System for identifying low-frequency halftone screens in image data
View Patent ↗In a system, such as in a digital copier, for classifying image data derived from an original image, the image data is enhanced before submission to a classification analysis. In the enhancement, portions of the image having a measured roughness (degree of gray level discontinuity) within a certain range are artificially increased in roughness. This increased roughness in the enhanced image data serves to increase confidence of the classification analysis for detecting low-frequency halftone screens, so that such low-frequency halftone areas are not misclassified as contone or high-frequency halftone areas.
1. A method of obtaining and processing image data, comprising;
scanning an original image to obtain original image data, the original image data including at least one sequential line of pixel data having a plurality of pixels:
for each pixel in the line, determining a roughness associated with the pixel;
if the roughness of a pixel is less than a predetermined low roughness threshold, setting the roughness associated with the pixel to a predetermined default roughness value, thereby yielding enhanced image data;
submitting the enhanced image data to a classification analysis;
submitting the original image data for subsequent processing, using a result of the classification analysis performed on the enhanced image data; and
following the processing, writing the processed image data to a memory.
2. The method of claim 1 , further comprising
during the determining step, maintaining a hysteresis count for each pixel in the line of pixel data;
if, for a pixel in the line, if the roughness is less than the predetermined low roughness threshold, decrementing the hysteresis count for a subsequent pixel in the line.
3. The method of claim 1 , further comprising
during the determining step, maintaining a hysteresis count for each pixel in the line of pixel data;
if, for a pixel in the line, if the roughness is greater than a predetermined high roughness threshold, setting the hysteresis count for a subsequent pixel in the line to a predetermined new value.
4. The method of claim 1 , further comprising
during the determining step, maintaining a hysteresis count for each pixel in the line of pixel data; and
wherein the setting the roughness to a predetermined default roughness value step occurs only if the hysteresis count for the pixel is not zero.
5. The method of claim 4 , wherein roughness is calculated as a difference between a maximum and minimum darkness values of a plurality of small pixel window sums within a large pixel context around the pixel.
6. The method of claim 1 , wherein the determining is applied to a one-dimensional line of pixels in an image.