Recognition method and device for check box in PDF document and electronic equipment

Abstract

The embodiment of the invention provides a recognition method and device for a check box in a PDF document and electronic equipment, and relates to the technical field of image recognition. The recognition method comprises the steps: obtaining a position clicked by a user in the displayed PDF document, wherein the clicked position is a blank position in a check box visually observed by the user; searching candidate boundary points in four directions, namely an upper direction, a lower direction, a left direction and a right direction, within a preset range by taking the clicking position as astarting point; if the candidate boundary points are searched in the preset range, recording display coordinates of each candidate boundary point; and judging whether a graph defined by the coordinates of the candidate boundary points is a square or not, and if the graph defined by the coordinates of the candidate boundary points is the square, determining that the graph defined by the coordinatesof the candidate boundary points is a check box. By adopting the recognition method, the check box in the form of the picture in the PDF document can be identified.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method, device and electronic equipment for recognizing a check box in a PDF document. Background technique [0002] Portable Document Format (PDF) is a unique cross-platform file format. It can encapsulate all information such as text, format, font, color, resolution, link and graphic image, sound, dynamic image of the document in a special integrated file. The PDF document can finally be displayed on the screen, and the content of the file is rendered into an image, and then output to the screen. There are often many tables and pictures in the PDF document, and these tables and pictures often have check boxes, and the user needs to use the check boxes to select the corresponding content. [0003] However, the inventor found in the process of implementing the present invention that the recognition of the check box in the PDF document in the prior art is limited to ...

AI Technical Summary

Problems solved by technology

[0003] However, the inventor found in the process of implementing the present invention that the recognition of the check box in the PDF document in the prior art is limited to the recognition when the check box is a comment object, and when the check box in the PDF document When it exists in the form of a picture, it cannot be recognized

[0004] It can be seen that the check boxes in the form of pictures in the PDF documents of the prior art cannot be recognized

Users cannot operate the check boxes in the form of pictures in PDF documents, which is not convenient enough to use

Images