An image enhancement method, device, equipment and storage medium
An image enhancement and image technology, applied in the field of image processing, can solve problems such as feature enhancement that cannot be of interest, and achieve the effect of noise suppression
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] figure 1 It is a flow chart of an image enhancement method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where it is necessary to enhance both small feature points in the image and edge features of the image during the image enhancement process. The method can be performed by an image enhancement device, such as figure 1 As shown, the method of this embodiment specifically includes:
[0030] S110. Set at least two filter kernels of different sizes, wherein the filter kernels of different sizes respectively correspond to features of the target image at different scales.
[0031] In this embodiment, in order to enhance the features of interest in the target image (that is, the original image) as much as possible, it is preferable to use filter kernels of different sizes to perform enhancement processing on the target image, wherein the more interesting features in the target image are The more, the more filter kernels ...
Embodiment 2
[0045] Figure 2a It is a flowchart of an image enhancement method provided by Embodiment 2 of the present invention. On the basis of the above-mentioned embodiments, this embodiment may optionally perform image enhancement processing on the acquired target image based on the at least two filter kernels, and generate a smooth image and an enhanced image corresponding to each filter kernel, including: based on the at least two filter kernels Two filter kernels of different sizes filter the acquired target image respectively to generate at least two corresponding smooth images; the pixel intensity of the target image is compared with each smooth image point by point to generate processing images corresponding to filter kernels; performing image enhancement on each processed image to generate enhanced images corresponding to each filter kernel. Further, it is optional to perform image enhancement on each processed image, and generate an enhanced image corresponding to each filte...
Embodiment 3
[0068] image 3 It is a flow chart of an image enhancement method provided by Embodiment 3 of the present invention. In this embodiment, on the basis of the foregoing embodiments, the optional filter kernel is an average filter kernel or a bilateral filter kernel. Further, optionally, selecting a smooth image includes: comparing the sizes of the filter kernels, and determining the smooth image corresponding to the filter kernel with the largest size as the smooth image satisfying the preset condition. Further, before reconstructing the selected target image and / or one of the smoothed images and each enhanced image, the method further includes: performing gray balance processing on the selected one of the smoothed images. Such as image 3 As shown, the method of this embodiment specifically includes:
[0069]S310. Set at least two filter kernels of different sizes, wherein the filter kernels of different sizes respectively correspond to features of the target image at differ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More