Degradation image restoration method based on intelligent page turning and accelerated TV-PDE

• Main Authors: XIAO DI, YU XINHU
• Format: Patent
• Language: Chinese; English
• Published: 19.08.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a degraded image restoration method based on intelligent page turning and accelerated TV-PDE. Comprising an automatic page turning machine automatic input image module, a Relief-MRMR-SVM hybrid support vector machine classifier module, an overall variation smooth denoising module, an overall variation rapid image restoration module and a weighting factor overall variation restoration module. The support vector machine classifier module classifies input data set images into images with stains and long-term degradation images, and de-noising is carried out on the divided images through overall variation smoothing. And finally, obtaining a conclusion by comparing the performance of the two different types of pictures in utilizing the rapid image of the improved overall variation and the performance of weighting factor overall variation restoration. The method is simple and intelligent in structure, can greatly improve the visual effect and eliminate the gradient effect, is superior to an