Apparatus for preprocessing of character recognition

• US 4,809,344 A
• Filed: 05/11/1987
• Issued: 02/28/1989
• Est. Priority Date: 05/11/1987
• Status: Expired due to Fees

• Current Assignee: Nippon Sheet Glass Company Limited
• Original Assignee: Nippon Sheet Glass Company Limited
• Inventors: Young, James R., Peppers, Norman A., Pierce, Gerald A., Katsuki, Kazuo, Nishi, Hisami
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): Couso, Jose L.
• Application Number:
  US07/048,229
• Time in Patent Office: 659 Days
• Field of Search: 382/1, 382/9, 382/10, 382/16, 382/18, 382/27, 382/30-35, 382/41, 382/42, 382/48, 382/45, 382/51, 382/58, 382/61, 382/63, 382/65, 382/67, 382/68, 235/454, 235/436, 235/439, 235/440, 358/225, 358/226, 358/288
• US Class Current: 382/173
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/146 Aligning or centring of the image pick-up or image-field

Abstract

In an apparatus for preprocessing of character recognition so as to obtain data necessary for character recognition, page segmentation is performed by simultaneously extracting a plurality of features, separation between lines, separation between characters, and separation between the lines and the characters are simultaneously performed, and a calculation time for normalizing the separated individual characters can be reduced, thereby performing proprocessing required for character recognition systematically at high speed.

Claims

1. An apparatus for preprocessing of character recognition comprising:

dividing means for dividing an area within a page into a plurality of areas,

multiplying means for multiplying one of the plurality of areas into a plurality of images,

feature extracting means for extracting features of said one of the plurality of means by optically detecting the presence or absence of a correlation between each of pairs of the plurality of images and a plurality of different masks,

a plurality of photosensor arrays each of which has a plurality of aligned light-receiving elements having different alignment directions and being respectively paired with the plurality of images,

first and second image sensors for reading lines and characters within the page in a predetermined scanning direction;

moving means for moving relatively the characters and said first and second image sensors in a direction different from the scanning direction;

calculating means for calculating a size of the characters along a moving direction on the basis of an output from said first image sensor; and

control means for controlling a scanning frequency of said second image sensor on the basis of the size of the characters calculated,

wherein each said one of the areas within the page is divided until each said one of the plurality of areas as directed has a single feature, and a beam from each said one of the plurality of areas with a single feature is incident on said plurality of photosensor arrays,

the lines and the characters in each said one of the plurality of areas as divided are separated on the basis of a density distribution represented by detection outputs form said light-receiving elements, and

each of the characters as separated is normalized by said second image sensor along the predetermined scanning direction.

2. An apparatus according to claim 1, wherein said multiplying means comprises a single convex lens having a relatively large aperture size and a plurality of convex lenses each having a relatively small aperture size, said plurality of convex lenses being aligned in a direction perpendicular to an optical axis of said single convex lens in an optical path of light passing through said single convex lens.

3. An apparatus according to claim 1, wherein said plurality of different masks include a mask for detecting a laterally written document and a mask for detecting a vertically written document.

4. An apparatus according to claim 3, wherein said plurality of different masks further include a mask having slits inclined at an arbitrary angle.

5. An apparatus according to claim 4, wherein said plurality of different masks further include a mask having a correlation with a given figure or a given table.

6. An apparatus according to claim 1, wherein said plurality of photosensor arrays include a photosensor array for detecting a laterally written document and a photosensor array for detecting a vertically written document.

7. An apparatus according to claim 6, wherein said plurality of photosensor arrays further include a photosensor array having said light-receiving elements aligned and inclined at an arbitrary angle.

8. An apparatus according to claim 1, wherein said moving means comprises a display for displaying the characters and shifting the characters in a direction perpendicular to the scanning direction.