Method and apparatus for locating and identifying fields within a document

• US 5,852,676 A
• Filed: 04/11/1995
• Issued: 12/22/1998
• Est. Priority Date: 04/11/1995
• Status: Expired due to Term

• Current Assignee: Docustream Incorporated
• Original Assignee: Teraform, Inc.
• Inventors: Lazar, Theodore G.
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): Mariam, Daniel G.
• Application Number:
  US08/419,663
• Time in Patent Office: 1,351 Days
• Field of Search: 382/175, 382/176, 382/138, 382/173, 382/174, 382/180
• US Class Current: 382/173
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A document to be processed is scanned into a machine readable image. The image is segmented into a plurality of fields. Predetermined characteristics are measured for each field and the set of characteristics is correlated with a predetermined set of characteristics derived from a reference image. The fields with the highest degree of correlation to the characteristics from the reference document are selected for further processing, e.g., optical character recognition.

Claims

1. A method of locating a specific subject image field in a subject image partitioned into a plurality of subject image fields, the method comprising the computer implemented steps of:

a) determining at least one characteristic value for each of the subject image fields, wherein the characteristic value is determined by one or more characteristics selected from the group consisting of the X-coordinate of the leftmost point of the subject image field, the Y-coordinate of the uppermost pixel of the subject image field, the width of the field, the height of the subject image field, the number of pixels in the subject image field, the number of characters in the subject image field, the number of horizontal lines above the subject image field, the number of horizontal lines below the subject image field, the number of vertical lines to the left of the subject image field, the number of vertical lines to the right of the subject image field, the distance from another field having a particular string of characters, the height, width and number of pixels for each character in the subject image field, and the ASCII value of each character in the subject image field;

b) determining a correlation value for each of the characteristic values by comparing each characteristic value to at least one predetermined criterion;

c) combining the correlation values to yield a composite correlation value for each of the subject image fields; and

d) locating the specific subject image field by determining the subject image field with the highest composite correlation value.

2. The method of claim 1 wherein the step of determining the composite correlation value includes applying a weighting factor to at least one of the correlation values.

3. The method of claim 1 further comprising the step of providing the specific subject image field to an optical character recognition system.

8. The method of claim 1 wherein the predetermined criterion is further comprised of degree of membership functions.

4. An apparatus for locating a specific subject image field in a subject image partitioned into a plurality of subject image fields, the apparatus comprising:

a) means for determining at least one characteristic value for each of the subject image fields, wherein the characteristic value is determined by one or more characteristics selected from the group consisting of the X-coordinate of the leftmost point of the subject image field, the Y-coordinate of the uppermost pixel of the subject image field, the width of the field, the height of the subject image field, the number of pixels in the subject image field, the number of characters in the subject image field, the number of horizontal lines above the subject image field, the number of horizontal lines below the subject image field, the number of vertical lines to the left of the subject image field, the number of vertical lines to the right of the subject image field, the distance from another field having a particular string of characters, the height, width and number of pixels for each character in the subject image field, and the ASCII value of each character in the subject image field;

b) means for determining a correlation value for each of the characteristic values by comparing each characteristic value to at least one predetermined criterion;

c) means for combining the correlation values to yield a composite correlation value for each of the subject image fields; and

d) means for determining the subject image field with the highest composite correlation value.

5. The apparatus of claim 4, the apparatus further comprising means for applying a weighting factor to at least one of the correlation values.

6. The apparatus of claim 4, the apparatus further comprising means for providing the specific subject image field to an optical character recognition system.

9. The apparatus of claim 4 wherein the predetermined criterion includes one or more degree of membership functions.

7. A computer-readable medium having stored thereon a plurality of sequences of instructions including instructions which, when executed by a processor, cause said processor to perform the steps of:

a) partitioning the subject image into a plurality of subject image fields;

b) determining at least one characteristic value for each of the subject image fields, wherein the characteristic value is determined by one or more characteristics selected from the group consisting of the X-coordinate of the leftmost point of the subject image field, the Y-coordinate of the uppermost pixel of the subject image field, the width of the field, the height of the subject image field, the number of pixels in the subject image field, the number of characters in the subject image field, the number of horizontal lines above the subject image field, the number of horizontal lines below the subject image field, the number of vertical lines to the left of the subject image field, the number of vertical lines to the right of the subject image field, the distance from another field having a particular string of characters, the height, width and number of pixels for each character in the subject image field, and the ASCII value of each character in the subject image field;

c) determining a correlation value for each of the characteristic values by comparing each characteristic value to at least one predetermined criterion;

d) combining the correlation values to yield a composite correlation value for each of the subject image fields; and

e) selecting the subject image field with the highest composite correlation value.

10. An apparatus for locating a specific subject image field in a subject image, the apparats comprising:

a) an image processing device configured to partition the subject image into a plurality of subject image fields;

b) a processor;

c) a first software control configured to direct the processor to determine at least one characteristic value for each subject image field, wherein the characteristic value is determined by one or more characteristics selected from the group consisting of the X-coordinate of the leftmost point of the subject image field, the Y-coordinate of the uppermost pixel of the subject image field, the width of the field the height of the subject image field, the number of pixels in the subject image field, the number of characters in the subject image field, the number of horizontal lines above the subject image field, the number of horizontal lines below the subject image field, the number of vertical lines to the left of the subject image field, the number of vertical lines to the right of the subject image field, the distance from another field having a particular string of characters, the height, width and number of pixels for each character in the subject image field, and the ASCII value of each character in the subject image field;

d) a second software control configured to direct the processor to determine correlation values for each of the characteristic values by comparing each characteristic value to at least one predetermined criterion;

e) a third software control configured to direct the processor to combine the correlation values to yield a composite correlation value for each of the subject image fields; and

f) a fourth software control configured to direct the processor to determine the subject image field having the highest composite correlation value.

11. The apparatus of claim 10 wherein the predetermined criterion is further comprised of degree of membership functions.

12. An apparatus for locating a specific subject image field on a printed subject document, the apparatus comprising:

a) an image processing device configured to convert the printed subject document into a subject image;

b) a partitioning module configured to partition the subject image into a plurality of subject image fields;

c) a characteristic value module configured to determine at least one characteristic value for each subject image field, wherein the characteristic value is determined by one or more characteristics selected from the group consisting of the X-coordinate of the leftmost point of the subject image field, the Y-coordinate of the uppermost pixel of the subject image field, the width of the field, the height of the subject image field, the number of pixels in the subject image field, the number of characters in the subject image field, the number of horizontal lines above the subject image field, the number of horizontal lines below the subject image field, the number of vertical lines to the left of the subject image field, the number of vertical lines to the right of the subject image field, the distance from another field having a particular string of characters, the height, width and number of pixels for each character in the subject image field, and the ASCII value of each character in the subject image field;

d) a correlation value module configured to determine a correlation value for each of the characteristic values by comparing each characteristic value to at least one predetermined criterion;

e) a combination module configured to combine the correlation values for each of the subject image fields; and

f) a selecting module configured to select the subject image field with the highest composite correlation value.

13. The apparatus of claim 12 wherein the predetermined criterion is further comprised of degree of membership functions.