Face image quality evaluation method and device, computer readable medium and communication terminal

Abstract

The invention relates to the technical field of image recognition, in particular to a face image quality evaluation method and device, a training method and device of a feature extraction model, an image processing system, a computer readable medium and a communication terminal. The face image quality evaluation method comprises the following steps: acquiring a to-be-processed image containing a human face; detecting the to-be-processed image to obtain a corresponding face image; inputting the face image into a trained feature extraction model based on a mobile face recognition network, and performing feature extraction on the face image to obtain feature data; and inputting the feature data into a first full connection layer and a second full connection layer which are continuously arranged for processing to obtain a face quality score of the face image. According to the face image quality evaluation method, feature extraction and quality scoring of the face image can be carried out in one network, so that the magnitude of the model is effectively reduced. Moreover, the face image quality evaluation method can achieve the quick evaluation of the quality of a face image, and guarantees the accuracy of a quality evaluation result.

Description

technical field [0001] The present disclosure relates to the technical field of image recognition, in particular to a face image quality evaluation method, a feature extraction model training method, a face image quality evaluation device, a feature extraction model training device, and an image processing method. system, a computer readable medium, and a wireless communication terminal. Background technique [0002] With the rapid development of image processing technology, face recognition technology has become an indispensable technology in monitoring, customs clearance and other fields. And low-quality face images will greatly reduce the success rate of face recognition. [0003] In the prior art, there are image processing and matching methods based on feature engineering and methods based on deep learning to evaluate the quality of human faces. But there are also certain problems and deficiencies in the prior art. For example, in the face quality evaluation method b...

AI Technical Summary

Problems solved by technology

For example, in the face quality evaluation method based on deep learning, the scoring and labeling of face images needs to be done manually, which takes a lot of time and energy and has a certain degree of subjectivity, and there are many factors that affect the quality of faces. The influence of various factors cannot be fully considered, resulting in inaccurate labeled samples, which in turn affects the accuracy of the model

In addition, more and more models need to be applied to smart mobile terminal devices, so there are higher requirements for model size and performance. The existing face quality assessment methods are difficult to meet the requirements in terms of model size and running time.

Images