Detection method and device for image scratch
A scratch and image technology, applied in the field of image processing, can solve the problems of low accuracy in locating the scratch area and the inability to accurately locate the range of the scratch area, so as to achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0032] Such as figure 1 As shown, it is a flowchart of a method for detecting image scratches provided by an embodiment of the present invention. The method includes:
[0033] 101: Project the single-color component in the two-dimensional image along the scratch direction to obtain the sum of one-dimensional scratch projections;
[0034] 102: Calculate the filter function of the pixel according to the complex wavelet function;
[0035] 103: Convolve the filter function with the sum of the one-dimensional scratch projections to obtain single-color complex ridge coefficients, and calculate the fused complex ridge coefficients of the image according to the single-color complex ridge coefficients;
[0036] 104: Determine the edge of the scratch according to the imaginary part of the fused complex ridge wave coefficient.
[0037] Through the method provided in this embodiment, the complex Ridgelet coefficient is obtained by performing complex Ridgelet transformation on the image,...
Embodiment 2
[0039] In practical applications, since the image scratches appear to be approximately vertical (inclination angle<5°), this embodiment takes the image scratches being vertical as an example. For scratches with a certain inclination angle, through the following examples method to process.
[0040] In most cases, image scratches can be approximated by vertical lines. Such as figure 2 Shown is a schematic diagram of image scratches. figure 2 Among them, n represents the discrete horizontal coordinates of the image, m represents the discrete vertical coordinates of the image, and the image scratches are vertical and appear as vertical lines perpendicular to the n axis. Wherein, the values of n and m are both integers or natural numbers.
[0041] Since a color image can be processed by dividing three basic colors, the embodiment of the present invention takes the division of the three primary colors of R (red), G (green) and B (blue) as an example for illustration. Images ...
Embodiment 3
[0089] In this embodiment, on the basis of the previous embodiment, the half-integer precision complex Ridgelet coefficient r obtained after fusion s (x), x∈N∪(N+1 / 2)(s=s 1 ,...,s J is to decompose the scale), after detecting the straight line features at each scale s, the salient straight lines detected at multiple scales s are fused to determine the final candidate scratch interval.
[0090] Such as Figure 4 As shown, the flow chart of the detection method for image scratches provided by this embodiment, the method includes:
[0091] 401: Obtain the interval of the significant straight line under multiple scales.
[0092] Among them, according to the second embodiment, the interval of the significant straight line in the interval of all possible scratches under the s scale can be obtained; when the value of the decomposition scale s is s 1 ,...,s J When , the interval of the significant straight line at multiple scales can be obtained by the method of the above embodim...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More