Techniques are provided for identifying objects (such as products within a physical store) within a captured video scene and indicating which of object in the captured scene matches a desired object requested by a user. The matching object is then displayed in an accentuated manner to the user in real-time (via augmented reality). Object identification is carried out via a multimodal methodology. Objects within the captured video scene are identified using a neural network trained to identify different types of objects. The identified objects can then be compared against a database of pre-stored images of the desired product to determine if a close match is found. Additionally, text on the identified objects is analyzed and compared to the text of the desired object. Based on either or both identification methods, the desired object is indicated to the user on their display, via an augmented reality graphic.

To replace text in a digital video image sequence, a system will process frames of the sequence to: define a region of interest (ROI) with original text in each of the frames; use the ROIs to select a reference frame from the sequence; select a target frame from the sequence; determine a transform function between the ROI of the reference frame and the ROI of the target frame; replace the original text in the ROI of the reference frame with replacement text to yield a modified reference frame ROI; and use the transform function to transform the modified reference frame ROI to a modified target frame ROI in which the original text is replaced with the replacement text. The system will then insert the modified target frame ROI into the target frame to produce a modified target frame. This process may repeat for other target frames of the sequence.

A system, method, and computer program product provides a way to separate connected or adhered adjacent characters of a digital image for license plate recognition. As a threshold processing, the method performs a recognition of character adhesion by obtaining character parameters using an image processor. The parameters include a horizontal max crossing and a ratio of width and height. A first rule-based module is used responsive to the character parameters to distinguish the adhered characters (character adhesions) that are easy to judge, leaving the uncertain part to a character adhesion classifier model for discrimination. Character adhesion data is obtained by data augmentation including the adding of a random distance between two single characters to create class like adhered characters. Then the character adhesion classifier model of single character and character adhesion data is trained. Any uncertain part can be distinguished by the trained character adhesion classifier model.

Methods and systems for managing information about fuel stations. A system includes an imaging system and a profile management system. The imaging system is used for generating imaging data for a fuel station onboard a vehicle. The profile management system receives the imaging data. The profile management system identifies selected information for the fuel station based on the imaging data received. The selected information includes an identification of the fuel station, pricing information, and at least one of fuel inventory information, or business hours information for the fuel station. The profile management system updates a profile for the fuel station based on the selected information. The profile management system sends at least a portion of the profile for the fuel station to a target system.

A parking enforcement system includes an autonomous vehicle that is equipped with an image capture device that is configured to capture images of license plates of parked vehicles while the autonomous vehicle moves through a parking zone. The system will process the images to extract license plate numbers from the images. The system will correlate the license plate numbers with data in a parking enforcement database to determine whether the license plate numbers are associated with an unexpired parking transaction. For any license plate number that is not subject to an unexpired parking transaction, the system may initiate an enforcement action. For any license plate number that is subject to an unexpired parking transaction, the system may not initiate an enforcement action.

A system capable of determining which recognition algorithms should be applied to regions of interest within digital representations is presented. A preprocessing module utilizes one or more feature identification algorithms to determine regions of interest based on feature density. The preprocessing modules leverages the feature density signature for each region to determine which of a plurality of diverse recognition modules should operate on the region of interest. A specific embodiment that focuses on structured documents is also presented. Further, the disclosed approach can be enhanced by addition of an object classifier that classifies types of objects found in the regions of interest.

A system and method for generating a notification of a price change for a transaction and facilitating an associated price adjustment based on electronic image capture of a paper receipt. An image capture system captures an electronic image of a paper transaction receipt, which is transmitted to a data extraction processor that extracts transaction receipt data from the captured electronic image. A unique key is generated by an authentication server that is matched to a transaction record to generate a reliability score for the OCRed image and to authorize price matching. If the price monitoring server identifies that the price of a purchased transaction item has changed, the price monitoring server automatically generates a notification to the user indicating the price change and an email to the customer service department of the merchant from which the transaction item was purchased, requesting a price adjustment that is credited back to the payment instrument.

A reward system and method collects feedback based on driving records and road conditions. A camera disposed on a vehicle can generate traffic-condition data, and the neural network based artificial intelligence is used to identify a traffic flow and a road-sign area in the traffic-condition data. When the road-sign area is identified, the optical character recognition is performed on the road-sign area to generate a geographic location information. The user information, the traffic flow and the geographic location information are embedded into the corresponding traffic-condition data. The traffic-condition data is transmitted to a map-data host for classification and storage. When the geographic location information of the traffic-condition data matches with road congestion location information and a clarity of the traffic-condition data is greater than a preset threshold, a contribution reward is calculated to improve timeliness of updating the traffic-condition data and the user's incentive for providing the traffic-condition data.

In one embodiment, a method includes accessing visual signals comprising images portraying textual content in a real-world environment associated with a first user from a client system associated with the first user, recognizing the textual content based on machine-learning models and the visual signals, determining a context associated with the first user with respect to the real-world environment based on the visual signals, executing tasks determined based on the textual content and the determined context for the first user, and sending instructions for presenting execution results of the tasks to the first user to the client system.

A video text tracking method and an electronic device are disclosed. In the method, a text line region is split into sub-regions, the sub-regions are tracked and then processed, and processed sub-regions are combined into a new text line. The technical solutions provided in this application are not only applicable to a straight-line text scenario or a curved text scenario, but also present a good tracking effect for a deformable text line.