Abstract: Techniques are disclosed for performing optical character recognition (OCR) by assessing and improving quality of electronic documents to perform the OCR. For example a method for identifying information in an electronic document includes obtaining a reference image of the electronic document, distorting the reference image by adjusting different sets of one or more parameters associated with a quality of the reference image to generate a plurality of distorted images, analyzing each distorted image to detect the adjusted set of parameters and corresponding adjusted values, determining an accuracy of detection of the set of parameters and the adjusted values, and training a model based at least on the plurality of distorted images and the accuracy of the detection, wherein the trained model determines at least a first technique for adjusting a set of parameters in a second image to prepare the second image for optical character recognition.

Abstract: Techniques are disclosed to identify a form document in an image using a digital fingerprint of the form document. To do so, the image is evaluated to detect features of the image and generate a boundary around each feature. For each boundary, dimensions of the boundary may be stored in a color channel of a pixel in a second image. Thus, the color of the pixel represents the size of the boundary. The second image is the digital fingerprint of the form. To identify the form corresponding to the digital fingerprint, the digital fingerprint may be compared to digital fingerprints of known forms.

Abstract: Systems of the present disclosure allow fields and labels to be identified in a digital image of a form without performing OCR. A digital image of a form can be partitioned into image segments using computer-vision image-segmentation techniques. Features for each image segment can be extracted using computer-vision feature-detection methods. The features extracted from an image segment can be included in an input instance for a machine-learning model. The machine-learning model can assign a classification to the input instance. The classification can associate the input instance with a field type or a label type.

Abstract: The disclosed embodiments relate to a system and method for calibrating optical character recognition (OCR) processes for an image captured through a mobile computing device. During operation, the system adjusts the OCR process through pre-recognition functions, OCR functions and/or post-recognition functions with multiple sets of parameter settings. With each of these sets, the system scores the OCR process output against an image with known text. Once the sets are scored, the system sorts the sets of parameters, removes some sets, then mixes and mutates the remaining sets in a process akin to evolutionary biology. By repeating this procedure, the system produces a set of parameter settings that can be used to calibrate OCR processing.

Abstract: A method and system identifies and addresses imaging artifacts in an image of a financial document to enable a software system to provide financial services based on the image of the financial document. The method and system receive document image data, extract image features from the document image data, and apply the image features to an analytics model to generate an image classification, according to one embodiment. The method and system use the image classification to determine whether the document image data contains one or more particular image artifacts (e.g., Moiré patterns), according to one embodiment. If the software system determines that it is likely that the document image data contains one or more particular image artifacts, then the software system applies a filter (e.g., a median filter) to the document image data to reduce and/or remove the one or more particular image artifacts, according to one embodiment.

Abstract: The disclosed embodiments provide a system that facilitates geolocation of a user. The system includes a server and an electronic device. First, the server receives a location of the user from an electronic device of the user and determines a window around the location. Next, the server transmits the window and one or more geofences within the window to the electronic device. The electronic device then obtains one or more precision buffers associated with one or more levels of accuracy for detecting the location of the user near the one or more geofences. Finally, the electronic device facilitates use of the one or more geofences by varying a geolocation technique for tracking the location of the user based on the one or more precision buffers.

Abstract: The disclosed embodiments provide a system that dynamically updates a geofence of a mobile business. During operation, the system establishes a first location and a first geofence for the mobile business. Next, the system receives a second location of the mobile business different than the first location of the mobile business. The system then generates an updated geofence for the mobile business based on the second location of the mobile business. The system subsequently broadcasts the second location of the mobile business to a set of mobile clients monitoring the mobile business.

Abstract: Apparatus for performing organic synthetic reactions, particularly no-carrier-added nucleophilic radiofluorination reactions for PET radiotracer production. The apparatus includes an optical reaction cell and a source of broadband infrared radiant energy, which permits direct coupling of the emitted radiant energy with the reaction medium to heat the reaction medium. Preferably, the apparatus includes means for focusing the emitted radiant energy into the reaction cell, and the reaction cell itself is preferably configured to reflect transmitted radiant energy back into the reaction medium to further improve the efficiency of the apparatus. The apparatus is well suited to the production of high-yield syntheses of 2-?.sup.18 F!fluoro-2-deoxy-D-glucose. Also provided is a method for performing organic synthetic reactions, including the manufacture of ?.sup.18 F!-labeled compounds useful as PET radiotracers, and particularly for the preparation of 2-?.sup.

Abstract: A rotary transformer for aircraft deicing apparatus, the transformer including a primary winding adjacent a laminated primary core, and a secondary winding adjacent a laminated secondary core; at least one of the cores being rotatable with respect to the other core.

Abstract: A rotating rectifier assembly has a substrate which has a metal core and a ceramic coating. An exciter rotor which produces an ac signal and the rectifier assembly are disposed about a generator shaft. The substrate has rectifiers arranged in a rectifying circuit. An ac lead extends from the ac windings in the exciter rotor to the rectifying circuit where a dc signal is generated and fed to a main generator rotor.

Abstract: Apparatus and method for electrically interconnecting in and supporting the rectifier components a rotating rectifier assembly. An exciter rotor and the rectifier assembly are disposed about a generator shaft. In an embodiment providing full wave rectification, the rectifier assembly has a substrate having rectifiers mounted in a rectifying circuit on two exposed conductive areas. An ac lead extends from each of the ac windings in the exciter rotor to the rotating rectifier assembly. A bus bar has a bar section secured to adjacent rectifiers. The bus bar further has a tab section adapted to receive one ac lead extending from the bar section. A support ring is disposed about the generator shaft and secured to the recifier substrate, as well as the exciter rotor. The tab section from each of the bus bars is wrapped around the inner sleeve of the ring so that the centrifical forces exerted on the bus bars during the rotation of the shaft are opposed by the inner sleeve of the ring.

Abstract: A video inspection system comprising a TV camera for producing a digital video image of a subject, an interface, having a direct memory access channel, for structuring the digital data, a high speed random access memory for storing the digital data, a bus oriented processor for performing high speed processing of the digital data in the memory, a digital computer for controlling the operation of the system and an operator terminal for communicating with the system.

Abstract: A digital self-calibrating power factor controller for an AC induction motor. During start-up a first number corresponding to the actual phase angle between motor voltage and current is determined and compared with a second number corresponding to a desired delay in energizing the motor. The second number is varied until both numbers are approximately equal. A third number corresponding to a desired phase angle is determined and stored and the system switches from start-up to run. The first number corresponding to the actual phase angle is now compared with the third number corresponding to the desired phase angle. The second number corresponding to a desired delay is now varied with motor load so as to keep the actual phase angle equal to the desired phase angle.

Abstract: A video inspection system comprising a TV camera for producing a digital video image of a subject, an interface, having a direct memory access channel, for structuring the digital data, a high speed random access memory for storing the digital data, a bus oriented processor for performing high speed processing of the digital data in the memory, a digital computer for controlling the operation of the system and an operator terminal for communicating with the system.

Abstract: An automatic process controller and method for automatically controlling in real time the formation of an object having boundaries which change with time. A TV camera provides a video image of the object. An interface circuit detects first and second boundaries of the object by analyzing the analog video signal and generates first and second digital numbers corresponding to the first and second boundaries. A programmable digital processor determines the maximum difference between the first and second digital numbers, compares that difference with a target object size and produces a control signal based on the comparison for controlling the continued formation of the object.