Face portrait compositing method based on Bayesian inference

Abstract

The invention discloses a face portrait compositing method based on Bayesian inference, which mainly solves a problem that an existing method does not consider similarity constraints between adjacent image blocks in a neighbor finding or weight solving stage. The scheme of the face portrait composting method comprises the steps of 1, dividing a training portrait sample set, a training photo sample set and a test sample set; 2, dividing all images into image blocks and forming block sets; 3, dividing the training photo block set and the corresponding portrait block set into a plurality of subsets; 4, selecting nearest neighbor blocks from a training photo-portrait block set; 5, carrying out neighbor block reselection on the nearest neighbor blocks according to an Euclidean distance in the training photo-portrait block set, and solving a linear combination weight of the reselected neighbor blocks; 6, solving portrait blocks to be composited according to the neighbor blocks and the combination weight; and 7, iteratively executing the steps 5-6 for N times, and fusing to acquire a final composite portrait. The face portrait composting method has the advantages of high resolution of a composite result and more complete details, and can be applied to face retrieval and recognition.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a face image synthesis method, which can be used for face retrieval and recognition in criminal investigation and case solving. Background technique [0002] Face portrait synthesis plays a huge role in digital entertainment and criminal investigation. For example, in 3D chocolate printing, it is usually necessary to use the face portrait synthesis algorithm to synthesize a black-and-white portrait as the printing track of the printer; in the process of criminal investigation and case detection, it is often not always possible to obtain photos of criminal suspects, but often witnesses Some descriptions or video image data, in order to quickly solve the case, a feasible solution is to draw a portrait based on the witness description and the clues provided by the video image, and then use the portrait to confirm the identity. However, due to the large differences in...

AI Technical Summary

Problems solved by technology

However, the shortcomings of this method are: because the similarity constraints between adjacent image blocks are not considered in the model, the synthesis results have the defects of block effects and blurred details.

However, the disadvantage of this method is that only one training image block is selected for image synthesis for each photo block position, resulting in deformation of the synthesis result.

However, the synthesis result of this method does not consider the similarity constraints between adjacent image blocks when selecting the neighbors, resulting in noisy and blurred synthesis results.

Images