A Fast Paper Detection and Segmentation Method Based on Spatial Constraints

Abstract

The invention discloses a method for fast paper detection and segmentation based on space constraints, comprising the following steps: establishing a reference coordinate system in an image, detecting straight lines in the image, and screening the detected straight lines according to the length; The straight line segment is used to judge the paper boundary to obtain the upper, lower, left and right boundaries of the paper. According to the four boundaries, the coordinates of the four vertices of the paper are obtained; the coordinates of the four vertices are used to image the paper. Divide to obtain a paper image. The invention utilizes space constraints to realize the rapid detection and segmentation of paper, and can still detect paper quickly and accurately in the case of different desktop backgrounds and the user rotates, moves and other operations on the paper, and has the advantages of easy operation, more friendliness and real-time operation. High performance and low cost.

Description

technical field [0001] The invention relates to the fields of computer vision and human-computer interaction, in particular to a fast paper detection and segmentation method based on space constraints. Background technique [0002] In recent years, with the rapid development of computer technology, the way of human-computer interaction has also become more and more diversified. Compared with the traditional human-computer interaction method using keyboard, mouse and other hardware, the user-centered human-computer interaction method has become a hot spot and direction of human-computer interaction research because it is more direct and natural, and more in line with people's habits. New interactive devices represented by Google Glass, LeapMotion, Kinect, etc., provide users with a new human-computer interaction experience. At the same time, the pen-based interaction method reduces the cognitive load of the user in the process of interacting with the computer through the dai...

AI Technical Summary

Problems solved by technology

Document 4 aims at the problem that traditional vision algorithms are difficult to robustly track blank paper lacking texture information, and proposes a compressive sensing paper tracking algorithm with structural constraints. track [4]

The key issue of how to accurately detect and segment paper images with text written in the pen-based interactive mode is rarely studied.

Images