Fingerprint positioning method and device, electronic equipment and storage medium

Abstract

The invention discloses a fingerprint positioning method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting a fingerprint feature of a current position into a preset neural network, and obtaining a regression point; obtaining the distance of the centroid of each preset area according to the regression point, and determining the area to which the regression point belongs; obtaining the distances from all points in the region to the regression points, determining the points with the distances smaller than a preset value, and generating a fingerprint feature set; and determining the centroid of the fingerprint feature set to obtain the position information of the current position. Therefore, the problems that the over-fitting or under-fitting phenomenon occurs, the positioning precision is low, the cost is high, the use requirement cannot be met and the like due to the fact that the coordinate position of the observation value is directly obtained through a trained model and the memory function is not achieved are solved.

Description

technical field [0001] The invention relates to the technical field of fingerprint positioning, in particular to a fingerprint positioning method, device, electronic equipment and storage medium. Background technique [0002] At present, in order to narrow the scope of fingerprint matching, the entire area is generally divided into multiple small areas, such as using machine learning or filtering theory, so that specific small areas can be located first, and then precise fingerprint positioning can be performed to reduce time complexity. [0003] In related technologies, with the introduction of the end-to-end method of the deep neural network, a model can be directly trained to directly obtain the regression result, that is, the coordinate position of the observation value, but there are too many input parameters, which is easy to overfit, and The neural network is too complex, the calculation cost is high, or the input parameters are too few, and it is easy to underfit. As...

AI Technical Summary

Problems solved by technology

[0004] The invention provides a fingerprint positioning method, device, electronic equipment and storage medium to solve the problem of directly obtaining the coordinate position of the observed value through the trained model, which does not have a memory function, resulting in the phenomenon of over-fitting or under-fitting. Low precision, high cost, unable to meet the use requirements and other issues

Images