1. A system for recognizing a logo from an image, the system comprising:
an image processing module configured to receive an image from an image
5 capturing device and pre-process the received image, wherein the received
image comprises a logo to be recognized;
a logo database comprising a plurality of logos; and
a logo recognition controller configured to receive the pre-processed image and sequentially send the pre-processed image to:
D a text based logo recognition module configured to recognize the logo
by detecting text of the logo present in the pre-processed image;
an image based logo recognition module configured to recognize the
logo by extracting one or more local and global features of a region of
interest associated with the logo present in the pre-processed image if
5 the text based logo recognition module fails to recognize the logo;
a sign based logo recognition module configured to recognize the logo by detecting one or more signs in proximity of the logo present in the pre-processed image if the image based logo recognition module fails to recognize the logo; and
) a region based logo recognition module configured to recognize the logo
by identifying regions where the logo is present in the pre-processed image if the sign based logo recognition module fails to recognize the logo.
> 2. The system of claim 1, wherein the logo in the received image is at least one of: a text based logo, a symbol based logo, and a combination of text and symbol.
3. The system of claim 1, wherein the logo in the received image is one of:

a logo existing in the logo database; and
a variant of the existing logo that is absent in the logo database.
4. The system of claim 1, wherein the text based logo recognition module detects the text using optical character recognition technique, further wherein upon detecting the text, the text based logo recognition module compares the detected text with text of the logos present in the logo database such that a match corresponds to the recognition of the logo.
5. The system of claim 1, wherein the image based logo recognition module further compares the extracted one or more local and global features of the region of interest with the one or more local and global features of the existing logos present in the logo database such that a match corresponds to the recognition of the logo.
6. The system of claim 1, wherein the sign based logo recognition module detects the one or more signs through an object detection technique, the detection of the one or more signs shortlists the logo as a potential logo.
7. The system of claim 6, wherein the sign based logo recognition module further extracts edges of the potential logo and classifies the extracted edges with the edges of a nearest neighbor from the existing logos, wherein the classification of the extracted edges of the potential logo candidate with the edges of the nearest neighbor from the existing logos facilitates in recognition of the logo present in the pre-processed image.
8. The system of claim 1, wherein the region based logo recognition module identifies regions by applying color segmentation and texture segmentation techniques, further wherein identification of the regions facilitates in shortlisting a potential logo candidate.
9. The system of claim 8, wherein the region based logo recognition module further extracts edges of the potential logo candidate and classifies the extracted edges

with the edges of a nearest neighbor from the existing logos, wherein the classification of the extracted edges of the potential logo candidate with the edges of the nearest neighbor from the existing logos facilitates in recognition of the logo present in the pre-processed image.
10. The system of claim 1, wherein the logo database is updated with the logo recognized by one of: the sign based logo recognition module and the region based logo recognition module.
11. A method for recognizing a logo from an image, the method comprising:
receiving an image from an image capturing device, wherein the received image comprises the logo to be recognized;
pre-processing the received image;
detecting text of the logo to recognize the logo present in the pre-processed image;
extracting one or more local and global features of a region of interest associated with the logo to recognize the logo present in the pre-processed image if the text is not detected in the logo;
detecting one or more signs in proximity of the logo to recognize the logo present in the pre-processed image if the logo is not recognized by extracting one or more local and global features of the logo; and
identifying a region where the logo is present in the pre-processed image to recognize the logo if the logo is not recognized by detecting the one or more signs in proximity of the logo.
12. The method of claim 11, wherein the logo in the received image is at least one of: a text based logo, a symbol based logo, and a combination of text and symbol.
13. The method of claim 11, wherein the logo in the received image is one of:

a logo existing in a logo database; and
a variant of the existing logo that is absent in the logo database.
14. The method of claim 11, wherein detection of the text is achieved using optical
5 character recognition technique, further wherein upon detecting the text, the
detected text is compared with text of logos present in a logo database such that a match corresponds to the recognition of the logo.
15. The method of claim 11, wherein the extracted one or more local and global
0 features of the region of interest are compared with the one or more local and
global features of existing logos present in a logo database such that a match corresponds to the recognition of the logo.
16. The method of claim 11, wherein the one or more signs are detected through an
5 object detection technique, the detection of the one or more signs shortlists the
logo as a shortlisted potential logo.
17. The method of claim 15 further comprises extracting edges of the potential logo
and classifying the extracted edges with the edges of a nearest neighbor from logos
0 existing in a logo database, wherein the classification of the extracted edges of the
potential logo candidate with the edges of the nearest neighbor from the logos existing in the logo database facilitates in the recognition of the logo present in the pre-processed image.
5 18. The method of claim 11, wherein the regions where the logo is present in the pre-processed image is identified by color segmentation and texture segmentation of the pre-processed image, further wherein identification of the regions facilitates in shortlisting a potential logo candidate.
0 19. The method of claim 17 further comprises extracting edges of the potential logo candidate and classifying the extracted edges with the edges of a nearest neighbor from logos existing in a logo database, wherein the classification of the extracted

edges of the potential logo candidate with the edges of the nearest neighbor from the logos existing in the logo database facilitates in the recognition of the logo present in the pre-processed image.
20. A computer program product comprising:
a non-transitory computer-readable medium having computer-readable program code stored thereon, the computer-readable program code comprising instructions that when executed by a processor, cause the processor to:
receive an image from an image capturing device, wherein the received image comprises the logo to be recognized;
pre-process the received image;
detect text of the logo to recognize the logo present in the pre-processed image;
extract one or more local and global features of a region of interest associated with the logo to recognize the logo present in the pre-processed image if the text is not detected in the logo;
detect one or more signs in proximity of the logo to recognize the logo present in the pre-processed image if the logo is not recognized by extracting one or more local and global features of the logo; and
identify regions where the logo is present in the pre-processed image to recognize the logo present in the pre-processed image if the logo is not recognized by detecting one or more signs in proximity of the logo.