Infrared image noise suppression method for enhancing details

Abstract

The invention discloses an infrared image noise suppression method for enhancing details. Different noise reduction methods are used for images in different areas by using noise classification; main noise in the selected area is effectively eliminated, detail information of the infrared image and edge information of the image are effectively reserved through a Sobel operator, the two images are fused through a Laplace pyramid fusion algorithm, and an image with a large number of image details and lower noise compared with a traditional method is obtained. The method is simple in thought, low in complexity, moderate in calculated amount and good in effect.

Description

technical field [0001] The invention belongs to the technical field of infrared image processing, and proposes an infrared image noise suppression method for enhancing details according to the characteristics that infrared images are greatly affected by noise, image contrast is low, and graphics are blurred. Background technique [0002] With the continuous development and progress of technology, infrared detection technology is more and more used in surveying and mapping, medical and military fields. , low imaging effect, and almost no texture information in infrared images. Affected by these problems, compared with visible light images, infrared images will lose a lot of image information and contour information, making it impossible for humans or machines to obtain corresponding image detail information. Or get wrong image information, which increases the difficulty for people or machines to recognize real images, which may lead to wrong judgments and cause serious conseq...

AI Technical Summary

Problems solved by technology

The mean filter algorithm can effectively remove Gaussian noise in infrared images, but it will lose the details of the image; the median filter algorithm can effectively reduce the salt and pepper noise of infrared images, but it will reduce the resolution of the image and make the image blurred; The noise reduction algorithm of infrared images based on neural network can effectively reduce the influence of compound noise, but its algorithm complexity is high, the calculation amount is huge, and its robustness is not high

[0004] Traditional filtering methods cannot effectively eliminate the impact of various noises on image quality. Therefore, the noise reduction methods for infrared image composite noise, whether improving traditional noise reduction algorithms or proposing new noise reduction methods, have become the focus of widespread attention.

The shortcomings of the currently used noise reduction algorithm mainly include: (1) the compound noise formed by various noises cannot be effectively eliminated, so that the noise reduction effect of the image cannot reach the expected effect; (2) although the noise reduction effect has achieved the expected effect However, part of the detailed information of the image is eliminated while the noise is reduced, so that the detailed information of the image is lost; (3) the noise reduction effect achieves the expected effect while reducing the resolution of the image, which reduces the image clarity; (4) noise reduction The complexity of the algorithm is high and the amount of calculation is large, which is not conducive to the hardware implementation of the algorithm in the later stage

Images