An image detection method and device

Abstract

The invention provides an image detection method and device. The method includes: obtaining an image to be detected; performing edge processing on the image to be detected according to an edge detection algorithm to obtain a first image; performing direction correction on the first image to obtain a target image. According to the image detection method and device of the embodiment of the present invention, the edge operator with a bandwidth is used instead of the traditional edge operator, which is beneficial to eliminate isolated noise and gather real edges; and, corresponding to the edge according to distance and / or direction According to the rules presented, it is beneficial to fit the fitted lines corresponding to the edges, improve the quality of the candidate fitted lines, and further improve the The accuracy of image edge positioning is improved. In addition, multi-edge operators and spatial grid correction are used to correct the direction of the image (plane and stereo), which improves the correction accuracy and reduces the amount of calculation.

Description

Technical field[0001]The present invention relates to the field of computer technology, in particular to an image detection method and device.Background technique[0002]With the rapid development of information technology, image data has become one of the main sources of information. In actual life and work, it is necessary to obtain information in some framed images in pictures or videos, for example, information on business cards, or information on labels, etc. When obtaining such information, terminal equipment is required Detect the image, especially to locate the edge of the image and correct the direction of the image.[0003]Traditional image edge detection methods generally use Hough transform or saliency detection, but these methods generally have the disadvantages of large amount of calculation and low detection accuracy. The existing image orientation correction methods also have poor correction accuracy. And the method is more complicated.Summary of the invention[0004]In vi...

AI Technical Summary

Problems solved by technology

[0003] Traditional image edge detection methods generally use Hough transform or saliency detection, but these methods generally have the defects of large amount of calculation and low detection accuracy, and the existing image direction correction methods also have low correction accuracy And the method is more complicated

Images