Claims:WE CLAIM:
1. A method for determining one or more target objects in an image, the method comprising:
segmenting, by an object determination system, the image into one or more segments based on one or more first set of visual attributes;
performing, by the object determination system, one or more morphological operations on the one or more segments to obtain one or more morphed segments;
identifying, by the object determination system, one or more candidates of one or more target objects based on one or more second set of visual attributes corresponding to each of the one or more morphed segments; and
identifying, by the object determination system, at least one of, true positive and false positive from the one or more candidates indicative of presence or absence of the one or more target objects respectively, based on neighbourhood information associated with the one or more candidates.

2. The method as claimed in claim 1, wherein the method is capable of receiving a document and converting the document into the image before segmenting step, when the document received is not in an image format.

3. The method as claimed in claim 1, wherein the one or more first set of visual attributes enable identifying at least one of paragraphs, logos, tables, footers and headers in the received image.

4. The method as claimed in claim 1, wherein the one or more target objects comprise at least a vacant field for initials, signature, notary, seal or a field for one of initials, signature, notary and seal.

5. The method as claimed in claim 1, wherein the method determines the one or more target objects in the image comprising at least one of blurred regions and crowded regions and represented in different orientations.

6. The method as claimed in claim 1, wherein the one or more morphological operations comprises erosion, dilation and redaction.

7. The method as claimed in claim 1, wherein the neighbourhood information comprises at least one of text, images, margins, tables and numbers placed adjacent to the one or more candidates.

8. The method as claimed in claim 1 further comprising determining a location in a document corresponding to a pixel location of the one or more target objects in the image to create a placeholder for at least one of initials, signature, notary and seal.

9. An object determination system for determining one or more target objects in an image, comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to:
segment the image into one or more segments based on one or more first set of visual attributes;
perform one or more morphological operations on the one or more segments to obtain one or more morphed segments;
identify one or more candidates of one or more target objects based on one or more second set of visual attributes corresponding to each of the one or more morphed segments; and
identify at least one of, true positive and false positive from the one or more candidates indicative of presence or absence of the one or more target objects respectively, based on neighbourhood information associated with the one or more candidates.

10. The object determination system as claimed in claim 9, wherein the processor is configured to receive a document and convert the document into the image before segmenting step, when the document received is not in an image format.

11. The object determination system as claimed in claim 9, wherein the one or more first set of visual attributes enable identifying at least one of paragraphs, logos, tables, footers and header in the received image.

12. The object determination system as claimed in claim 9, wherein the one or more target objects comprises a vacant field for initials, signature, notary and seal or a field for one of initials, signature, notary and seal.

13. The object determination system as claimed in claim 9, wherein the processor determines the one or more target objects in the image comprising at least one of blurred regions and crowded regions and represented in different orientations.

14. The object determination system as claimed in claim 9, wherein the one or more morphological operations comprises erosion, dilation and redaction.

15. The object determination system as claimed in claim 9, wherein the neighbourhood information comprises at least one of text, images, margins, tables, and numbers placed adjacent to the one or more candidates.

16. The object determination system as claimed in claim 9, wherein the processor determines a location in a document corresponding to a pixel location of the one or more target objects in the image to create a placeholder for at least one of initials, signature, seal and notary.

17. A non-transitory computer readable medium including instruction stored thereon that when processed by at least one processor cause an object determination system to perform operation comprising:
segmenting an image into one or more segments based on one or more first set of visual attributes;
performing one or more morphological operations on the one or more segments to obtain one or more morphed segment;
identifying one or more candidates of one or more target objects based on one or more second set of visual attributes corresponding to each of the one or more morphed segments; and

identifying at least one of, true positive and false positive from the one or more candidates indicative of presence or absence of the one or more target objects respectively, based on neighbourhood information associated with the one or more candidates.
Dated this 2nd day of April, 2019

Madhusudan S.T
Of K&S Partners
Agent for the Applicant
IN/PA-1297
, Description:TECHNICAL FIELD
[001] The present subject matter is related in general to computer vision and image processing, more particularly, but not exclusively to a method and system for determining one or more target objects in an image.