Color migration driven X-ray enhanced image quality evaluation method and system

Through the color migration-driven method, X-ray detection images are segmented and grayscale mapped, and two enhancement images are obtained through color migration technology. Their characteristics are calculated and weighted evaluation is performed. This solves the problem of lack of a special quality evaluation algorithm for evaluating the enhancement quality of X-ray detection images in the prior art, and accurately evaluated image quality in a scene without reference image.

CN119672009AActive Publication Date: 2025-03-21HUAZHONG UNIV OF SCI & TECH
4 Cites 0 Cited by

Patent Information

Application Number
CN202411860639.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-17
Publication Date
2025-03-21
Estimated Expiration
2044-12-17

AI Technical Summary

Technical Problem

The prior art lacks a special quality evaluation algorithm for evaluating the enhanced quality of X-ray detection images, and most quality evaluation algorithms are suitable for natural images, making it difficult to effectively evaluate the quality of X-ray detection images in scenarios without reference images or low-quality reference images.

Method used

A color migration-driven X-ray enhancement image quality evaluation method is proposed. By segmenting the X-ray image into a sub-map, a natural image similar to the sub-map texture features is obtained for grayscale mapping, the image is enhanced using the enhancement algorithm to be evaluated, and two enhanced images are obtained through color migration technology, and their texture features, visual perception features and grayscale features are calculated, and weighted calculations are performed to evaluate image quality.

Benefits of technology

In scenarios where there is no reference image or low-quality reference image, the quality of X-ray enhanced images can be accurately evaluated, simulate the visual perception mechanism of the human eye, and make the evaluation results closer to human subjective perception, providing an efficient and low-cost image quality evaluation method.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention belongs to the field of X-ray image quality evaluation, and particularly discloses a color migration driven X-ray enhanced image quality evaluation method and system. According to the method, the thought of bidirectional mapping is put forward, two enhanced images are obtained through two methods of first enhancement and then migration and first migration and then enhancement, and the accuracy of evaluation is ensured through complementation of the two enhanced images; according to the method, human eye visual perception is simulated based on the Retinex theory, the image is decomposed into the reflection component and the illumination component, comprehensive matching degree calculation, reflection component evaluation and illumination component evaluation are carried out on the reflection component and the illumination component of the original image and the enhanced image, a visual perception mechanism of human eyes to the image is simulated, and the image quality is improved. And the evaluation result can be closer to the subjective perception of human on the image quality. Therefore, the quality of the X-ray enhanced image can be quantitatively evaluated in an actual production scene without a reference image or a high-quality reference image, the effects of various image enhancement algorithms are quantitatively evaluated, and a technical support is provided for selecting a more suitable image enhancement algorithm.
Need to check novelty before this filing date? Find Prior Art