Brightness compensation method for non-uniform illumination tobacco leaf image

Abstract

The invention discloses a brightness compensation method for non-uniform illumination tobacco leaf images. The method comprises the steps: inputting the tobacco leaf image into a network database, carrying out the defogging of the image through a dark channel prior algorithm, achieving the brightness difference compensation of the image through an image enhancement algorithm which automatically adjusts the background contrast, and obtaining the tobacco leaf image after illumination correction. According to the image enhancement stray light removal algorithm capable of automatically adjusting the background contrast based on the picture, on the basis of defogging of a dark channel prior method, the distribution characteristics of background illumination are obtained through polynomial fitting, and the purposes of recovering and enhancing the image are achieved by adjusting a contrast factor. Therefore, the non-uniform illumination background can be effectively recovered, effective earlier-stage processing is provided for actual image application, the original quality of the image is ensured, and a good foundation is laid for accurately identifying the maturity of the tobacco leavesin different environments.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a brightness compensation method for unevenly illuminated tobacco leaf images. Background technique [0002] When taking pictures with mobile phones or cameras in actual field harvesting, during the shooting process of tobacco leaf images, it is often affected by factors such as changes in illumination (changes in shooting angle), shadows, and differences in reflection characteristics of the surface of the object, resulting in uneven illumination on the surface of the imaged tobacco leaves , resulting in some areas of the obtained tobacco leaf image being over-illuminated, while some areas are weakly illuminated, which not only seriously affects the aesthetic effect of the picture, but also misleads the results of tobacco leaf maturity recognition, especially for tobacco leaf images. The processing (such as background extraction and feature value extraction) ...

AI Technical Summary

Problems solved by technology

[0002] When taking pictures with mobile phones or cameras in actual field harvesting, during the shooting process of tobacco leaf images, it is often affected by factors such as changes in illumination (changes in shooting angle), shadows, and differences in reflection characteristics of the surface of the object, resulting in uneven illumination on the surface of the imaged tobacco leaves , res

Images