Computer vision-based methods for enhanced jbig2 and generic bitonal compression

Abstract

A system and method of symbol matching may include a processor configured to determine which pixels of a first symbol are tangent pixels; for each of the determined tangent pixels, determine whether a second symbol includes a pixel corresponding to the tangent pixel that includes at least one same tangent constraint as that of the tangent pixel; accept the first and second symbols as a match based on shared tangent constraints conditional upon a determination that the second symbol includes for each of at least a subset of the tangent pixels of the first symbol a corresponding pixel that includes the at least one same tangent constraint as that of the tangent pixel; and generate a document including a single symbol that is mapped to the first and second symbols.

1 . A symbol matching method, comprising:
 determining which pixels of a first symbol are tangent pixels;   for each of the determined tangent pixels, determining whether a second symbol includes a pixel corresponding to the tangent pixel that includes at least one same tangent constraint as that of the tangent pixel;   accepting the first and second symbols as a match based on shared tangent constraints conditional upon a determination that the second symbol includes for each of at least a subset of the tangent pixels of the first symbol a corresponding pixel that includes the at least one same tangent constraint as that of the tangent pixel; and   generating a document including a single symbol that is mapped to the first and second symbols.   
     
     
         2 . The symbol matching method of  claim 1 , wherein the accepting of the match is conditional upon that, for each of the at least a subset of the tangent pixels of the first symbol, a corresponding pixel of the second symbol is determined to include all tangent constraints of the tangent pixel. 
     
     
         3 . The symbol matching method of  claim 1 , wherein the accepting of the match is responsive to a determination that the second symbol includes for each of the at least a subset of the tangent pixels of the first symbol a corresponding pixel that includes one or more same tangent constraints. 
     
     
         4 . The symbol matching method of  claim 1 , wherein the subset includes only tangent pixels neighbored by another tangent pixel that has at least one same tangent constraint as that of the tangent pixel. 
     
     
         5 . The symbol matching method of  claim 1 , wherein pixels of the first and second symbols correspond if they are not offset from each other by more than one with respect to their respective bitmaps. 
     
     
         6 . The symbol matching method of  claim 5 , wherein the acceptance of the first and second symbols as a match based on shared tangent constraints is condition upon that, for each of the at least the subset of the tangent pixels, the corresponding pixel that includes the at least one same tangent constraint as that of the tangent pixel is not offset from the tangent pixel in a direction that does not parallel a tangent direction of the tangent pixel. 
     
     
         7 . The symbol matching method of  claim 1 , wherein a number of shared constraints required for acceptance of the first and second symbols as a match based on the shared constraints depends on a height, width, and a mean stroke thickness. 
     
     
         8 . The symbol matching method of  claim 1 , further comprising:
 for each of the at least a subset of the tangent pixels:
 analyzing eight pixel neighbors of the tangent pixel; and 
 determining, base on the analysis of the eight pixel neighbors, a number of the at least one same tangent constraint required for use of the constraint similarity between the tangent pixel and its corresponding pixel as a basis for accepting the first and second symbols as a match. 
   
     
     
         9 . The symbol matching method of  claim 1 , further comprising:
 for each of the at least a subset of the tangent pixels:
 determining whether the first symbol includes another pixel that is symmetric to the tangent pixel with respect to an axis; and 
 determining, based on the determination regarding the inclusion of the symmetric pixel, a number of the at least one same tangent constraint required for use of the constraint similarity between the tangent pixel and its corresponding pixel as a basis for accepting the first and second symbols as a match. 
   
     
     
         10 . The symbol matching method of  claim 1 , wherein the symbol matching method is used for data compression.