Method and system for eliminating highlight of image affected by highlight reflection on object surface

Abstract

The invention provides a method and a system for eliminating highlight of an image affected by highlight reflection on an object surface. The method comprises the following steps of S1.separating a highlight pixel of the image based on an SVM model; and S2.utilizing adjacent regions with structural similarity of the image to carry out assignment restoration on a highlight pixel region. A statistical learning method is utilized and the highlight pixel of an endoscope image is automatically separated based on an SVM classifier, the method fully utilizes the advantages of sample learning, after a separation model is obtained through training, an optimal classification result can be obtained without artificial participation; an image restoration method based on dynamic search and similarity measure is provided in the aspect of image restoration in order to fully utilize the effective information of the adjacent regions with the structural similarity in the full range, and the natural restoration of the highlight region is realized.

Description

technical field [0001] The present invention relates to the field of image processing, and more specifically, to a method and system for removing high light from an image affected by high light reflection on the surface of an object. Background technique [0002] At present, compared with traditional surgery, minimally invasive surgery only causes very small trauma to human tissue, and this technology can significantly reduce postoperative recovery time and mortality. Therefore, research on minimally invasive surgery and related auxiliary diagnosis and treatment methods has become a hot spot in medical technology research today. [0003] Endoscopic images provide clinicians with a true view of the internal environment as well as organ surfaces. An endoscope usually refers to a fixed tubular camera with a fiber optic light source fixed at the top of the camera for illumination and imaging. During the operation, the surgeon can obtain a real-time image of the surgical scene ...

AI Technical Summary

Problems solved by technology

[0006] Although the above method can obtain the basic separation and visual repair effect of the highlight area, the robustness and accuracy of highlight separation and the visual effect of highlight removal need to be improved and improved.

Moreover, threshold-based methods are often difficult to determine the optimal threshold, and analysis-based algorithms require manual intervention, which restricts the applicability of the algorithm.

Methods based on interpolation or using neighboring pixels at a single distance to repair the highlight area often fail when the highlight area is large

Images