Gait recognition method based on similar rule Gaussian kernel function classifier

Abstract

Provided is a gait recognition method based on a similar rule Gaussian kernel function classifier. The method comprises the steps that a camera collects a current background image and an original gait image sequence of a detection target in real time, image preprocessing is carried out by the adoption of an Euclidean distance method and the like, and a standard gait image sequence is obtained; one gait sequence is divided into three gait subsequences by application of an interval frame grabbing technology, feature extraction is carried out, and gait feature vectors are obtained; similar rule construction is carried out by utilization of the feature vectors in a gait feature vector database; the gait feature vectors of the detection target are classified through the Gaussian kernel function classifier corresponding to the similar rule construction, and a recognition result is counted and output. The method can rapidly remove the background, and adaptability under different situations is improved by application of the image normalization and the interval frame grabbing technology. In addition, the similar rule Gaussian kernel function classifier can effectively avoid the problems of overfitting, dimension disasters and the like, and improve the integral recognition precision.

Description

technical field [0001] The invention belongs to the technical field of biological feature recognition, in particular to the technical field of gait recognition, and specifically relates to a gait recognition method based on a similarity rule Gaussian kernel function classifier. Background technique [0002] Gait recognition technology is an emerging identification technology in the field of biometric identification technology. Its main function is to identify the identity by recognizing people's walking movements. Compared with other traditional technologies in the field of biometric identification (such as: face recognition, fingerprint recognition, iris recognition), gait recognition has the advantages of non-contact, strong adaptability and difficulty in camouflage. Due to the above advantages, gait recognition has broad application prospects in the field of video image recognition, especially in the field of security monitoring. [0003] In recent years, scholars at hom...

AI Technical Summary

Problems solved by technology

[0004] In terms of background modeling, background removal is a major problem. From the research results at home and abroad, most background removal methods use the idea of ​​"iterative elimination". However, this type of method has many iterations, slow algorithm speed, and system performance. It also decreases, unable to meet the needs of practical applications

[0005] In terms of gait feature extraction, research papers at home and abroad cover more than a dozen features for gait recognition, including joint angle changes, gait energy maps, outermost contour distance signals, etc., but most of them are sensitive to image noise points

[0006] In terms of gait recognition speed, the general gait recognition system adopts a large amount of calculations and low algorithm efficiency, and the operating environment mostly relies on the support of high-performance computers, which cannot meet actual needs on popular PCs

[0007] In terms of gait recognition accuracy, the traditional classification algorithms used in general systems cannot effectively avoid problems such as overfitting and dimension disasters, which affect the overall recognition accuracy of the system

Images