Image registration automatic verifying method based on learning

Abstract

The invention belongs to a computer visual and module recognition, which discloses an automatic detection method for image registering based on machine learning. The method comprises the following parts: adopt phase correlation diagram as sample data; construct feature data via the phase correlation diagram; classify the feature data via a classifier; conduct registering detection according to the classification result. The invention adopts supervision machine learning method to design the classifier; the classifier is adopted to conduct registering detection of classification result. After a registering experiment of 400 groups of different images without disturbance, it is proved that the correct detection rate reaches 100 per cent, which indicates that the image registering detection method based on classifier has high efficiency.

Description

technical field [0001] The invention belongs to the fields of computer vision and pattern recognition. Specifically, it involves the verification of image registration results. Background technique [0002] Image registration is a fundamental problem in computer vision and its related applications. How to measure whether the two images are truly registered, in other words, how to reasonably measure the similarity between the two images after registration transformation, is a core issue of image registration, which directly determines whether automatic registration can be performed. Taking the registration algorithm based on Fourier-Mellin transformation as an example, the invention proposes an automatic inspection method for image registration based on machine learning. [0003] We first make a detailed analysis and description of the problems existing in the image registration algorithm based on Fourier-Mellin transform. [0004] 1. Image registration method based on Fou...

AI Technical Summary

Problems solved by technology

[0051] [3]Luca Lucchese and Guido Maria Cortelazzo, "High resolution estimation of planar rotations based on Fourier transform and radial projection," In Proc.ISCAS 97, vol.2, pp.1181-1184, June 1997, etc. The problem has been studied in detail, and some measures such as windowing and filtering have been taken to improve the peak value, reduce spectral aliasing, and increase robustness, but still fail to solve the problem fundamentally

[0061] 2. Irregular distribution

Images