Comprehensive evaluation method and evaluation system for scanned image quality

Abstract

The invention is applied to the field of image quality evaluation, and provides a comprehensive evaluation method for scanned image quality. The method includes: step S1, pre-processing scanned images; step S2, performing no-reference image quality evaluation of the pre-processed scanned images, and obtaining a no-reference image quality evaluation index D1; step S3, performing reference image quality evaluation of the pre-processed scanned images, and obtaining a reference image quality evaluation index D2; and step S4, calculating and obtaining an image quality comprehensive evaluation index D according to the no-reference image quality evaluation index D1 and the reference image quality evaluation index D2 and respective weights. According to the method, the image quality comprehensive evaluation index is provided, many evaluation indexes in the market are converged to one, the evaluation of the image quality by human subjective consciousness is replaced, and unified description of the image quality is realized.

Description

technical field [0001] The invention belongs to the field of image quality evaluation, in particular to a scanning image quality evaluation method and evaluation system based on multi-objective and multi-constraint. Background technique [0002] Scanning image quality is mainly manifested in two aspects of image intelligibility and fidelity. The degree of intelligibility reflects the ability of the collected images to provide information to humans or computers, and is related to image applications; the degree of fidelity reflects the deviation between the scanned image and the standard image, and the smaller the deviation, the more realistic the image. A more intelligible or realistic image indicates a higher image quality, and vice versa. At present, there are too many image quality evaluation indicators, and each has its own evaluation method, which is complicated and complicated. In order to achieve a unified description of image quality, it is necessary to use mathemati...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a scanning image quality evaluation method based on multi-objective and multi-constraints, which aims to solve the problem that the current image quality evaluation methods are not uniform and focus is different, which leads to the evaluation results mixed with too many subjective factors. , providing a comprehensive image quality evaluation index

Images