Edge detection for mixed raster content (mrc) images for improved compression and image quality

A system for detecting edge pixels in an image plane based on intensity and neutrality of a current pixel, when separating an image signal into a set of image planes, the system comprising:

• a min-max module configured to search for a minimum value and a maximum value of a specified characteristic within at least one predefined neighborhood pixel window centered on a current pixel in the image signal, wherein the predefined neighborhood pixel window comprises the edge pixels;
• and
• a dynamic threshold module configured to detect the edge pixels in the image plane based on predetermined criteria, wherein the predetermined criteria for detecting the edge pixels comprises determining whether:
• (a) a difference between the maximum value and the minimum value of the specified characteristic is greater than or equal to a predetermined threshold, wherein the predetermined threshold is based on intensity and neutrality of the current pixel in the image signal;
• and
• (b) (i) a difference between a current value and the minimum value of the specified characteristic, or (ii) a difference between a current value and the maximum value of the specified characteristic is greater than or equal to a predetermined threshold, wherein the predetermined threshold is based on the intensity and the neutrality of the current pixel in the image signal.

A method for detecting edge pixels in an image plane based on intensity and neutrality of a current pixel, when separating an image signal into a set of image planes, the method comprising:

• dividing the image plane into one or more regions based on the intensity and the neutrality of the current pixel, wherein the intensity of the current pixel is dependent on a luminance value of a luminance channel of the current pixel, and the neutrality of the current pixel is dependent on a chrominance value of a first chrominance channel of the current pixel, and a chrominance value of a second chrominance channel of the current pixel;
• searching for a minimum value and a maximum value of a specified characteristic within at least one predefined neighborhood pixel window centered on the current pixel in the one or more regions of the image plane, wherein the predefined neighborhood pixel window comprises the edge pixels;
• and
• detecting, via a dynamic threshold module, the edge pixels in the one or more regions in the image plane based on predetermined criteria,
• wherein the predetermined criteria for detecting the edge pixels in the one or more regions in the image plane comprises determining whether:
• (a) a difference between the maximum value and the minimum value of the specified characteristic is greater than or equal to a predetermined threshold, wherein the predetermined threshold is based on the intensity and the neutrality of the current pixel in the image signal;
• and
• (b) (i) a difference between a current value and the minimum value of the specified characteristic, or (ii) a difference between a current value and the maximum value of the specified characteristic is greater than or equal to a predetermined threshold, wherein the predetermined threshold is based on the intensity and the neutrality of the current pixel in the image signal.