003] Since a rectangle cannot be expressed by a single analytical formula like a circle, in the current general shape detection method, the detection of a rectangle must first be detected by a straight line. Generally, rectangle detection can be summarized as the following steps: [0004] First, extract the edge map. Edge detection oper...

AI Technical Summary

Problems solved by technology

However, in the application of seal detection, the length of the rectangular edge segment itself has certain limitations. The method of voting separately and connecting straight lines in multiple sub-images will cause the rectangular edge to be missed, and the rectangle cannot be detected.

[0012] In addition, in the seal image, the rectangular shape feature is easily destroyed

For example, due to the smearing of the stamp, the abrasion of the stamp itself, etc., the rectangle in the image will have rounded corners and incomplete sides, especially the short side of the rectangle is prone to incompleteness

For these pictures, when Hough votes, there will be too few votes on the short side, resulting in missed detection of straight lines. If the threshold setting is changed, non-linear lines will be falsely detected as straight lines.

Then the method of extracting four peaks after Hough transform will cause inaccurate detection because the two peaks corresponding to the short side do not appear.

Images