A Face Image Age Recognition Method Based on Improved Ensemble Learning Strategy

Abstract

A face image age recognition method based on an improved integrated learning strategy, comprising the following steps: 1) In the integrated learning model, multiple weak classifiers need to be obtained, and each weak classifier can independently realize the prediction and estimation of the input object, Construct a prediction model containing multiple weak classifiers; 2) multiple weak classifiers obtained based on DCNN and strong classifiers obtained by integration, all adopt softmax classifiers; 3) adopt an improved ensemble learning strategy, first, follow the voting principle combined method, and use the set threshold T to control the trust degree of each weak classifier's "opinion"; then, when the trust degree of weak classifiers is generally low, abandon the voting combination method, and calculate the trust degree of each weak classifier confidence coefficient a i As their respective weight values; finally, use the method of weighted combination to obtain the probability distribution array of the strong classifier and take the classification label corresponding to its largest component as the final prediction result. The invention significantly improves the accuracy.

Description

technical field [0001] The invention relates to a face image age recognition method, in particular to a face image age recognition method based on an improved integrated learning strategy. Background technique [0002] With the rapid development of computer vision, pattern recognition and biometric technology, computer-based face age estimation has attracted more and more attention in recent years. It has a wide range of computer vision application prospects, including security detection, forensics, human-computer interaction (HCI), electronic customer information management (ECRM), etc. In real life, the use of surveillance cameras and age recognition systems can effectively prevent vending machines from selling cigarettes and illegal drugs to minors. In social security, fraud and illegal activities at ATMs usually occur in a specific age group, so it can be confirmed and prevented in advance by introducing age information. In the field of biometrics, facial age estimatio...

AI Technical Summary

Problems solved by technology

[0003] Although there are relevant studies on face age estimation at home and abroad, the estimation accuracy is not high due to the differences in individual age generation, the complexity of texture information, lack of data, and interference factors.

Images