Abstract: A method and system for warning a driver of a vehicle using a mobile device is disclosed. The method includes capturing at least one facial aspect of the driver and a path view visible ahead of the vehicle up to a predefined distance. The method further includes identifying using image analytics at least one path event demanding attention of the driver based on a path view and a field of view of the driver. The method includes detecting absence of a driver response in response to identifying the at least one path event within the field of view of the driver. The method further includes extracting driver details associated with the driver. The method includes issuing a notification to the driver based on the driver details, when the absence of the driver response is detected.

Abstract: The present disclosure relates to a method for surveillance an area of interest. A surveillance device pre-sets an area of interest for each of plurality of image capturing devices. The surveillance device synchronizes the plurality of image capturing devices to simultaneously observe the area of interest. Upon synchronizing, the surveillance device continuously receives view port details from each of the plurality of image capturing devices. If the received view port details matches with pre-set view port details of the area of interest, then one or more images are captured at the intersection of field of view of plurality of image capturing devices. The captured images are provided to the surveillance device to generate a 3-D model. The 3-D model is observed for detecting presence or absence of a new element in the area of interest.

Abstract: A method and system for warning a driver of a vehicle using a mobile device is disclosed. The method includes capturing at least one facial aspect of the driver and a path view visible ahead of the vehicle up to a predefined distance. The method further includes identifying using image analytics at least one path event demanding attention of the driver based on a path view and a field of view of the driver. The method includes detecting absence of a driver response in response to identifying the at least one path event within the field of view of the driver. The method further includes extracting driver details associated with the driver. The method includes issuing a notification to the driver based on the driver details, when the absence of the driver response is detected.

Abstract: Embodiments of the present disclosure disclose a method for performing Optical Character Recognition (OCR) of an article. The method comprises acquiring an image of the article. The image of the article is scanned using predetermined scan settings. Then, textual regions of the scanned image of the article are identified. The OCR of the at least one of the textual regions is performed using predetermined OCR settings. One or more textual regions of the textual regions are marked upon determining an error in performing the OCR of the one or more textual regions. The OCR of the one or more textual regions is iterated as per one or more predefined OCR scanning parameters based on an OCR quality of the one or more textual regions upon marking the one or more textual regions.

Abstract: The present disclosure relates to a method and device for assisting a user for capturing an image. In an embodiment, an image is focused by a user of an image capturing device. The image capturing device extracts one or more features from the image being focused. The extracted features are classified into significant features and background features. The image capturing device also extracts one or more line segments in the image. Upon extracting the features and the line segments, the image capturing device determines relation between the features and the line segments. The image capturing device provides assistance to the user for capturing the image based on the relation.

Abstract: The present disclosure relates to a method and device for capturing multi-media of an area of interest in plurality of areas using plurality of multi-media capturing devices. The method comprises receiving feeds from each of plurality of multi-media capturing devices and analyzing the feeds to obtain one or more multi-media parameters associated with the plurality of areas. The feeds comprise speech data and at least one of gaze data, dynamics data and gesture data of corresponding plurality of areas. Upon analyzing, interest index is determined for each of the plurality of areas based on the one or more multi-media parameters, weightage parameters and time parameter. Based on the interest index, the area of interest is identified from the plurality of areas for capturing the multi-media of the area of interest.

Abstract: The present disclosure relates to a method and device for capturing multi-media of an area of interest in plurality of areas using plurality of multi-media capturing devices. The method comprises receiving feeds from each of plurality of multi-media capturing devices and analyzing the feeds to obtain one or more multi-media parameters associated with the plurality of areas. The feeds comprise speech data and at least one of gaze data, dynamics data and gesture data of corresponding plurality of areas. Upon analyzing, interest index is determined for each of the plurality of areas based on the one or more multi-media parameters, weightage parameters and time parameter. Based on the interest index, the area of interest is identified from the plurality of areas for capturing the multi-media of the area of interest.

Abstract: The present disclosure relates to a method for surveillance an area of interest. A surveillance device pre-sets an area of interest for each of plurality of image capturing devices. The surveillance device synchronizes the plurality of image capturing devices to simultaneously observe the area of interest. Upon synchronizing, the surveillance device continuously receives view port details from each of the plurality of image capturing devices. If the received view port details matches with pre-set view port details of the area of interest, then one or more images are captured at the intersection of field of view of plurality of image capturing devices. The captured images are provided to the surveillance device to generate a 3-D model. The 3-D model is observed for detecting presence or absence of a new element in the area of interest.

Abstract: Systems and methods for performing real-time image vectorization are disclosed. In one embodiment, the method comprises receiving a vectorized base image. The method further comprises displaying the vectorized base image on a display screen of the camera. The method further comprises obtaining a user feedback on the vectorized base image from a user. The user feedback comprises user selection of at least one non-vectorized subsection in the vectorized base image. The method further comprises receiving a subsection image, from the camera, comprising the at least one non-vectorized subsection selected based on the user feedback. The further comprises performing vectorization on the subsection image to obtain vectorized subsections. The method further comprises overlaying the vectorized subsections on the at least one non-vectorized subsection of the vectorized base image. The method further comprises merging the vectorized base image with the vectorized subsections to obtain an output vectorized image.

Abstract: Systems and methods for performing real-time image vectorization are disclosed. In one embodiment, the method comprises receiving a vectorized base image. The method further comprises displaying the vectorized base image on a display screen of the camera. The method further comprises obtaining a user feedback on the vectorized base image from a user. The user feedback comprises user selection of at least one non-vectorized subsection in the vectorized base image. The method further comprises receiving a subsection image, from the camera, comprising the at least one non-vectorized subsection selected based on the user feedback. The further comprises performing vectorization on the subsection image to obtain vectorized subsections. The method further comprises overlaying the vectorized subsections on the at least one non-vectorized subsection of the vectorized base image. The method further comprises merging the vectorized base image with the vectorized subsections to obtain an output vectorized image.

Abstract: Embodiments of the present disclosure disclose a method for performing Optical Character Recognition (OCR) of an article. The method comprises acquiring an image of the article. The image of the article is scanned using predetermined scan settings. Then, textual regions of the scanned image of the article are identified. The OCR of the at least one of the textual regions is performed using predetermined OCR settings. One or more textual regions of the textual regions are marked upon determining an error in performing the OCR of the one or more textual regions. The OCR of the one or more textual regions is iterated as per one or more predefined OCR scanning parameters based on an OCR quality of the one or more textual regions upon marking the one or more textual regions.

Abstract: The present disclosure relates to a method and device for assisting a user for capturing an image. In an embodiment, an image is focused by a user of an image capturing device. The image capturing device extracts one or more features from the image being focused. The extracted features are classified into significant features and background features. The image capturing device also extracts one or more line segments in the image. Upon extracting the features and the line segments, the image capturing device determines relation between the features and the line segments. The image capturing device provides assistance to the user for capturing the image based on the relation.