Perceptual loss and deep convolutional neural network-based sketch simplifying method

Abstract

The invention discloses a perceptual loss and deep convolutional neural network-based sketch simplifying method. The method comprises the steps of: 1) obtaining data: obtain the data by using a sketchmap and corresponding label data; 2) processing data: transforming the sketch map and corresponding line sketch map of an image data set into a format required for training a deep convolutional neural network through preprocessing; 3) constructing a model: constructing a deep convolutional neural network suitable for sketch simplification according to a training objective; 4) defining a loss function; 5) training the model: calculating the loss value of the network according to the loss function, calculating the gradient of each network layer parameter through back propagation and updating parameters of each layer of the network through a random gradient descent method; and 6) verifying the model: verifying the trained model by using a verification data set and testing the generalizationperformance. The method disclosed by the invention has the advantages that sketches with rougher miscellaneous lines and unclear main structure lines can be processed by a sketch simplifying network;and the network has strong robustness to the influence of illumination.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to a sketch simplification method based on a deep convolutional neural network based on perceptual loss. Background technique [0002] Sketching is the first step in creating art. In this step, creators usually only want to express the concept and composition, rather than focusing on the details. After creating the sketch, the creator needs to draw a clean line draft on the basis of the sketch, which is a tedious and labor-intensive job. [0003] In recent years, with the rapid development of deep learning, deep convolutional neural networks can be used to learn the characteristics of clean line drawings, thereby transforming sketches with many messy lines into simplified line drawings with the characteristics of line drawings. However, the existing problem is that the current deep learning method directly measures the loss by calculating the Euclidean distance b...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and provide a sketch simplification method based on a deep convolutional neural network based on perceptual loss, which can well simplify sketches of any size and break through the previous sketch simplification Problems such as loss, blur, line deformation and distortion in the method, insufficient simplification ability, etc.

Images