Image capture systems

• US 6,904,183 B2
• Filed: 02/15/2001
• Issued: 06/07/2005
• Est. Priority Date: 03/03/2000
• Status: Expired due to Fees

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Slatter, David Neil
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): Dang, Duy M.
• Application Number:
  US09/784,503
• Publication Number:
  US 20010019636A1
• Time in Patent Office: 1,573 Days
• Field of Search: 382/318, 382/312, 382/313, 382/321, 382/284, 382/294, 358/450, 358/540
• US Class Current: 382/284
• CPC Class Codes: G06V 10/10 Image acquisition document image scanning and transmission H04N1/00; control of digital cameras H04N23/60
• CPC Class Codes: H04N 1/00326 with a data reading, recognizing or recording apparatus, e.g. with a bar-code apparatus arrangements for the associated working of recording or reproducing apparatus with related apparatus G11B31/00
• CPC Class Codes: H04N 1/00331 with an apparatus performing optical character recognition character recognition G06V30/10
• CPC Class Codes: H04N 1/195 the array comprising a two-dimensional array or a combination of two-dimensional arrays
• CPC Class Codes: H04N 1/19594 using a television camera or a still video camera
• CPC Class Codes: H04N 1/3876 Recombination of partial images to recreate the original image
• CPC Class Codes: H04N 2201/0414 Scanning an image in a series of overlapping zones
• CPC Class Codes: H04N 2201/0436 Scanning a picture-bearing surface lying face up on a support H04N2201/0434 takes precedence; using cylindrical picture bearing surfaces H04N1/06; with manual scanning H04N1/107

Abstract

An electronic image capture apparatus is disclosed comprising: an electronic camera having a detector, a lens having a field of view which is adapted to limit the radiation incident upon the detector to that within the field of view, an actuator for moving the field of view across the document, a control means for controlling the actuator to move the camera across the document so as to obtain a set of overlapping sub-images corresponding to different areas of the document, and electronic processing means adapted to receive the set of sub-images produced by the camera and to process the sub-images to form a composite image of the portion of the document covered by the set of sub-images. A set of processable sub-image files are produced which each comprise a data set of characters corresponding to characters appearing in a respective sub-image in the set and the relative location of the characters in that sub-image. The contents of each of the processable sub-image files are stitched into a blank text document by applying logical operators to the data in the files to produce a complete composite text document containing data indicative of the textual content of the scanned document.

Claims

1. An electronic image capture apparatus comprising:

an image detecting device adapted to capture a set of sub-images or tiles corresponding to different areas of a document at known locations and a processor adapted to receive the set of sub-images produced by the image detecting device an to process the sub-images to form a machine-readable text document equivalent to the portion of the document covered by the set of sub-images;

wherein;

the processor includes an optical character recognition sub-routine which is adapted to produce a first set of processable data files which each comprises a data set of characters corresponding to characters appearing in a respective sub-image in the set and relative location of the characters in that sub-image;

the processor establishes a co-ordinate system which defines a template of the machine readable document whereby any point in the imaged document can be uniquely identified by co-ordinate of that point in the machine readable text document;

the processor establishes a second co-ordinate system for each sub-image;

the processor, after optical character recognition, stores in the processable data files the characters located in each sub-image along with the location of characters in the second co-ordinate system; and

the processor is adapted to stitch together the characters stored in the data tiles to produce a machine readable text document.

2. An electronic image capture apparatus according to claim 1 wherein the image detecting device comprises an electronic camera having a detector, a lens having a field of view which is adapted to limit radiation incident upon the detector to that within a field of view, an actuator for moving the field of view of the camera relative to the document to be imaged, and a controller for controlling the actuator to move the field of view of the camera across the document so as to capture the set of sub-images or tiles.

3. An electronic imaging apparatus according to claim 1 wherein the data in the first set of processable data files is stitched together to produce the machine readable document by allocating characters in the data files onto corresponding locations in a spatial template of the machine readable document.

4. An electronic imaging apparatus according to claim 1 wherein the first and second co-ordinate systems are the same or are related through a transform whereby each character stored in a processable data file can be mapped onto the co-ordinate frame of the machine readable document.

5. An electronic imaging apparatus according to claim 1 wherein the sub-images overlap spatially at least by a width of the largest character which is expected in the document.

6. An electronic imaging apparatus according to claim 1 wherein where only one data file contains a character at a given location in the machine readable text document the processor is adapted to allocate that character to that location.

7. An electronic imaging apparatus according to claim 6 wherein if none of the processable data files contain a character for a location in the machine-readable text document then a space is entered in the text document at that location.

8. An electronic imaging apparatus according to claim 6 wherein the processor is adapted to determine reliability of the data in the processable data files.

9. An electronic imaging apparatus according to claim 8 wherein in the event that two or more data files contain different characters corresponding to the same location in the machine readable text file the processor is adapted to select which data to allocate based on the reliability of the data.

10. An electronic imaging apparatus according to claim 8 wherein the processor is adapted to determine the reliability of the data by applying one or more logical rules to the data in the processable data files.

11. An electronic imaging apparatus according to claim 10 wherein the logical rules include using the character which is located furthest away from the edge of a sub-image to construct the machine readable document if there is a conflict.

12. An electronic imaging apparatus according to claim 1 wherein the processor is adapted to identify lines of text within each processable data file from a spatial distribution of the characters identified within each sub-image.

13. An electronic imaging apparatus according to claim 1 wherein the data in the processable data files comprises ASCII characters.