Systems and methods for handwritten digital pen lexical inference

• US 7,489,819 B2
• Filed: 05/11/2007
• Issued: 02/10/2009
• Est. Priority Date: 05/12/2006
• Status: Expired due to Fees

• Current Assignee: Velosum, Inc.
• Original Assignee: Velosum, Inc.
• Inventors: Sheets, Rodney L.
• Primary Examiner(s): Bella; Matthew C.
• Assistant Examiner(s): LIEW, ALEX KOK SOON
• Application Number:
  US11/747,418
• Publication Number:
  US 20070263931A1
• Time in Patent Office: 641 Days
• Field of Search: None
• US Class Current: 382/186
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06V 10/945 User interactive design; Environments; Toolboxes
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1426 by sensing position defining codes on a support
• CPC Class Codes: G06V 30/1448 based on markings or identifiers characterising the document or the area
• CPC Class Codes: G06V 30/2272 with lexical matching
• CPC Class Codes: G06V 30/387 using human interaction, e.g. selection of the best displayed recognition candidate

Abstract

Systems and methods are provided for recognizing handwritten characters drawn on a paper form using a digital pen that records stroke coordinates corresponding to respective pen strokes. In one embodiment, a field on the paper form is assigned a lexical inference level. For example, the field may be assigned a word level, a word prefix level, and/or a word stem level. The assigned lexical inference level is used to recognize one or more stroke coordinates corresponding to pen strokes written in the field. Recognized characters are then used to create or modify an inference lexicon used to perform handwriting recognition for the entire field. In one embodiment, the inference lexicon is used for handwriting recognition in the same field on subsequently processed forms.

Claims

1. A method for recognizing handwriting on a paper form using a digital pen, the method comprising:

accessing a stroke collection file comprising data corresponding to a set of pen strokes marked by a user on the paper form using the digital pen;

associating a field on the paper form with a predetermined lexical inference type;

determining a subset of pen strokes in the stroke collection file corresponding to the field, wherein determining comprises;

associating the field with an area on the paper form corresponding to a first set of coordinates;

accessing a second set of coordinates corresponding to a particular stroke from the stroke collection file; and

comparing the second set of coordinates to the first set of coordinates to determine whether the particular stroke was written within the area associated with the field;

based on the lexical inference type, dynamically updating an inference lexicon associated with the field; and

performing handwriting recognition on the subset of pen strokes based on the dynamically updated inference lexicon.

2. The method of claim 1, further comprising selecting the predetermined lexical inference type from a group comprising a word level, a word prefix level, a word suffix level, a word stem level, a punctuation model, and a grammar model.

3. The method of claim 1, further comprising associating the predetermined lexical inference type with a list of lexical inferences expected to be written in the field by the user.

4. The method of claim 1, wherein the lexical inference type comprises a word level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the pen strokes in the subset as a word in a predetermined word list; and

based on a frequency of the recognized word, selectively adding the recognized word to the inference lexicon associated with the field.

5. The method of claim 1, wherein the lexical inference type comprises a word prefix level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the strokes in the subset as a word prefix in a predetermined prefix list; and

based on the recognized word prefix, modifying valid lexical entries in the inference lexicon.

6. The method of claim 1, wherein the lexical inference type comprises a word stem level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the strokes in the subset as a word stem in a predetermined stem list; and

based on the recognized word stem, modifying valid lexical entries in the inference lexicon.

7. A system for recognizing handwriting, the system comprising:

a digital pen configured to write pen strokes on a paper form and to store corresponding stroke coordinates associated with respective pen stroke locations on the paper form; and

a processor configured to;

associate a field on the paper form with a predetermined lexical inference type;

determine that the stroke coordinates correspond to the field by;

associating the field with an area on the paper form corresponding to a predetermined set of coordinates; and

comparing the stroke coordinates to the predetermined coordinates to determine whether the pen strokes were written within the area associated with the field;

based on the lexical inference type, dynamically update an inference lexicon associated with the field; and

perform handwriting recognition on the pen strokes based on the dynamically updated inference lexicon.

8. The system of claim 7, further comprising a wireless communication device configured to receive the stroke coordinates from the digital pen and to provide the stroke coordinates to the processor.

9. The system of claim 7, wherein the processor comprises a web-based server.

10. The system of claim 7, wherein the processor is further configured to select the predetermined lexical inference type from a group comprising a word level, a word prefix level, a word suffix level, a word stem level, a punctuation model, and a grammar model.

11. The system of claim 7, wherein the processor is further configured to associate the predetermined lexical inference type with a list of lexical inferences expected to be written in the field by the user.

12. The system of claim 7, wherein the lexical inference type comprises a word level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the pen strokes as a word in a predetermined word list; and

based on a frequency of the recognized word, selectively adding the recognized word to the inference lexicon associated with the field.

13. The system of claim 7, wherein the lexical inference type comprises a word prefix level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the pen strokes as a word prefix in a predetermined prefix list; and

based on the recognized word prefix, modifying valid lexical entries in the inference lexicon.

14. The system of claim 7, wherein the lexical inference type comprises a word stem level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the pen strokes as a word stem in a predetermined stem list; and

based on the recognized word stem, modifying valid lexical entries in the inference lexicon.

15. A computer readable medium storing computer executable instructions for performing a method for recognizing handwriting on a paper form using a digital pen, the method comprising:

accessing a stroke collection file comprising data corresponding to a set of pen strokes marked by a user on the paper form using the digital pen;

associating a field on the paper form with a predetermined lexical inference type;

determining a subset of pen strokes in the stroke collection file corresponding to the field, wherein determining comprises;

associating the field with an area on the paper form corresponding to a first set of coordinates;

accessing a second set of coordinates corresponding to a particular stroke from the stroke collection file; and

comparing the second set of coordinates to the first set of coordinates to determine whether the particular stroke was written within the area associated with the field;

based on the lexical inference type, dynamically updating an inference lexicon associated with the field; and

performing handwriting recognition on the subset of pen strokes based on the dynamically updated inference lexicon.

16. The computer readable medium of claim 15, wherein the method further comprises selecting the predetermined lexical inference type from a group comprising a word level, a word prefix level, a word suffix level, a word stem level, a punctuation model, and a grammar model.

17. The computer readable medium of claim 15, wherein the method further comprises associating the predetermined lexical inference type with a list of lexical inferences expected to be written in the field by the user.

18. The computer readable medium of claim 15, wherein the lexical inference type comprises a word level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the pen strokes in the subset as a word in a predetermined word list; and

based on a frequency of the recognized word, selectively adding the recognized word to the inference lexicon associated with the field.

19. The computer readable medium of claim 15, wherein the lexical inference type comprises a word prefix level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the strokes in the subset as a word prefix in a predetermined prefix list; and

based on the recognized word prefix, modifying valid lexical entries in the inference lexicon.

20. The computer readable medium of claim 15, wherein the lexical inference type comprises a word stem level, and wherein dynamically updating the inference lexicon associated with the field comprises:

recognizing one or more of the strokes in the subset as a word stem in a predetermined stem list; and

based on the recognized word stem, modifying valid lexical entries in the inference lexicon.