System and method for establishing age evaluation model based on deep learning technology

Abstract

The invention discloses a system and method for establishing an age evaluation model based on a deep learning technology. The method comprises the steps of photographing a full-mouth curved-surface fault film of Chinese Han population in the northwest, dividing a curved-surface fault film data set into a training set, a verification set and a test set according to the proportion of 8:1:1, inputting the training set into an EfficitNet-B5 network, carrying out the training of a classifier, and finally, establishing an automatic classification model of 18 years old or not through the performanceof the classifier on the test set. A traditional deep learning model is simplified, a label directly related to an output value is added to an image, a neural network model related to the input imageand the output value is established through a computer algorithm, and then automatic evaluation of the image is achieved; and the whole curved surface fault film is selected as the input image of theneural network instead of being limited to teeth in a certain area, the most comprehensive tooth information is provided for a computer to explore the correlation between the tooth structure and the age, and missing of other structural new information with prompt significance is avoided.

Description

technical field [0001] The invention belongs to the field of deep learning technology, and relates to a system and method for establishing an age assessment model based on deep learning technology. Background technique [0002] As an important age node for distinguishing adults and minors, 18 years old is the focus of many scholars' exploration and research, so a large number of scholars have conducted exploration and research on it. However, most age-related human developmental structures complete development before the age of 18, which undoubtedly increases the difficulty for forensic experts to distinguish adults from minors. In this case, the third molar is the most effective indicator because it is still in the development stage at about 18 years old. In 1993, Mincer et al. published a study in which they evaluated the developmental stage of mandibular third molars using a staging system based on the Demirjian method to determine whether the subjects were adults or min...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of less research on the judgment of important age nodes and low accuracy in the prior art, and to provide a system and method for establishing an age evaluation model based on deep learning technology

Images