System and method for detecting an object within an image
A method of detecting an object in an image includes (i) processing, with a machine-learned model, pixel intensities of a pixel pair in a first region of the image, to determine a first confidence score representing a likelihood of the object being present within the first region, and (ii) determining, based on the first confidence score, presence of the object in the first region.
1. A method of detecting an object in an image, comprising:
processing, with a machine-learned model, pixel intensities of a pixel pair in a first region of the image, to determine a first confidence score representing a likelihood of the object being present within the first region; and
determining, based on the first confidence score, presence of the object in the first region.
2. The method of claim 1 , further comprising:
processing, with the machine-learned model, pixel intensities of a pixel pair in an additional region of the image, to determine a second confidence score representing a likelihood of the object being present within the additional region; and
determining, based on the second confidence score, presence of the object in the additional region.
3. The method of claim 2 , further comprising:
determining, based on the first and second confidence scores, presence of the object in the image.
4. The method of claim 2 , wherein the first region and the additional region do not overlap.
5. The method of claim 1 , wherein said processing includes processing pixel intensities of a plurality of additional pixel pairs.
6. The method of claim 1 , further comprising converting the image into a grayscale image prior to the step of processing.
7. The method of claim 6 , wherein said processing includes determining a difference between the pixel intensities.
8. The method of claim 7 , wherein the machine-learned model includes a series of classifiers, each classifier compares the difference to a set of thresholds.
9. The method of claim 1 , further comprising rotating the image by a predetermined angle prior to the step of processing.
10. The method of claim 1 , further comprising, prior to the step of processing, rescaling the image to a resolution that differs from an original resolution of the image.
11. A system for detecting an object within an image, comprising:
a processor; and
a memory communicatively coupled with the processor and storing machine-readable instructions that, when executed by the processor, cause the processor to:
process, with a machine-learned model, pixel intensities of a pixel pair in a first region of the image, to determine a first confidence score representing a likelihood of the object being present within the first region; and
determine, based on the first confidence score, presence of the object in the first region.
12. The system of claim 11 , the memory further storing machine-readable instructions that, when executed by the processor, further cause the processor to:
process, with the machine-learned model, pixel intensities of a pixel pair in an additional region of the image, to determine a second confidence score representing a likelihood of the object being present within the additional region; and
determine, based on the second confidence score, presence of the object in the additional region.
13. The system of claim 12 , the memory further storing machine-readable instructions that, when executed by the processor, further cause the processor to determine, based on the first and second confidence scores, presence of the object in the image.
14. The system of claim 12 , wherein the first region and the additional region do not overlap.
15. The system of claim 11 , the memory further storing machine-readable instructions that, when executed by the processor, further cause the processor to, when processing the pixel intensities of the pixel pair, process pixel intensities of a plurality of additional pixel pairs.
16. The system of claim 11 , the memory further storing machine-readable instructions that, when executed by the processor, further cause the processor to convert the image into a grayscale image prior to said processing.
17. The system of claim 16 , the memory further storing machine-readable instructions that, when executed by the processor, further cause the processor to, when processing said pixel intensities, determine a difference between the pixel intensities.
18. The system of claim 17 , wherein the machine-learned model includes a series of classifiers, each classifier compares the difference to a set of thresholds.
19. The system of claim 11 , the memory further storing machine-readable instructions that, when executed by the processor, further cause the processor to rotate the image by a predetermined angle prior to said processing.
20. The system of claim 11 , the memory further storing machine-readable instructions that, when executed by the processor, further cause the processor to, prior to processing, rescale the image to a resolution that differs from an original resolution of the image.