A Curve Noise Reduction Method Based on Active Contour Model
An active contour model and curve technology, applied in the field of curve noise reduction, to achieve the effect of simple algorithm, fast operation speed and noise elimination
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] A curve noise reduction method based on an active contour model, comprising the following steps:
[0035] 1) The iteration formula is defined according to the internal energy formula, and the experimental value of position x after the kth iteration is:
[0036] x k =[X k-1 +c 1 |ΔX k-1 | 2 +c 2 |ΔΔX k-1 | 2 ]; the total energy of the entire curve after the kth iteration is Among them, k is the number of iterations; x∈(n 1 , n 2 );
[0037] 2) The constraint condition is E out (k)-E 0 (k)≤T 1 ; where E 0 (k) is the total energy of the curve before iteration; T 1 It needs to be determined through experiments according to the specific situation. But for any problem, E out The output curves are as figure 2 As shown, so the relative difference formula of the total energy can be adopted, namely
[0038]
[0039] Therefore, δ Eout It can be set to 0.01 according to the precision requirement.
[0040] 3) When the iteration meets the constraints, stop th...
Embodiment 2
[0042] The curve noise reduction method based on the active contour model as described in Embodiment 1, the difference is that the constraints are x 0 is the experimental value at position x before iteration, T 2 is the second threshold set; in practical applications, T 1 The value is not easy to grasp, but for any problem, E out The output curves are as image 3 As shown, therefore, the relative difference formula of the total energy can be used, that is
[0043]
[0044] therefore, It can be set to 0.01 according to the precision requirement.
Embodiment 3
[0046] The curve denoising method based on the active contour model as described in embodiment 1, the difference is that c 1 = 0.3, c 2 = 0.5. c 1 ,c 2 The size of depends on the convergence speed, the larger the value of the coefficient, the faster the convergence.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


