Mark detection system and method

• US 10,579,896 B2
• Filed: 01/12/2018
• Issued: 03/03/2020
• Est. Priority Date: 11/28/2017
• Status: Active Grant

• Current Assignee: Newgen Software Technologies Limited
• Original Assignee: Newgen Software Technologies Limited
• Inventors: Abhishek, Jindal, Puja, Lal
• Primary Examiner(s): Varndell, Ross
• Application Number:
  US15/869,142
• Publication Number:
  US 20190164003A1
• Time in Patent Office: 781 Days
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/162 Quantising the image signal
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables

Abstract

A mark detection system and method is provided. The system includes a memory having computer-readable instructions stored therein. The system further includes an image processor configured to execute the computer-readable instructions to access an image of a document and process the image to generate a binarized image. The image processor is further configured to extract components of the binarized image using a connected-component labelling algorithm. Furthermore, the image processor is configured to analyze features of the extracted components to detect one or more marks in the document.

Claims

1. A mark detection system, the system comprising:

a memory having computer-readable instructions stored therein; and

an image processor configured to execute the computer-readable instructions to;

access an image of a document;

process the image to generate a binarized image,

extract components of the binarized image;

analyze features of the extracted components to detect one or more marks in the document;

detect a portion of a component connected to the one or more detected marks;

remove the portion of a component connected to the detected one or more marks based upon a value of a preservation variable;

detect at least portion of a component overlapping with the one or more detected marks; and

selectively remove portions of the one or more detected marks based upon a value of a preferences variable, wherein the values of each of the preservation and the preferences variable are selected by a user of the system.

2. The mark detection system of claim 1, wherein the image processor is further configured to execute the computer-readable instructions to selectively remove one or more marks based upon the features of the extracted components.

3. The mark detection system of claim 1, wherein the marks comprise tick marks, cross marks, or combinations thereof.

4. The mark detection system of claim 1, further comprising a digital imager configured to acquire a digital image of the document as the image of the document.

5. The mark detection system of claim 1, wherein the image processor is further configured to extract the components of the binarized image using a connected-component labelling algorithm.

6. The mark detection system of claim 5, wherein the image processor is further configured to execute the computer-readable instructions to:

remove noise components in the binarized image using the connected-component algorithm;

remove one or more horizontal and/or vertical lines present in the image; and

detect a skew angle of the image.

7. The mark detection system of claim 1, wherein the image processor is further configured to execute the computer-readable instructions to extract the components of the binarized image using an eight-neighbor connected-component labelling algorithm.

8. The mark detection system of claim 1, wherein the features of the extracted components comprise length, stroke width, angle with respect to a pre-determined axis, trend of pixel transitions, or combinations thereof.

9. The mark detection system of claim 8, wherein the image processor is further configured to execute the computer-readable instructions to adjust the one or more features of the extracted components based on the detected skew angle.

10. A method for removing marks in a document, the method comprising:

accessing an image of the document;

processing the image to generate a binarized image of the document;

extracting components of the binarized image using a connected-component labelling algorithm;

analyzing features of the extracted components to detect one or more marks in the document; and

selectively removing the detected one or more marks in the document;

detecting a portion of a component connected to the one or more detected marks;

removing the portion of a component connected to the detected one or more marks based upon a value of a preservation variable;

detecting at least portion of a component overlapping with the one or more detected marks; and

selectively remove portions of the one or more detected marks based upon a value of a preferences variable, wherein the values of each of the preservation and the preferences variable are selected by a user of the system.

11. The method of claim 10, further comprising removing noise components from the binarized image using the connected-component labelling algorithm.

12. The method of claim 10, wherein selectively removing the one or more marks comprises removing one or more of tick marks, cross marks, or combinations thereof.

13. The method of claim 10, wherein selectively removing the detected one or more marks comprising:

accessing values of a preservation variable and a preferences variable;

detecting portions of components connected to or overlapping with the detected one or more marks; and

removing portions of the one or more marks based upon the values of the preservation and the preferences variables.

14. A mark detection system, the system comprising:

a memory having computer-readable instructions stored therein; and

an image processor configured to execute the computer-readable instructions to;

access an image of a document;

process the image to generate a binarized image,

extract components of the binarized image using a connected-component labelling algorithm;

analyze features of the extracted components to detect one or more marks in the document;

remove portions of the one or more detected marks from the document;

detect a portion of a component connected to the one or more detected marks;

remove the portion of a component connected to the detected one or more marks based upon a value of a preservation variable;

detect at least portion of a component overlapping with the one or more detected marks; and

selectively remove portions of the one or more detected marks based upon a value of a preferences variable, wherein the values of each of the preservation and the preferences variable are selected by a user of the system.

15. The mark detection system of claim 14, further comprising a digital imager configured to acquire a digital image of the document as the image of the document.

16. The mark detection system of claim 14, wherein the image processor is configured to execute the computer-readable instructions to remove portions of the one or more detected marks based upon the values of preservation and the preferences variables.

17. The mark detection system of claim 14, wherein the image processor is configured to execute the computer-readable instructions to extract one or more line items from the document.