Method of performing eye circle correction an image and related computing device
View Patent ↗A method of correcting an eye circle on an image with at least one eye visible and the eye circle being located beneath the eye includes defining a core area of the image for correction, the core area being located substantially below a position of the eye in the image. The method also defines a processing area being larger in area than the core area and including the core area, and defines a surrounding area as a remaining area of the processing area not being located within the core area. An average brightness of the core area is compared to an average brightness of the surrounding area. Then a smoothing process is performed to blend the core area with the surrounding area to correct the eye circle when the average brightness of the core area is greater than that of the surrounding area by more than a first threshold.
1. A method of correcting an eye circle on an image containing a face with at least one eye visible on the face and the eye circle being located beneath the eye, the method comprising:
loading the image into a computing device having a processor, the processor executing the following steps:
defining a core area of the image for correction, the core area being located substantially below a position of the eye in the image;
defining a processing area being larger in area than the core area and including the core area, and defining a surrounding area as a remaining area of the processing area not being located within the core area;
comparing an average brightness of the core area to an average brightness of the surrounding area;
performing a smoothing process to blend the core area with the surrounding area to correct the eye circle when the average brightness of the core area is greater than the average brightness of the surrounding area by an amount greater than a first threshold; and
outputting an enhanced image having the corrected eye circle.
2. The method of claim 1 further comprising:
comparing a brightness of each pixel located within the core area with a second threshold; and
altering the brightness of each pixel to become a new brightness, the new brightness being calculated through an interpolation process using brightness values of surrounding pixels.
3. The method of claim 1 , wherein the core area is located below a position of two eye corners of the eye.
4. The method of claim 3 , wherein the core area is modeled as being a semi-circle, with the points corresponding to the two eye corners being located at opposite ends of a diameter of the semi-circle, and an area of the semi-circle being located below the diameter of the semi-circle.
5. The method of claim 3 , wherein the core area is modeled as being a quadrilateral inscribed in a semi-circle, with the points corresponding to the two eye corners being located at opposite ends of a diameter of the semi-circle, and an area of the semi-circle being located below the diameter of the semi-circle.
6. The method of claim 5 , wherein the processing area has an area approximately twice as large as an area of the core area.
7. The method of claim 1 , wherein the smoothing process is a Gaussian blur process.
8. A computing device for correcting an eye circle on an image containing a face with at least one eye visible on the face and the eye circle being located beneath the eye, the computing device comprising:
a memory for storing the image; and
a processor for loading the image and executing the following steps:
defining a core area of the image for correction, the core area being located substantially below a position of the eye in the image;
defining a processing area being larger in area than the core area and including the core area, and defining a surrounding area as a remaining area of the processing area not being located within the core area;
comparing an average brightness of the core area to an average brightness of the surrounding area;
performing a smoothing process to blend the core area with the surrounding area to correct the eye circle when the average brightness of the core area is greater than the average brightness of the surrounding area by an amount greater than a first threshold; and
outputting an enhanced image having the corrected eye circle.
9. The computing device of claim 8 further comprising:
comparing a brightness of each pixel located within the core area with a second threshold; and
altering the brightness of each pixel to become a new brightness, the new brightness being calculated through an interpolation process using brightness values of surrounding pixels.
10. The computing device of claim 8 , wherein the core area is located below a position of two eye corners of the eye.
11. The computing device of claim 10 , wherein the core area is modeled as being a semi-circle, with the points corresponding to the two eye corners being located at opposite ends of a diameter of the semi-circle, and an area of the semi-circle being located below the diameter of the semi-circle.
12. The computing device of claim 10 , wherein the core area is modeled as being a quadrilateral inscribed in a semi-circle, with the points corresponding to the two eye corners being located at opposite ends of a diameter of the semi-circle, and an area of the semi-circle being located below the diameter of the semi-circle.
13. The computing device of claim 12 , wherein the processing area has an area approximately twice as large as an area of the core area.
14. The computing device of claim 8 , wherein the smoothing process is a Gaussian blur process.