Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes training at least one machine learning model to determine features that can be used to determine whether an image is an authentic image of a document or an automatically generated document image, using a training set of authentic images and a training set of automatically generated document images. A request to classify an image as either an authentic image of a document or an automatically generated document image is received. The machine learning model(s) are used to classify the image as either an authentic image of a document or an automatically generated document image, based on features included in the image that are identified by the machine learning model(s). A classification of the image is provided. The machine learning model(s) are updated based on the image and the classification of the image.

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes receiving a request to authenticate a document image. The image is preprocessed to prepare the image for line orientation analysis. The preprocessed image is analyzed to determine lines in the preprocessed image. The determined lines are automatically analyzed by performing line orientation test(s) on the determined lines to generate line orientation test result(s) for the preprocessed image. The line orientation test result(s) are evaluated to determine whether the image is authentic. In response to determining that at least one line orientation test result matches a predefined condition corresponding to an unauthentic document, a determination is made that the image is not authentic.

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes training at least one machine learning model to determine features that can be used to determine whether an image is an authentic image of a document or an automatically generated document image, using a training set of authentic images and a training set of automatically generated document images. A request to classify an image as either an authentic image of a document or an automatically generated document image is received. The machine learning model(s) are used to classify the image as either an authentic image of a document or an automatically generated document image, based on features included in the image that are identified by the machine learning model(s). A classification of the image is provided. The machine learning model(s) are updated based on the image and the classification of the image.

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes receiving a request to authenticate a document image. The image is preprocessed to prepare the image for line orientation analysis. The preprocessed image is analyzed to determine lines in the preprocessed image. The determined lines are automatically analyzed by performing line orientation test(s) on the determined lines to generate line orientation test result(s) for the preprocessed image. The line orientation test result(s) are evaluated to determine whether the image is authentic. In response to determining that at least one line orientation test result matches a predefined condition corresponding to an unauthentic document, a determination is made that the image is not authentic.

Abstract: Methods, systems, and computer-readable storage media for receiving a set of frames, each frame being provided as a digital image that depicts a portion of an event and a logo associated with a brand, for each frame in the set of frames, and for each pixel in a frame: determining a weight of the pixel based on a distribution assigned to the frame, providing a quality of the logo depicted in the frame, and calculating a pixel quotient based on the weight and the quality, for each frame in the set of frames: determining a frame quotient at least partially based on a sum of all pixel quotients for the frame, and determining an impact indicator for the logo based on a total size of digital media comprising the set of frames and a sum of frame quotients of the frames in the set of frames.

Abstract: A method for generating and viewing on a handheld device a 3-D augmented reality feature containing a rich media message that is linked to a physical object comprises the steps of: a) by a first user: i. Taking a picture of a physical object; ii. selecting an augmented reality theme; iii. attaching the rich media animated object to the image taken, in the desired position and location on the physical object; iv. generating a reach media message from the augmented reality image obtained in step (iii); iv. optionally attaching an additional file to the rich media message; v. Transferring the physical object to a second user; and vi. sending to said second user a message via a communication channel, which contains the augmented reality rich media; b) by the second user (the recipient): vii. viewing the physical object received from the first user, using an AR viewer in the mobile phone camera, thereby to see the augmented reality rich media appearing on said physical object.

Abstract: A method for detecting an event indicative of a change of TV channel by a viewer comprises analyzing one or more video frames displayed on the TV screen to identify a change which is associated with a TV channel change.

Abstract: A TV system with camera or any other media delivery device with camera comprising a screen and related electronics, comprises in combination: 1) Human detector suitable to determine whether one or more viewers are located in front of the screen; 2) A viewer's body pose tracker suitable to analyze a body pose and to determine whether a change has occurred in said pose; 3) An object detector suitable to detect the presence of a plurality of objects in the environment of the screen; 4) An object tracker suitable to detect a change in location of one or more objects; and 5) Logic circuitry suitable to obtain inputs from one or more detectors and trackers and to determine whether a specified condition has been reached on the basis of said inputs.

Abstract: A method for generating and viewing on a handheld device a 3-D augmented reality feature containing a rich media message that is linked to a physical object comprises the steps of: a) by a first user: i. Taking a picture of a physical object; ii. selecting an augmented reality theme; iii. attaching the rich media animated object to the image taken, in the desired position and location on the physical object; iv. generating a reach media message from the augmented reality image obtained in step (iii); iv. optionally attaching an additional file to the rich media message; v. Transferring the physical object to a second user; and vi. sending to said second user a message via a communication channel, which contains the augmented reality rich media; b) by the second user (the recipient): vii. viewing the physical object received from the first user, using an AR viewer in the mobile phone camera, thereby to see the augmented reality rich media appearing on said physical object.

Abstract: A method for generating a preview image of an item to be photographed using flashlights, wherein said preview image is generated without any added light, comprises the steps of: (a) calculating the distance between a portion of the item to be photographed and the camera; (b) calculating the flash light dissemination on the area of said portion, using the distance to said portion and the known flash power to be applied; (c) recalculating captured exposure parameter according to the information gathered from the surface of said portion; and (d) changing the brightness of the preview image by using the calculated lighting parameters at each location.