Computer imaging pre-processing for automated medication dispensing analysis

A method comprising:

• capturing a first image of medication held by a receptacle;
• creating a second image based on the first image in which each pixel of the second image is identified by a single value;
• dividing pixels of the second image into first and second mutually exclusive subsets of pixels, wherein pixels of the first subset are more likely to correspond to the receptacle than are pixels of the second subset;
• processing the second image along a first axis by, for each point along the first axis:
• defining a line that is perpendicular to the first axis and intersects the first axis at the point;
• counting how many of the pixels in the second image located along the line are in the first subset;
• and
• recording the count;
• determining a first local maximum of the counts and a second local maximum of the counts;
• estimating a position of a first edge of the receptacle based on a position of the first local maximum along the first axis;
• estimating a position of a second edge of the receptacle based on a position of the second local maximum along the first axis;
• defining an ellipse based on the first and second edges;
• and
• outputting a processed image based on the first image, wherein the processed image indicates that areas of the first image that are outside the defined ellipse are excluded from further processing.

A non-transitory computer-readable medium storing instructions, the instructions comprising:

• capturing a first image of medication held by a receptacle;
• creating a second image based on the first image in which each pixel of the second image is identified by a single value;
• dividing pixels of the second image into first and second mutually exclusive subsets of pixels, wherein pixels of the first subset are more likely to correspond to the receptacle than are pixels of the second subset;
• processing the second image along a first axis by, for each point along the first axis:
• defining a line that is perpendicular to the first axis and intersects the first axis at the point;
• counting how many of the pixels in the second image located along the line are in the first subset;
• and
• recording the count;
• determining a first local maximum of the counts and a second local maximum of the counts;
• estimating a position of a first edge of the receptacle based on a position of the first local maximum along the first axis;
• estimating a position of a second edge of the receptacle based on a position of the second local maximum along the first axis;
• defining an ellipse based on the first and second edges;
• and
• outputting a processed image based on the first image, wherein the processed image indicates that areas of the first image that are outside the defined ellipse are excluded from further processing.