Automatic footprint recognition method based on multi-feature jointed decision making

Abstract

The invention discloses an automatic footprint recognition method based on multi-feature jointed decision making. The method comprises the following steps that: S1, extracting a footprint pressure distribution feature in an off state; S2, extracting a directional gradient histogram feature of the footprint; S3, extracting a wavelet Fourier Merlin feature of the footprint; S4, carrying out feature selection on the footprint pressure distribution feature P, the directional gradient histogram feature H, and the wavelet Fourier Merlin feature F by using a two-dimensional principal component analysis and a two-dimensional linear discriminant analysis technique so as to obtain P<G>S, H<G>S, and F<G>S respectively; and S5, identifying a feature of a to-be-identified footprint and footprint data stored in a feature database in advance by using a KNN classifier.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method for automatic recognition of footprints based on multi-feature joint decision-making. Background technique [0002] The study of footprint features mainly includes three features: the geometric shape feature of footprints, the pressure shape features of footprints, and the texture features of footprints. Footprint recognition is mainly recognized by a single feature, and common recognition methods include neural networks, support vector machines, Bayesian classifiers, K-nearest neighbor classifiers, etc. [0003] At present, there is still a lack of systematic and in-depth application research foundation for the research on footprint biometric analysis and identification application technology. [0004] Footprint features are usually represented by foot shape features, such as foot length, foot width, and heel width, which are difficult to extract accurately; ...

AI Technical Summary

Problems solved by technology

[0004] Footprint features are usually represented by foot shape features, such as foot length, foot width, and heel width, which are difficult to extract accurately; some researchers take a pair or a series of footprints to extract footprint texture features, and need to take off the socks and require the user to cooperate. time, lack of convenience

Footprint recognition is usually a single feature recognition, lack of multi-feature and multi-angle description, it is difficult to achieve accurate and efficient recognition

Images