Method and apparatus for implementing a streaming two-dimensional digital image segmentation

A digital image processor useful for segmenting a digital image, the digital image being comprised of a plurality of image elements disposed in an arrangement of horizontal rows and vertical columns, the image elements including a first type positioned in a background portion and a second type positioned in a non-background portion, the second type of the image elements each having a value defining by a strength of a property, there being at least two classifications of the second type of image elements based on the property, the system comprising:

• means for determining whether selected image elements positioned along a horizontal row are of the second type;
• means for calculating a first average of the values of the selected image elements if the selected image elements are of the second type;
• means for determining whether the first average meets a predetermined threshold to obtain a first classification result;
• means for calculating a second average for each of the selected elements, the second average being based on a stored value representing a sum of the values of the each selected element and adjacent image elements of the second type disposed along a vertical column in which the each selected element is positioned;
• means for determining whether each of the second averages meets the predetermined threshold to obtain respective second classification results;
• and,
• means for classifying each of the selected elements based on the first and second classification results.

A method for segmenting a digital image, the digital image being comprised of a plurality of image elements disposed in an arrangement of horizontal rows and vertical columns, the image elements including background image elements and non-background image elements, the non-background image elements each having a value defining a strength of a property, there being at least two classifications of the non-background image elements based on the property, the method comprising steps of:

• accessing the digital image;
• scanning the digital image on an image element by image element basis, the scanning being conducted in a background mode if an adjacent image element previously scanned is a background element and in a non-background mode if the adjacent image element previously scanned is a non-background element;
• determining whether the scanning is in the background mode;
• successively selecting background elements and initializing a column strength value for each background element if the scanning is in the background mode;
• converting the scanning to the non-background mode if a non-background element is detected during the scanning in the background mode;
• summing values corresponding to the property for successive adjacent non-background elements and adding values corresponding to the property to the column strength value for each non-background element while in the non-background mode;
• detecting a background element thereby indicating an end of a run of successive adjacent non-background elements;
• calculating a first average for the successive adjacent non-background elements disposed along a selected row based on the summed values and a length of the run;
• determining whether the first average strength meets a predetermined threshold to obtain a first classification result;
• calculating a second average for each of the selected elements, the second average being based on the column strength value of the each selected element;
• determining whether each of the second averages meets the predetermined threshold to obtain respective second classification results;
• and,
• classifying each of the successive adjacent elements based on the first and second classification results.