Photo restoration system construction method and photo restoration method and system

Abstract

The invention discloses a photo restoration system construction method, a photo restoration method and system, the photo restoration system construction method comprises the following steps: S1, constructing and training a first adversarial neural network, and converting a first old damage photo into a pseudo old damage photo through the first adversarial neural network; S2, constructing a secondadversarial neural network, and training the second adversarial neural network by taking the pseudo-old damage picture generated by the first adversarial neural network and a preset clear picture as training samples; and taking the second adversarial neural network as a photo restoration system. The method has the advantages that the old and damaged photo can be quickly and efficiently restored, and the restoration effect is good.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for constructing a photo restoration system, a photo restoration method and a system. Background technique [0002] In recent years, deep learning technology has achieved remarkable results in many fields, such as the successful application in speech recognition, chat robots and machine translation in the field of natural language processing. In terms of image processing, the emergence of convolutional neural networks has made deep learning far superior to traditional machine learning methods in image classification, face recognition, image segmentation, and target detection. [0003] For old and damaged photos that are damaged, yellowed, moldy, corroded, faded, creased, and spotted due to natural or human factors, at present, image restoration software, such as Photoshop (PS), is usually used to repair the old photos. Manual restoration of damaged photos. Thi...

AI Technical Summary

Problems solved by technology

This repair method often requires strong professional skills, and only people who are proficient in software skills can operate, and the repair time is long and the repair cost is high.

Due to the strong diversity of damage methods and damage degrees of old damaged photos, it is difficult for traditional image processing methods and machine learning methods to achieve ideal results.

Images