Method and device for identifying reticulate pattern face image based on multi-task convolutional neural network

Abstract

The present invention discloses a method and a device for identifying a reticulate pattern face image based on a multi-task convolutional neural network. The method comprises the steps of: collecting reticulate pattern face image and corresponding clear face image pairs, then using the multi-task convolutional neural network to respectively design object functions based on regression and classification, training a face image reticulate pattern removing model, and finally inputting the reticulate pattern face image into the trained reticulate pattern removing model to obtain a face image without reticulate pattern, thereby performing subsequent face image identification tasks. According to the method, a multi-task learning frame is adopted, the task for restoring a reticulate pattern image to a clear image is expressed as two object functions which are assistant with each other, and the convolutional neural network is utilized to learn complicated nonlinear transformation referred therein. The method not only effectively improves convergence rate during model training, but also can greatly improve image restoration effect and generalization ability, thereby greatly improving identification accuracy rate of the reticulate pattern face image.

Description

technical field [0001] The invention relates to computer vision, pattern recognition, machine learning and other technical fields, in particular to a multi-task ConvNet for Face Recognition method (Multi-taskConvNetforFaceRecognition, MTCN for short) based on multi-task convolutional neural network. Background technique [0002] As a kind of biometric identification technology, face recognition has good development and application prospects due to its non-contact, accurate and convenient characteristics. Face recognition technology has played a very important role in many application scenarios, such as airport security check, border inspection and customs clearance. Traditional face recognition technology is mainly aimed at the data collected in different time periods in the same scene. However, with the improvement of the current level of face recognition technology, in order to use face recognition technology more conveniently. Face recognition technology based on ID car...

AI Technical Summary

Problems solved by technology

But simply using the textured image as input and the clear image as output, the trained neural network has a relatively general effect, and the training process is relatively long and the convergence is slow.

Moreover, due to the lack of prior knowledge guidance in the training process, the generalization performance of the trained model is poor.

Images