System and method for script and orientation detection of images

A method for script and orientation detection of an image, comprising:nextracting textual content in the image;obtaining a vertical component run (VCR) and a horizontal component run (HCR) by vectorizing each connected component in the extracted textual content in the image;computing a concatenated vertical document vector (VDV) and horizontal document vector (HDV) by averaging the obtained VCR and HCR for each connected component in the image;obtaining a substantially matching script and orientation by comparing the computed concatenated VDV and HDV of the image with each of a plurality of reference VDVs and HDVs, wherein each reference VDV and HDV is associated with a script and an orientation of a plurality of scripts and orientations;determining whether the computed concatenated VDV and HDV of the image substantially match with the reference VDV and HDV associated with the matching script and orientation; andif the computed concatenated VDV and HDV of the image substantially match with the reference VDV and HDV associated with the matching script and orientation, then declaring the matching script and orientation as the script and orientation of the image.

A non-transitory computer-readable storage medium for script and orientation detection of images having instructions that when executed by a computing device, cause the computing device to:nextract textual content in the image;obtain a vertical component run (VCR) and a horizontal component run (HCR) by vectorizing each connected component in the extracted textual content in the image; compute a concatenated vertical document vector (VDV) and horizontal document vector (HDV) by averaging the obtained VCR and HCR for each connected component in the image;obtain a substantially matching script and orientation by comparing the computed concatenated VDV and HDV of the image with each of a set of reference VDV and HDV, wherein each reference VDV and HDV is associated with a script and an orientation of a plurality of scripts and orientations;determine whether the computed concatenated VDV and HDV of the image substantially match with the reference VDV and HDV associated with the matching script and orientation; andif the computed concatenated VDV and HDV of the image substantially match with the reference VDV and HDV associated with the matching script and orientation, then declaring the matching script and orientation as the script and orientation of the image.

A system for script and orientation detection of images, comprising:na processor;a memory coupled to the processor; anda script and orientation detection module residing in the memory,wherein the script and orientation detection module extracts textual content in the image,wherein the script and orientation detection module obtains a vertical component run (VCR) and a horizontal component run (HCR) by vectorizing each connected component in the extracted textual content in the image,wherein the script and orientation detection module computes a concatenated vertical document vector (VDV) and horizontal document vector (HDV) by averaging the obtained VCR and HCR for each connected component in the image,wherein the script and orientation detection module obtains a substantially matching script and orientation by comparing the computed concatenated VDV and HDV of the image with each of a plurality of reference VDVs and HDVs, wherein each reference VDV and HDV is associated with a script and an orientation of a plurality of scripts and orientations,wherein the script and orientation detection module determines whether the computed concatenated VDV and HDV of the image substantially match with the reference VDV and HDV associated with the matching script and orientation, andwherein the script and orientation detection module declares the matching script and orientation as the script and orientation of the image, when the computed concatenated VDV and HDV of the image substantially match with the reference VDV and HDV associated with the matching script and orientation.