Edge detection in images
View Patent ↗An edge detection engine operates to scan an image to identify edges within the image. An annular aperture is used to locate the edges in the image. An output image is generated by the edge detection engine that identifies the locations of the edges found in the image.
1. A method of detecting edges within a digital image, the method comprising:
processing at least a portion of the digital image, using a computing device, in a pixel-by-pixel manner including at an analysis point in the digital image, by:
identifying pixels surrounding the analysis point;
identifying a location of a bisection that divides the pixels surrounding the analysis point into two halves;
determining an angle of the bisection that maximizes a difference in intensities of the pixels between the two halves, the determined angle of the bisection identifying the presence of an edge in the digital image;
storing the determined angle of the bisection, in correspondence with a pixel location, in a computer readable non-transitory storage device to identify an edge point in the image.
2. The method of claim 1 , wherein identifying pixels surrounding the analysis point involves the use of an annular aperture mask.
3. The method of claim 2 , wherein the annular aperture mask is generated using a circle drawing algorithm.
4. The method of claim 1 , wherein determining that an edge is present in the digital image comprises determining whether the difference in intensities between the two halves is greater than a threshold.
5. The method of claim 1 , further comprising moving the analysis point sequentially across the pixels of at least a portion of the digital image and repeating the processing.
6. The method of claim 1 , further comprising generating an angle and magnitude map and storing the angle of the bisection and a magnitude of the difference in intensities of the pixels between the two halves in the angle and magnitude map for the analysis point.
7. The method of claim 1 , further comprising generating an output image after determining that an edge is present in the digital image.
8. The method of claim 7 , wherein generating output data comprises drawing a line in the output image at the angle of the bisection.
9. The method of claim 8 , further comprising:
checking a set of pixels perpendicular to the bisection before drawing the line to determine a point of greatest magnitude; and
shifting a position of the line to the point of greatest magnitude.
10. An edge detection system comprising:
a computing device comprising:
a processing device; and
a computer readable non-transitory storage device storing data instructions that, when executed by the processing device generates an edge detection engine comprising:
an annular aperture generator that operates to generate an annular aperture using a circle drawing algorithm;
a line generator that generates lines representative of a set of bisectors of the annular aperture, wherein each of the bisectors divides the annular aperture into a first half having a first intensity value and a second half having a second intensity value;
an image scanning engine that utilizes the annular aperture as a mask to scan a digital image, that utilizes the set of bisectors to identify a bisection angle that results in a greatest difference of intensity between the first and second intensity values for the set of bisectors and that identifies edges within the digital image; and
an output data generator that utilizes the lines to represent the edges in the output image.
11. The computing device of claim 10 , wherein the circle drawing algorithm is Bresenham's circle algorithm.
12. The computing device of claim 10 , wherein the annular aperture has a thickness of one pixel.
13. The computing device of claim 10 , wherein the annular aperture has a radius in a range from about 5 pixels to about 25 pixels.
14. The computing device of claim 10 , wherein the line generator utilizes Bresenham's line algorithm.
15. The computing device of claim 10 , wherein the line generator generates lines representative of the set of all possible bisectors of the annular aperture.
16. The computing device of claim 10 , wherein the image scanning engine generates an angle and magnitude map identifying an angle and a magnitude for potential edge identified in the digital image.
17. A medical instrument comprising:
a processing device;
an image capture device operable under direction of the processing device to capture an input image; and
a non-transitory storage device including an edge detection engine, the edge detection engine including instructions executable by the processor to process the input image to detect edges within the input image by:
processing the image using an annular aperture mask and a set of bisectors of the annular aperture mask, wherein each of the bisectors divides the annular aperture mask into a first half having a first intensity and a second half having a second intensity;
utilizing the set of bisectors to identify a bisection angle that results in a greatest difference of intensity between the first and second intensity values for the set of bisectors; and
comparing the greatest difference of intensity to a threshold value to detect an image edge.
18. The medical instrument of claim 17 , wherein the medical instrument is an ophthalmoscope.
19. The medical instrument of claim 17 , wherein the medical instrument is a culposcope.