Systems and methods for digitized document image text contouring

A system, comprising:

• a processor;
• and
• a memory storing an image,
• wherein the processor is configured to:
• determine a linearity of an image based on one or more vertical edges and horizontal edges of the image, wherein determining the linearity of the image comprises:
• identifying, via canny edge detection, a vertical edge of the image and a horizontal edge of the image,
• identifying, via canny edge detection one or more boundaries of the image,
• calculating a first degree of rotation between the vertical edge of the image and at least one of the one or more boundaries of the image, and
• calculating a second degree of rotation between the horizontal edge of the image and at least one of the one or more boundaries of the image;
• apply, based on the determination, one or more linearity adjustments to the image;
• identify, via canny edge detection, a shape within an image;
• generate a geometric point array based on the shape;
• create a bounding box derived from the geometric point array;
• generate a contour via a pass over a preprinted portion of the image;
• smudge the shape to create a pixel blob;
• and
• apply a filter to transform the pixel blob to contact the preprinted portion.

A computer readable non-transitory medium comprising computer-executable instructions that are executed on a processor and comprise the steps of:

• determining a linearity of an image based on one or more vertical edges and horizontal edges of the image, wherein determining the linearity of the image comprises:
• identifying, via canny edge detection, a vertical edge of the image and a horizontal edge of the image,
• identifying, via canny edge detection one or more boundaries of the image,
• calculating a first degree of rotation between the vertical edge of the image and at least one of the one or more boundaries of the image, and
• calculating a second degree of rotation between the horizontal edge of the image and at least one of the one or more boundaries of the image;
• applying, based on the determination, one or more linearity adjustments to the image;
• identifying, via canny edge detection, a shape within an image;
• generating a geometric point array based on the shape;
• creating a bounding box derived from the geometric point array;
• generating a contour via a pass over a preprinted portion of the image;
• smudging the shape to create a pixel blob;
• and
• applying a filter to transform the pixel blob to contact the preprinted portion.