Method for automatically drawing human face cartoon

Abstract

The invention discloses a method for automatically drawing a human face cartoon. The method comprises the following steps: acquiring a human face image consisting of a plurality of regions according to a plurality of feature base points; respectively drawing by taking the eye area, the eyebrow area, the nose area, the mouth area, the hair style area and the face shape area as independent modules;wherein one or more regions of the eye region, the eyebrow region, the mouth region, the hair style region and the face shape region are respectively formed by fusing a plurality of image layers; andfusing the drawn eye area, eyebrow area, nose area, mouth area, hairstyle area and face area with the cartoon background template. According to the drawing method, dependence on a designer is small, adatabase is not needed, a matching process does not exist, the workload is relatively small, and the cartoon feeling is high while the truth is guaranteed. A real and fine cartoon is made by means ofcodes or a designed calculation method, and the effect is controllable. The method is not limited by environmental factors, and the final finished product effect is not affected by illumination and foreign matter shielding.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for automatically drawing a human face cartoon. Background technique [0002] Face cartoons have been widely used in Internet socialization by the public. The drawing of cartoons usually requires a designer with professional skills to spend a certain amount of time to complete. The development of computer image processing technologies such as computer vision and computer graphics has made it possible to use computer software. It is possible to realize the generation of human face cartoons. [0003] At present, there are two types of facial cartoon generation technologies in the industry: 1) facial features similarity matching technology. This method extracts the target user's facial features and image information through the facial features positioning technology, and based on the point features or image features of the facial features, performs sim...

AI Technical Summary

Problems solved by technology

Face alignment, triangulation and other technologies used in face fusion technology need to perform affine transformation on the image level between the target face and the template face. In the scene, the style of the cartoon template is required to be very realistic, which will reduce the interesting and cute characteristics of the cartoon face itself

In addition, face fusion technology is still alpha fusion of image pixel values ​​in essence, so it is very difficult to solve the problem of facial shadows caused by factors such as camera angle, environment, eyes and bangs, etc. more demanding

Images