Underwater image noise reduction method and system based on improved wavelet threshold
An underwater image and wavelet threshold technology, applied in the field of computer vision, can solve the problems of blurred edge contour, loss of high-frequency information, discontinuity and other problems in reconstructed images, so as to reduce edge blur, improve accuracy, and improve details and edge information. Effect
Pending Publication Date: 2021-05-04
DALIAN MARITIME UNIVERSITY
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Among them, although the hard threshold function can effectively remove image noise, its discontinuous characteristic at the threshold makes it generate more artificial noise points in images with more edge information; although the soft threshold function reduces the The number of artificial noise points in the function, but more high-frequency information will be lost in the noise reduction, making the edge contour of the reconstructed image blurred
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] In order to make the technical solutions and advantages of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the drawings in the embodiments of the present invention:
[0027] figure 1 It is the overall flowchart of the present invention; a kind of underwater image denoising method that improves wavelet threshold, comprises the following steps:
[0028] S1: Perform wavelet decomposition on the original image containing noise to obtain the original wavelet coefficient matrix W(G);
[0029] S2: Use the improved threshold function and adaptive threshold estimation method to process the obtained original wavelet coefficient matrix W(G) to obtain the improved wavelet coefficient matrix
[0030] S3: Using the improved wavelet coefficient matrix Carry out wavelet inverse transformation to obtain the reconstructed image, and thus obtain the denoised image.
...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an underwater image noise reduction method and system based on an improved wavelet threshold, and belongs to the field of computer vision, and the method comprises the following steps: carrying out the wavelet decomposition of an original image containing noise, and obtaining an original wavelet coefficient matrix W (G); processing the obtained original wavelet coefficient matrix W (G) by using an improved threshold function and a self-adaptive threshold estimation method to obtain an improved wavelet coefficient matrix, and performing wavelet inverse transformation by using the improved wavelet coefficient matrix to obtain a reconstructed image so as to obtain a noise-reduced image; on the basis of wavelet threshold transformation, an improved threshold function is provided in combination with a soft and hard threshold function, and the function can effectively overcome the defects of the existing soft and hard threshold function; image information is effectively reserved, the phenomenon that the edge of a target object is blurred is reduced to a certain extent, the wavelet threshold noise reduction technology is adopted, underwater image information can be reserved and recovered, and then the precision of follow-up binocular stereo positioning is improved.
Description
technical field [0001] The invention relates to the field of computer vision, in particular to an underwater image noise reduction method and system with improved wavelet threshold. Background technique [0002] At present, the main means for people to explore marine resources is the visual system, but due to the absorption and scattering of light by water and the influence of suspended particles in the water, the images captured by the camera underwater will contain a lot of noise, making the captured images It becomes blurred or even loses many image features, which seriously affects the subsequent higher-level recognition and positioning tasks of the image. During the process of underwater light propagation, suspended particles will have an effect on the light, deflecting the light and changing the direction of propagation, which is the scattering effect of water on light. Among them, the forward scattering will blur the underwater image, while the back scattering will i...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00
CPCG06T2207/20064G06T2207/30184G06T5/70
Inventor 赵红李春艳白瑾珺陈廷凯王荣峰王宁田嘉禾陈帅唐路源鲁挺
Owner DALIAN MARITIME UNIVERSITY