Infant image composition method and device

Abstract

The invention discloses an infant image composition method and device, and belongs to the technical field of image processing. The composition method includes the steps that feature point locating is conducted on a father source image, a mother source image and an infant source image to obtain feature vectors of the source images; a standard infant template is utilized to restrict the feature vectors of the source images so as to obtain a target infant shape; transformation processing is respectively conducted on the source images according to the target infant shape to obtain three transformation images; the three transformation images are fused to obtain a target infant image. In the process of shape composition, the standard infant template is adopted to conduct restriction, large fusion weight can be arranged to a father and a mother, so that appearance of an infant tends to be like the father and the mother; with the restriction effect of the standard infant template, the problems of distortion and stretching of the facial form of the composited infant are solved, and visual quality of the composited infant photo is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, to a baby image synthesis method and device. Background technique [0002] Because of its entertainment and fun, baby image synthesis technology has been widely used in network media, and many commercial software also support this function. How to synthesize a baby image that looks similar to its parents and has high visual aesthetics is a challenging problem. Baby image synthesis technology is based on a male image, a female image and an original baby image, and synthesizes baby images from two levels of shape and skin color, which involves image deformation, image fusion, etc. knowledge in many ways. [0003] Typical baby image synthesis technology completes baby image synthesis from two angles of shape synthesis and skin color synthesis. For shape synthesis, the commonly used method is to first use the active shape model (Active Shape Model, hereinaft...

AI Technical Summary

Problems solved by technology

[0004] However, there is a big difference between the facial shape of an adult and that of a baby. In the prior art, the direct linear combination of the shapes of the father, mother and baby to obtain the synthesized target baby shape will cause the synthesized target baby shape to appear distorted, pulled Stretching and other problems, it is not suitable for synthesizing a delicate human face like a baby

In addition, the existing face fusion technology only fuses the facial features, ignoring the importance of the forehead area, which leads to the problem of inconsistent skin color and ghosting in the final synthesized baby image, especially when the hair of the father image or mother image Ghosting is more of an issue when covering the forehead area

Images