Human face stick figure generation method and device

Abstract

The invention discloses a method and a device for generating a human face stick figure. The method comprises the following steps of: cutting a human face image from an image and predicting an attribute category; inputting the human face image into a universal human face portrait synthesis model to enable the universal human face portrait synthesis model to synthesize a first human face stick figure; determining a special human face portrait synthesis model required by the attribute category, and inputting the human face image into the special human face portrait synthesis model to enable the special human face portrait synthesis model to synthesize a second human face stick figure; and fusing the first face stick figure and the second face stick figure. The method comprises the following steps: synthesizing a first human face stick figure by using a universal human face portrait synthesis model; aiming at different face attribute categories, different special face portrait synthesis models are used for synthesizing a second face stick figure. Therefore, the influence of the human face attribute change on the portrait stick figure synthesis quality is overcome, the human face stickfigure obtained by the first human face stick figure and the second human face stick figure is more accurate, and the personalized requirements of different human face attributes are met.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for generating human face stick figures. Background technique [0002] Converting face images into stick figures has important application value in the fields of public safety and digital entertainment. [0003] In the traditional image processing method, if the effect of the generated stick figure is to be good, the computational complexity of the image processing method is very high, which is difficult to meet the real-time requirements. With the development of machine learning technology, image processing based on machine learning Compared with traditional image processing technology, the technology has higher computing speed and higher accuracy, so many machine learning models for generating stick figures from face images have been derived. [0004] However, the stick figures generated by these machine learning models from face images are greatly affect...

AI Technical Summary

Problems solved by technology

[0003] In the traditional image processing method, if the effect of the generated stick figure is to be good, the computational complexity of the image processing method is very high, which is difficult to meet the real-time requirements. With the development of machine learning technology, image processing based on machine learning Compared with traditional image processing technology, the technology has higher computing speed and higher accuracy, so many machine learning models for generating stick figures from face images have been derived

[0004] However, the stick figures generated by these machine learning models from face images are greatly affected by changes in face attributes (such as face texture characteristics and other attributes), and the generation effect is not good.

Images