A Two-Stage Face Portrait Generation Method Combined with Local and Global Features

Abstract

The invention discloses a two-stage human face portrait generation method combining local and global characteristics. The steps are: (1) dividing samples; (2) dividing image blocks; (3) dividing image block subsets; (4) generating initial synthetic portrait blocks; (5) generating final synthetic portrait blocks; (6) synthesizing portraits. The present invention adopts a staged method. In the first stage, the sample block is divided into multiple subsets with globality, and the initial image block is synthesized in the subset. In the second stage, the sample block is divided into multiple subsets with locality. Synthesizing the final image block in the subset can synthesize a high-quality image with a clean background and clear details. The present invention only uses simple K-means clustering and sample block position information to divide sample block sets, uses simple mapping to generate synthetic portraits, and greatly improves the speed of synthetic portraits.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a two-stage human face portrait generation method combining local and global characteristics in the technical field of pattern recognition and computer vision. The invention can be used for face retrieval and recognition in the field of public security. Background technique [0002] In the criminal investigation and pursuit, the public security department has a database of citizens’ photos, combined with face recognition technology to determine the identity of criminal suspects. However, it is generally difficult to obtain photos of criminal suspects in practice, but they can be obtained with the cooperation of painters and witnesses. Sketch portraits of criminal suspects for subsequent face retrieval and recognition. Due to the great difference between portraits and ordinary face photos, it is difficult to obtain satisfactory recognition results by directly using...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the algorithm complexity is high and the image synthesis speed is slow

The disadvantage of this method is that because the method uses selective integration technology, the generated pseudo-portrait needs to be weighted and averaged, resulting in unclean background and unclear details, which in turn reduces the quality of the generated image.

The disadvantage of this method is that the quality of the synthesized image depends mostly on the initial image synthesis method, and the use of sparse representation for image synthesis will lead to too slow image synthesis

Images