CLIAMS:We Claim:

1. A method of reducing functional ambiguity from an image, the method comprising:
identifying, by a processor of a functional ambiguity determination system, at least one object in the image based on object data received from an object repository, wherein each of the at least one object is annotated with description data;
determining, by the processor, a relative spatial proximity score for each of the at least one object based on a proximity distance among the at least one identified object;
determining, by the processor, a functional proximity score for each of the at least one object based on one or more functionalities, associated with the at least one object, extracted from the object repository;
identifying, by the processor, one or more domains, from a knowledge repository, associated with each of the one or more functionalities;
computing a domain score for each of the one or more domains based on the relative spatial proximity score, the functional proximity score and one or more user profiles of the users obtained from the knowledge repository; and
reducing, by the processor, the functional ambiguity from the image by associating a domain and at least one functionality associated with the at least one object based on the domain score.

2. The method as claimed in claim 1, wherein the computing the domain score further comprising:
providing the domain score associated with the one or more domains to the user for the user selection; and
receiving an input from the user indicating one of a new domain or a selected domain associated with the at least one object in the image.

3. The method as claimed in claim 2, further comprising:
updating a user selection of the one or more domains in the knowledge repository based on the input received from the user.

4. The method as claimed in claim 1, wherein determining the relative spatial proximity score for each of the at least one object further comprises:
obtaining a spatial score for each of the at least one object using Self-Organizing Maps (SOM);
determining a predefined number of object from amongst the at least one object based on the spatial score;
providing terms corresponding to the predefined number of objects to a Bidirectional Recurrent Neural Network (BRNN) to compute a term representation; and
determining the relative spatial proximity score for each of the at least one object based on the term representation.

5. The method as claimed in claim 1, wherein determining the functional proximity score further comprises:
identifying at least one nearest neighbouring functionality of the one or more functionalities based on a markov random walk model;
computing the functional proximity score for each of the one or more functionalities based on the a functional distance between a functionality and the nearest neighbouring functionality from amongst the one or more functionalities; and
mapping the functional proximity score to corresponding spatial proximal objects identified based on the relative spatial proximity score.

6. The method as claimed in claim 1, wherein computing the domain score for each of the one or more domains further comprises:
computing the domain score based on the functional proximity score associated with at least one functionalities;
obtaining a matrix of the at least one object, the one or more functionalities and the one or more domains; and
computing an ambiguity factor by applying at least one of a cocycle base algorithm and a maxmaxflow algorithm to the matrix based on one or more user profiles obtained from knowledge repository.

7. The method as claimed in claim 1 further comprising:
generating a text summary of the domain and the at least one functionality associated with the at least one object along with the user profile; and
converting the text summary into corresponding audio format to generate an audio summary.

8. A functional ambiguity determination system for reducing functional ambiguity from an image, comprising:
a processor;
an object repository coupled with the processor, and configured to store at least one object data and annotated description data for at least one object;
a knowledge repository coupled with the object repository and the processor, and configured to store one or more functionalities associated with at least one object, one or more domains associated with the one or more functionalities, and one or more user profiles associated with one or more users; and
a memory disposed in communication with the processor and storing processor-executable instructions, the instructions comprising instructions to:
identify at least one object in the image based on the object data received from the object repository;
determine a relative spatial proximity score for each of the at least one object based on a proximity distance among the at least one identified object;
determine a functional proximity score for each of the at least one object based on one or more functionalities, associated with the at least one object, extracted from the object repository;
identify one or more domains, from the knowledge repository, associated with each of the one or more functionalities;
compute a domain score for each of the one or more domains based on the relative spatial proximity score, the functional proximity score and one or more user profiles of the users obtained from the knowledge repository; and
reduce the functional ambiguity from the image by associating a domain and at least one functionality associated with the at least one object based on the domain score.

9. The system as claimed in claim 8, wherein the processor is configured to compute the domain score by the steps of:
providing the domain score associated with the one or more domains to the user for the user selection; and
receiving an input from the user indicating one of a new domain or a selected domain associated with the at least one object in the image.

10. The system as claimed in claim 9, wherein the processor is further configured to:
update a user selection of the one or more domains in the knowledge repository based on the input received from the user.

11. The system as claimed in claim 8, wherein the processor is configured to determine the relative spatial proximity score for each of the at least one object by the steps of:
obtain a spatial score for each of the at least one object using Self-Organizing Maps (SOM);
determine a predefined number of object from amongst the at least one object based on the spatial score;
provide terms corresponding to the predefined number of objects to a Bidirectional Recurrent Neural Network (BRNN) to compute a term representation; and
determine the relative spatial proximity score for each of the at least one object based on the term representation.

12. The system as claimed in claim 10, wherein the processor is configured to determine the functional proximity score by performing the steps of:
identifying at least one nearest neighbouring functionality of the one or more functionalities based on a markov random walk model;
computing the functional proximity score for each of the one or more functionalities based on the a functional distance between a functionality and the nearest neighbouring functionality from amongst the one or more functionalities; and
mapping the functional proximity score to corresponding spatial proximal objects identified based on the relative spatial proximity score.

13. The system as claimed in claim 11, wherein the processor is configured to compute the domain score for each of the one or more domains by performing the steps of:
computing the domain score based on the functional proximity score associated with at least one functionalities;
obtaining a matrix of the at least one object, the one or more functionalities and the one or more domains; and
computing an ambiguity factor by applying at least one of a cocycle base algorithm and a maxmaxflow algorithm to the matrix.

14. The system as claimed in claim 8, wherein the processor is further configured to:
generate a text summary of the domain and the at least one functionality associated with the at least one object along with the user profile; and
convert the text summary into corresponding audio format to generate an audio summary.

15. A non-transitory computer readable medium including instructions stored thereon that when processed by at least one processor cause a system to perform acts of:
identifying at least one object in the image based on the object data received from the object repository;
determining a relative spatial proximity score for each of the at least one object based on a proximity distance among the at least one identified object;
determining a functional proximity score for each of the at least one object based on one or more functionalities, associated with the at least one object, extracted from the object repository;
identifying one or more domains, from the knowledge repository, associated with each of the one or more functionalities;
computing a domain score for each of the one or more domains based on the relative spatial proximity score, the functional proximity score and one or more user profiles of the users obtained from the knowledge repository; and
reducing the functional ambiguity from the image by associating a domain and at least one functionality associated with the at least one object based on the domain score.

Dated this 28th day of March 2015

M.S. Devi
Of K&S Partners
Agent for the Applicant
,TagSPECI:FIELD OF THE DISCLOSURE
The present subject matter is related, in general to content management, and more particularly, but not exclusively to method and system for reducing functional ambiguity in visual contents.