Image processing methods and devices
An image and filter processing technology, applied in the field of face recognition, to achieve the effect of improving performance, fast processing speed, and improving illumination robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] refer to figure 1 , figure 1 It is a schematic flowchart of the first embodiment of the method for processing an image according to the embodiment of the present invention.
[0048] In Embodiment 1, the method for processing an image includes:
[0049] Step 101, obtaining the high-frequency sub-band coefficients of the image to be processed;
[0050] Preferably, the acquisition of the high-frequency sub-band coefficients of the image to be processed includes:
[0051] The image to be processed is decomposed by non-sampled Shearlet transform to obtain high-frequency sub-band coefficients.
[0052] Specifically, the non-sampled Shearlet transform is introduced into the field of face recognition illumination preprocessing. Compared with the non-subsampled contourlet transform (NSCT), the non-sampled Shearlet transform is faster.
[0053] Step 102, performing illumination filtering processing on the high-frequency sub-band coefficients to obtain a filtered high-frequenc...
Embodiment 2
[0063] refer to figure 2 , figure 2It is a schematic flowchart of the second embodiment of the image processing method according to the embodiment of the present invention.
[0064] On the basis of Embodiment 1, the method also includes:
[0065] Step 104, obtaining the low-frequency sub-band coefficients of the image to be processed;
[0066] Specifically, the image is decomposed by non-sampling Shearlet transform to obtain low-frequency sub-band coefficients.
[0067] Step 105, performing illumination filtering on the low-frequency subband coefficients through the logarithmic total variation quotient image model LTVQI to obtain a filtered low-frequency coefficient subband set;
[0068] Specifically, the logarithmic total variation quotient image model LTVQI is used to de-illuminate the low-frequency sub-band coefficients to obtain face detail information in the low-frequency sub-band. The LTVQI model has good edge-preserving properties for low-frequency illumination re...
Embodiment 3
[0073] refer to image 3 , image 3 It is a schematic flowchart of the third embodiment of the method for processing an image according to the embodiment of the present invention.
[0074] On the basis of the second embodiment, before obtaining the high-frequency sub-band coefficients of the image to be processed, it also includes:
[0075] Step 107, performing logarithmic threshold transformation on the image to be processed.
[0076] Specifically, the logarithmic domain transformation is performed on the face image to obtain the image. The logarithmic transformation converts the product operation into an addition and subtraction operation, which is beneficial to the addition and subtraction operation processing of the threshold function in the subsequent step.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 