Screen display methods for computer-aided data entry

• US 5,923,792 A
• Filed: 02/07/1996
• Issued: 07/13/1999
• Est. Priority Date: 02/07/1996
• Status: Expired due to Fees

• Current Assignee: Transpacific IP Group Limited
• Original Assignee: Industrial Technology Research Institute
• Inventors: Lin, Wen-Wen, Lien, Yao-Nan, Shyu, Ing-Shyh, Chen, Mou-Yen, Tu, Lo-Ting, Huang, Yea-Shuan
• Primary Examiner(s): Couso, Jose L.
• Application Number:
  US08/598,080
• Time in Patent Office: 1,252 Days
• Field of Search: 382/309, 382/310, 382/311
• US Class Current: 382/309
• CPC Class Codes: G06V 10/987 with the intervention of an operator

Abstract

An optical character recognition screen editing process is performed efficiently and only when necessary. The process is ordered so that editing is performed in increasing order of work intensity. That is, less "expensive" (i.e., less time consuming) correction methods are performed first, as a filter for more "expensive" correction methods. In the preferred embodiment, individual character are corrected first, information fields are corrected second, and entire forms are correction last. Preferably, the individual characters may be collected from a number of forms before being displayed for correction.

Claims

1. A method for manually editing a plurality of optically scanned documents, comprising the steps of:

a. determining if characters on the optically scanned documents are not recognized;

b. accumulating a plurality of unrecognized characters from the documents;

c. displaying together the accumulated unrecognized characters;

d. manually editing the unrecognized characters;

e. performing a first integrity check on;

(1) documents having manually edited characters; and

(2) documents not having unrecognized characters;

f. performing a field edit on fields from the documents failing the first integrity check;

g. performing a second integrity check on the field edited fields; and

h. saving the field edited information if it passes the second integrity check.

2. The method of claim 1, wherein the step of determining if characters on the optically scanned document are not recognized further comprises:

a. classifying an optically scanned document as one of;

(1) completely recognized;

(2) manual editing required; and

(3) rejected;

b. saving the document if it is classified as completely recognized;

c. performing an edit on the entire document if it is classified as rejected; and

d. performing claim 1, steps b-h on the document if it is classified as manual editing required.

3. The method of claim 1, wherein the step of accumulating a plurality of unrecognized characters comprises saving in an intermediate file the unrecognized characters and information identifying the location of the unrecognized character.

4. The method of claim 1, wherein the step of manually editing the unrecognized characters further includes the steps of:

a. displaying on a first portion of a monitor the accumulated unrecognized characters; and

b. providing on a second portion of the monitor an area for displaying input corrected characters.

5. The method of claim 4, further comprising displaying on a third portion of the screen information about the displayed characters.

6. The method of claim 4, wherein before the step of displaying, selecting one of either only numerals and only letters for display.

7. The method of claim 4, wherein before the step of displaying, selecting a character editing screen display set up.

8. The method of claim 7, wherein the step of selecting a character editing screen display setup further comprises the steps of:

a. accumulating a number of unrecognized characters;

b. selecting whether the unrecognized characters are to be displayed at a uniform size;

c. if the unrecognized characters are not selected to be displayed at a uniform size, arranging the accumulated characters in size order;

d. if the unrecognized characters are selected to be displayed at a uniform size;

(1) normalizing the unrecognized character;

(2) determining an image density of the normalized unrecognized characters; and

(3) arranging the normalized characters in order of image density;

e. aligning the unrecognized characters.

9. The method of claim 8, wherein the step of aligning further comprises the steps of:

a. calculating a center alignment for each character to be displayed; and

b. determining the alignment line for each character to be displayed.

10. The method of claim 1, wherein the step of performing an integrity check further comprises comparing a field entry with predetermined information to cross-check accuracy of the entry.

11. The method of claim 1, wherein the step of performing the integrity check further comprises checking a value range of a field entry to determine if it satisfies a predetermined relationship.

12. The method of claim 1, wherein the step of field editing further comprises the steps of:

a. displaying on a first portion of a monitor a rejected field; and

b. providing on a second portion of the monitor an area for displaying an input corrected character string.

13. The method of claim 12, further comprising displaying on a third portion of the screen information about the rejected field.

14. The method of claim 12, further comprising displaying on a fourth portion of a monitor the rejected field and fields elated to the rejected field.

15. The method of claim 14, further comprising indicating characters in the rejected field and related fields that are likely to be erroneous.

16. The method of claim 1, wherein if the field fails the second integrity check, the step of field editing further comprises the steps of:

a. determining if the field is either one of an independent field and a related field;

b. if the field is an independent field, highlighting a name of the rejected field;

c. if the field is related, displaying the rejected field and fields related to it.

17. A method for displaying a number of unrecognized optically scanned images, comprising the steps of:

a. accumulating a number of unrecognized characters from a plurality of documents;

b. selecting if the accumulated unrecognized characters are to be displayed at a uniform size;

c. if the accumulated unrecognized characters are not selected to be displayed at a uniform size, arranging the accumulated characters in size order;

d. if the accumulated unrecognized characters are selected to be displayed at a uniform size;

(1) normalizing the unrecognized characters;

(2) determining an image density of the accumulated unrecognized characters;

(3) arranging the characters in order of image density;

e. aligning the accumulated unrecognized characters; and

f. displaying the aligned accumulated unrecognized characters.

18. The method of claim 17, wherein the step of aligning further comprises the steps of:

a. calculating a center alignment for each character to be displayed; and

b. determining the alignment line for each character to be displayed.

19. The method of claim 17, further comprising the steps of after aligning the unrecognized characters:

a. displaying on a first portion of a monitor the accumulated unrecognized characters; and

b. providing on a second portion of the monitor an area for displaying input corrected characters.

20. The method of claim 19, further comprising displaying on a third portion of the screen information about the displayed characters.

21. The method of claim 17, wherein before the step of accumulating, selecting one of only numerals and only letters for display.