Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.

Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.

An information processing apparatus includes a processor configured to acquire a first recognition result and a first recognition probability on target data from a first recognizer, acquire a second recognition result and a second recognition probability on the target data from a second recognizer, execute checking of the first recognition result and the second recognition result, and execute first control in a case where the first recognition result and the second recognition result match each other as a result of the checking. The first control is control for executing either of first processing or second processing on the matched recognition result and outputting a processing result based on at least one of the first recognition probability or the second recognition probability. A human workload for the first processing is smaller than a human workload for the second processing.

A computer-implemented method for client-side identity verification may include (1) receiving, via an endpoint computing device, input from a user that includes biometric data of the user captured by a sensor of the endpoint computing device and visual data of a physical identification document that includes a record of the biometric data, (2) verifying, by the endpoint computing device, that the biometric data captured by the sensor of the endpoint computing device matches the record of the biometric data in the physical identification document, and (3) transmitting, to a server, a verification that the user has been identified while preventing the biometric data from being included in the verification sent to the server. Various other methods, systems, and computer-readable media are also disclosed.

Systems, apparatuses, methods, and computer program products are disclosed for authenticating handwriting on paper-based documents. An example method includes receiving, by an embedded chip device, handwriting information from a signature device in communication with the embedded chip device. The example method further includes transmitting, by the embedded chip device, document identification information to the signature device. The example method further includes receiving, by the embedded chip device, authentication information from the signature device. Subsequently, the example method includes storing, by the embedded chip device, the handwriting information and the authentication information as handwriting authentication metadata in association with the document identification information.

A clustering method includes configuring a network with clustering target objects; collecting significance of the clustering target objects; performing network embedding for outputting a set of vectors representing neighboring objects of the clustering target objects constituting the network using a neural network; and performing clustering on the clustering target objects using the set of vectors and information on each of the clustering target objects, wherein the neural network is trained so that neighboring objects having high significance are output with higher probability.

A robot management system (RMS) includes a plurality of service robots deployed within an operations venue that includes a plurality of gaming devices, an operator terminal presenting a graphical user interface (GUI) to an operator, and a robot management system server (RMS server) configured in networked communication with the plurality of service robots. The RMS server is configured to: identify location data for the service robots; create an interactive overlay map of the operations venue that includes a static map of the operations venue, overlay data showing the location data of the plurality of service robots over the static map, and an interactive icon for each service robot of the plurality of service robots; display, via the GUI, the overlay map; receive a first input indicating a selection of a first interactive icon associated with a first service robot; and display current status information associated with the first service robot.

Described are methods and systems for training a machine learning (ML) model to detect anomalies in images of documents. A first image of a first set of images of documents is obtained. Each first image relates to a region of the document and the first set of images comprises an image of a document containing an anomaly and an image of a document not containing an anomaly. Signal processing algorithms are applied to the first images to generate a signal for each first image and each algorithm, and a discriminative power of each algorithm is evaluated. Based on the discriminative power, a signal processing algorithm is selected and ML model input data is generated using signals generated by applying the algorithm to second digital images. The ML model is trained using the input data to produce output indicating whether an image of a document contains an anomaly.

A method, a computer system and a computer program product train machine learning models. The method includes coupling the machine learning system to a network and receiving. by the machine learning system via the network, a new estimator not included in the list of estimators and a respective documentation. The method also includes adding the new estimator to the list stored in memory. The method further includes reading the documentation and providing the machine learning process tool with respective extracted data and adapting, by the machine learning process tool, at least one training data set out of the group of training data sets to the new estimator on the basis of the extracted data. Lastly, the method includes training at least a subset of the machine learning models by using the new estimator, with the at least one training data set as an input, the training resulting in an output.

In a system, a setting window including at least a preview region in which a scanned image is previewed and a text field to which attribute information on the scanned image is input is displayed, when a character region within the scanned image previewed in the setting window is moused over, control to preliminarily display a character string corresponding to the moused-over character region in the text field is performed, and when the moused-over character region is clicked by a mouse, control to fix the character string preliminarily displayed in the text field is performed.