Robustness face super-resolution processing method based on contour inspection

Abstract

The invention provides a robustness face super-resolution processing method based on contour inspection, which comprises the following steps: on the basis of a traditional face super-resolution method based on manifold, simultaneously selecting two types of image features for mass reduction process robustness and simultaneously taking as a criterion of image similarity in the algorithm process through coupling the two types of image features into an (Locally embedding) algorithm. The robustness face super-resolution processing method solves the problem incapable of being better solved by a traditional method that serious noise and fuzziness are lack of reality to a super-resolution recovery effect of a single frame face image in the monitoring and imaging process.

Description

technical field [0001] The invention relates to the field of image processing (image restoration), aiming at the demand for face image restoration in low-quality surveillance video, and specifically relates to a robust face super-resolution processing method based on contour prior. Background technique [0002] Face super-resolution technology estimates high-resolution face images from existing low-resolution face images. With the rapid development of surveillance systems, surveillance systems are playing an increasingly important role in the criminal investigation industry, such as security precautions, video evidence collection, and criminal investigations. Among them, face images, as one of the direct evidence, occupy an important position in case analysis and court evidence collection. However, due to the relatively long distance between the target object and the camera under the existing conditions, there are very few pixels available for the captured surveillance face...

AI Technical Summary

Problems solved by technology

To sum up, most of these existing methods only follow the traditional technical ideas and use single differences such as image pixel values ​​and image gradient values ​​as the basis of face similarity criteria and algorithms. In the process of processing low-quality images in general environments , you can get a good effect, but when the image quality is very low, the pixels will be severely damaged and aliased, and the features used to represent the image are easily damaged. The image restored by the traditional method is not impressive. people are satisfied

[0004] In 2010, Lan[4] proposed a face super-resolution method based on shape constraints to address the problem of serious image pixel damage caused by severe blur and noise in the monitoring environment, adding shape constraints to the traditional PCA architecture as similarity Metric criteria, using the robustness to interference when human eyes recognize shapes to artificially add shape feature points as constraints, and optimize the reconstruction results of low-quality images

This method alleviates the interference of severe pixel damage to the reconstruction results to a certain extent, but the process of obtaining features through manual intervention in this method has a large chance, and it is difficult to guarantee the accuracy and stability of the restoration results.

Images