Abstract: An automated method for capturing data from electronic images of commercial documents such as invoices, bills of lading, explanations of benefits, etc. is described. An optimal mapping between the fields of interest in an image of a page of a document and the corresponding fields of a pre-trained image of a page of a similar document is defined. This mapping allows an automatic precise extraction of data from the fields of interest in an image regardless of distortions the image is subjected to in the process of scanning.

Abstract: An automated method for assembling common commercial documents such as invoices, bills of lading and purchase orders placed in multipage files containing multiple documents without separators is described. The method is applicable in the presence of attachments and utilizes training data consisting of fields of interest and their locations in documents together with invariant fields frequently present in documents.

Abstract: An automated method for generation of training samples for classification of electronic images of commercial documents such as invoices, bills of lading, explanations of benefits, etc. is described. An image of a page of a document is generated as a representative of similar pages from the same origin regardless whether the page of the document contains permanent and variable information or just permanent information.

Abstract: A completely automated method for classifying electronic images of commercial documents such as invoices, bills of lading, explanations of benefits, etc. is based on the layout of the documents. A document is classified as belonging to a class of similarly laid out images if its distance, determined by a set of pre-defined metrics, to any of the template layouts from the same class of template layouts does not exceed a certain user-defined threshold. Alternatively, if the sum of distances from a given image to several template layouts from the same class does not exceed a user-selected threshold, the image is deemed to belong to a class of images with a specific layout.

Abstract: A hand-held mobile communication device, such as smart telephone, alone or in protective case, incorporating sensors and signal conditioning modules for measuring signals from external sources of electromagnetic radiation (EMR) in different spectral ranges. These include detector monitoring EMR that pose potential health hazards or may interfere with various electronic devices. Other integrated EMR sensor is a photodiode for the ultraviolet detection to monitor the user's sun exposure and a thermal infrared detector for non-contact measurement of temperature of humans or inanimate objects. This detector in combination with a digital camera and a pattern recognition signal processing allows accurate non-contact measuring temperatures at specific location.

Abstract: A completely automated method for classifying electronic images of commercial documents such as invoices, bills of lading, explanations of benefits, etc. is based on the layout of the documents. A document is classified as belonging to a class of similarly laid out images if its distance, determined by a predefined metric, to any of the templates from the same class of templates exceeds a certain user-defined threshold. Alternatively, if the sum of distances from a given image to several templates from the same class exceeds a user-selected threshold, the image is deemed to belong to a class of images with a specific layout.

Abstract: A hand-held mobile communication device, such as smart telephone, incorporating sensors and signal conditioning modules for measuring signals from external sources of electromagnetic radiation (EMR) in the low, radio, ultraviolet, and infrared spectral ranges. These include the detector for receiving and monitoring electromagnetic fields originating from various external sources of radiation that pose potential health hazards or may interfere with various electronic devices. The mobile phone equipped with such sensors could alternate between communication and monitoring functions. Other integrated EMR sensors are a photodiode for the ultraviolet detection to monitor the user's sun exposure and a thermopile for non-contact measurement of temperature of humans or inanimate objects.

Abstract: A method of electronically endorsing a check includes obtaining an electronic image of the check and composing an endorsement data element for the check that includes at least first information identifying a party endorsing the check. The method further includes creating a message data file including the electronic image and the endorsement data element, and creating a signed message data file that includes the message data file and a digital signature of the message data file creating using a private key. The private key may be specific to the party endorsing the check or to an electronic device with which the method is implemented. Also, a method of performing an inquiry relating to a check that was endorsed as described above using the endorsement data element.

Abstract: A method of electronically endorsing a check includes obtaining an electronic image of the check and composing an endorsement data element for the check that includes at least first information identifying a party endorsing the check. The method further includes creating a message data file including the electronic image and the endorsement data element, and creating a signed message data file that includes the message data file and a digital signature of the message data file creating using a private key. The private key may be specific to the party endorsing the check or to an electronic device with which the method is implemented. Also, a method of performing an inquiry relating to a check that was endorsed as described above using the endorsement data element.

Abstract: The present invention provides a system and method of automatically selecting check templates for image-based fraud detection including the steps of presenting a check image from an account, matching the check image against a series of known check templates from the account, producing confidence scores corresponding to the degree of similarity of the check image compared to each check template and matching the confidence scores with a predetermined high similarity threshold and a predetermined low similarity threshold.

Abstract: A method and apparatus for hierarchical character recognition processing of ambiguous and noisy characters which produces highly reliable results at high levels of hierarchical processing. The invention first applies a universal classifier system (which may comprise one or more universal classifiers) to input image data, and identifies "suspicious" characters. The image data for suspicious characters is then applied to a "specialist" classifier that is designed to handle only a narrow and well-defined set of recognition cases. This hierarchical processing architecture and method results in increased accuracy of recognition. The method is particularly applicable to handwritten characters and to distorted and noisy machine-printed characters.

Abstract: In an inserting machine for collating inserts and placing a collation of said inserts into an envelope, a method is disclosed of determining the amount of postage to be applied to said envelope into which said collation of inserts have been inserted. The inserting machine includes a feed deck and a plurality of feed station adapted to selectively feed said inserts onto said feed deck.