Method for identifying marked content

Abstract

Briefly, in accordance with one embodiment, a method of identifying marked content is described.

1 - 6 . (canceled) 
     
     
         7 . A method of classifying content of at least one image comprising:
 applying a trained analysis of variance process to said at least one image, wherein the trained analysis of variance process is trained based on forming multiple prediction error sets from neighboring samples of a set of known images;   classifying the content of said at least one image based at least in part on the value obtained from application of the trained analysis of variance process.   
     
     
         8 . The method of  claim 7 , wherein said trained analysis of variance process comprises a trained support vector machine (SVM) process. 
     
     
         9 . (canceled) 
     
     
         10 . The method of  claim 8 , wherein said trained analysis of variance process is based at least in part on thresholded prediction error images. 
     
     
         11 - 21 . (canceled) 
     
     
         22 . A non-transitory computer-readable medium having computing device executable instructions stored thereon, the instructions comprising instructions for:
 applying a trained analysis of variance process to at least one image, wherein the trained analysis of variance process being trained based on forming multiple prediction error sets from neighboring samples of a set of known images; and   classifying the content of said at least one image based at least in part on the value obtained from application of the trained analysis of variance process.   
     
     
         23 . The medium of  claim 22 , wherein said instructions for applying said trained analysis of variance process comprise instructions for applying a trained support vector machine (SVM) process. 
     
     
         24 . (canceled) 
     
     
         25 . The medium of  claim 23 , wherein said instructions for applying said trained analysis of variance process are based at least in part on thresholded prediction error images. 
     
     
         26 - 29 . (canceled) 
     
     
         30 . An apparatus comprising:
 means for applying a trained analysis of variance process to at least one image, wherein said trained analysis of variance process is trained based on forming multiple prediction error sets from neighboring samples of a set of known images; and   means for classifying the content of said at least one image based at least in part on the value obtained from application of the trained analysis of variance process.   
     
     
         31 . The apparatus of  claim 30 , wherein said means for applying trained analysis of variance process comprises means for applying a trained SVM process. 
     
     
         32 . (canceled) 
     
     
         33 . The apparatus of  claim 31 , wherein said means for applying a trained SVM process is based at least in part on thresholded prediction error images. 
     
     
         34 . The method of  claim 7 , wherein the applying a trained analysis of variance process to said at least one image comprises deriving prediction error sets based on sets of neighboring samples of the said at least one image. 
     
     
         35 . The medium of  claim 22 , wherein the instructions for applying a trained analysis of variance process to said at least one image comprises instructions for deriving prediction error sets based on sets of neighboring samples of the said at least one image. 
     
     
         36 . The apparatus of  claim 30 , wherein the means for applying the trained analysis of variance process to said at least one image comprises means for deriving prediction error sets based on sets of neighboring samples of the said at least one image.