Face recognition method

Abstract

The invention provides a face recognition method. The face recognition method comprises the following main steps: acquiring original image data shot by an infrared camera and an RGB camera, wherein the original image data is composed of shot image data of a face of a living body, and performing brightness adjustment on a shot image through image preprocessing; extracting a feature face of the faceby adoption of a PCA principal component analysis method so as to form a feature face matrix, carry out image data detection, carrying out synchronous processing on the image shot by the infrared camera and the RGB camera, carrying out feature contour positioning on the face by adoption of a feature point extraction algorithm, and carrying out face extraction by using a modulo mode; and calculating the Euler distance between a single-time feature face and the feature face in a face library by detecting the single-time face feature, comparing the single-time feature face with the feature facein the face library, and if the Euler distance is smaller than a threshold value, judging that face recognition succeeds. According to the invention, image preprocessing and pre-extraction are carriedout on the actual environment, so the function of increasing the recognition distance and the recognition rate is actually achieved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a face recognition method. Background technique [0002] Face recognition in a broad sense actually includes a series of related technologies for building a face recognition system, including face image acquisition, face positioning, face recognition preprocessing, identity confirmation, and identity search; A technology or system for face recognition or identity search. [0003] The biological characteristics studied by biometric recognition technology include face, fingerprint, palm print, iris, retina, voice, body shape, personal habits (such as the strength and frequency of typing on the keyboard, signature), etc. The corresponding recognition technologies include face recognition, Fingerprint recognition, palmprint recognition, iris recognition, retina recognition, speech recognition (identification can be performed with speech recognition, and voice...

AI Technical Summary

Problems solved by technology

The face recognition accuracy rate of the existing face recognition check-in system is greatly reduced with the increase of the distance. At the same time, when the actual face database and the standard face database of the existing face recognition technology are quite different, the set value will not be able to meet the role of the basis for discrimination. , and most of the face recognition systems on the market now use traditional recognition technology, the problem is that it often cannot improve the recognition of faces, and it is incomplete or inaccurate for face recognition detection, and it cannot be used in the actual environment. Image preprocessing and pre-extraction to improve the recognition rate and recognition distance of face recognition technology

Images