Human face depth and surface normal vector predication method based on dilated convolution neural network

Abstract

The invention provides a human face depth and surface normal vector predication method based on a dilated convolution neural network. The method includes steps of training the dilated convolution neural network S1, constructing the dilated convolution neural network including a plurality of convolution layers, a plurality of dilated convolution layers and a plurality of deconvolution layers that are connected in sequence, wherein each convolution layer is connected with a normalized operation and an motivation operation; S2, initializing the weight value of the dilated convolution neural network; S3, inputting training pictures into the dilated convolution neural network and performing iteration training on the dilated convolution neural network targeting at minimizing a cost function andupdating the weight value after each iteration process; S4, inputting testing pictures into the dilated convolution neural network obtained through training and outputting a corresponding human face depth map and a surface normal vector map; S5, judging whether the predication precision of the dilated convolution neural network obtained through training meets requirements or not according to the output human face depth map and the human face normal vector method, ending the training if the precision meets the requirements, and returning to S3 for training again if the precision does not meetsthe requirements.

Description

technical field [0001] The invention relates to the fields of computer vision and digital image processing, in particular to a method for predicting human face depth and surface normal vectors based on a hollow convolutional neural network. Background technique [0002] Facial depth prediction is a novel and challenging problem in computer vision. Depth prediction of the face is an important part of understanding the geometric relationship of the whole face. Correspondingly, the geometric relationship of the face can well reflect the organs on the face and the entire facial environment. If a better face depth can be obtained The information will provide great help to the face recognition problem. Similarly, it will also help to build a 3D model of the face, which will help solve the problem of 3D reconstruction of the face. However, predicting the depth information of the entire face from an RGB image of a face is itself a problem with a pathological nature, because there a...

AI Technical Summary

Problems solved by technology

For example, with the continuous increase of the convolutional layer, the gradient disappears and the training cannot continue; the receptive field of the deep network is relatively small, the depth map and surface normal vector map trained are not very accurate, and the image is relatively rough

Images