Image quality evaluation method and system

Abstract

The invention belongs to the technical field of image processing and computer vision, and discloses an image quality evaluation method and system. The method comprises the following steps: image preprocessing: carrying out equal-proportion scaling and normalization on an image, and carrying out default value filling on a lacking part; image effective position prediction and image filtering: determining a certificate image position and a certificate category based on a pixel-level segmentation-classification technology model, and filtering the image by setting a threshold value; correcting the to-be-evaluated image: segmenting the certificate image according to the certificate image position information and correcting the certificate image; multi-dimensional quality evaluation: performing quality evaluation and scoring from five dimensions of type, integrity, definition, light spot and PS judgment based on deep learning and a convolutional neural network technology model; and outputting a result in a structured manner. According to the method, the to-be-evaluated certificate image is effectively distinguished by adopting a pixel-level image segmentation-classification technology, multi-dimensional evaluation scoring is performed in combination with deep learning, a convolutional neural network technology and a traditional method, an extracted prediction result is efficient and accurate, and an evaluation result is accurate.

Description

technical field [0001] The invention belongs to the technical field of image processing and computer vision, and in particular relates to an image quality evaluation method and system. Background technique [0002] In the daily data review process, whether the collected images meet the relevant specifications is an important prerequisite for review tasks or many other downstream tasks. General image quality-related specifications include but are not limited to whether the image is the original image, whether the image is complete, whether the image is blurred, whether there are PS traces in the image, and so on. How to quickly and automatically judge and score image quality is crucial to the automated data review and approval procedures. [0003] Existing data review methods are roughly divided into two types: (1) manual review. This method is incapable of reviewing and approving large quantities of data. At this time, it often takes a lot of manpower and time to invest in...

AI Technical Summary

Problems solved by technology

This method is incapable of reviewing and approving large quantities of data. At this time, it often takes a lot of manpower and time to invest in the work of reviewing images, resulting in high costs and unrelieved error rates. ; (2) Semi-manual and semi-automatic

This method generally uses the traditional image processing mode to judge a certain aspect of the image, such as sharpness, and then manually proofread the image again; due to the use of traditional technology, this method often cannot support all The pictures collected by collection methods (scanner, camera, mobile phone, etc.), especially the pictures collected by mobile phones, therefore, this kind of semi-manual and semi-automatic is also time-consuming and laborious.

Images