Jagged edge reduction using kernel regression

Abstract

An apparatus may include a processor and memory to store instructions to direct the processor to: detect edges in an image, including portions of the image that correspond to a jagged edge configuration; selectively apply kernel regression to portions of the image that correspond to the jagged edge configuration; and output a corrected image.

1 - 20 . (canceled) 
     
     
         21 . An apparatus, comprising:
 a processor; and   memory to store instructions to direct the processor to:
 detect edges in an image, including portions of the image that correspond to a jagged edge configuration; 
 selectively apply kernel regression to portions of the image that correspond to the jagged edge configuration; and 
 output a corrected image. 
   
     
     
         22 . The apparatus of  claim 21 , wherein the memory further includes instructions to direct the processor to:
 dilate the detected edges of the image to include portions of the image adjacent to the detected edges in a dilated image region; and   selectively apply kernel regression to the portions of the image within the dilated image region.   
     
     
         23 . The apparatus of  claim 21 , wherein the memory further includes instructions to direct the processor to compare the image to jagged edge configurations. 
     
     
         24 . The apparatus of  claim 23 , wherein the memory further includes instructions to direct the processor to adjust a size of kernels utilized in the kernel regression based on the comparison of the image to jagged edge configurations. 
     
     
         25 . An apparatus, comprising:
 a processor; and   memory to store instructions to direct the processor to:
 detect an edge in an image; 
 dilate the detected edge of the image to include portions of the image adjacent to the detected edge in a dilated image region; 
 selectively apply kernel regression to detecting edges in an image, including portions of the image that correspond to a jagged edge configuration; 
 selectively apply kernel regression to portions of the image that correspond to the jagged edge configuration; and 
 output a corrected image. 
   
     
     
         26 . The apparatus of  claim 25 , wherein the memory further includes instructions to direct the processor to dilate the edges by more than one pixel in at least one direction around the detected edges. 
     
     
         27 . The apparatus of  claim 25 , wherein the memory further includes instructions to direct the processor to detect the edge in the image with Canny edge detection. 
     
     
         28 . The apparatus of  claim 25 , wherein the memory further includes instructions to direct the processor to apply kernel regression to the detected edge and not apply kernel regression to other portions of the image. 
     
     
         29 . An apparatus, comprising:
 a processor; and   memory to store instructions to direct the processor to:
 detect an edge in an image and compare the image to plural jagged edge configurations; 
 selectively apply kernel regression to portions of the image based, at least in part, on the detection of the edge in the image corresponding to the jagged edge configurations; and 
 output a corrected image. 
   
     
     
         30 . The apparatus of  claim 29 , wherein the memory further includes instructions to direct the processor to apply kernel regression to the portions of the image that correspond the jagged edge configurations. 
     
     
         31 . The apparatus of  claim 29 , wherein the memory further includes instructions to direct the processor to determine a score of a degree of match to each of the plural jagged edge configurations. 
     
     
         32 . The apparatus of  claim 31 , wherein the memory further includes instructions to direct the processor to determine a composite score for jaggedness in the image, including to select a maximum score out of the scores of the degree of match to the plural jagged edge configurations. 
     
     
         33 . The apparatus of  claim 31 , wherein the memory further includes instructions to direct the processor to determine a composite score for jaggedness in the image by aggregating the scores of the degree of match to the plural jagged edge configurations. 
     
     
         34 . The apparatus of  claim 29 , wherein the memory further includes instructions to direct the processor to adjust a size of kernels utilized in the kernel regression based on the comparison of the image to jagged edge configurations.