Abstract: A method, including calculating a first distance matrix for a first binary image and a second distance matrix for a second binary image, and calculating a first gradient matrix for the first distance matrix and a second gradient matrix for the second distance matrix. Using the calculated distance and gradient matrices, a displacement matrix is calculated that defines a change in position between elements in the first distance matrix and corresponding elements in the second distance matrix. Outlier elements are identified including elements in the displacement matrix satisfying at least one predetermined criterion, and the identified outlier are replaced with calculated interpolated values.

Abstract: A method, system, and computer program product for font reproduction in electronic documents are provided. The method includes: receiving an image of a printed document; extracting pairs of consecutive characters from the image of the printed document; storing the extracted pairs as images of the characters; and reproducing the printed document as an electronic document with text of overlapping extracted character pair images. Extracting pairs of consecutive characters includes extracting adjacent horizontal characters, extracting spaced horizontal characters, and extracting spaced vertical characters. Reproducing the printed document as an electronic document includes reproducing the spacing between words and between lines using the spaced horizontal characters and the spaced vertical characters as anchors in the reproduced document.

Abstract: A novel and useful method of processing digital images to correct distortion caused by a sheet-fed scanner. The method of the present invention derives a model which estimates the distortion. Match points are detected in the digital image and compared to match points of pre-defined templates. Treating the relative locations of the detected match points as polar coordinates (as opposed to Cartesian coordinates) enables a model to be derived to correct the distortion. In the event that there are multiple distortions to the digital image the digital image is partitioned into segments, with a separate model derived for each segment.

Abstract: A computer implemented method for adaptive optical character recognition on a document with distorted characters includes performing a distortion-correction transformation on a segmented character of the document assuming the segmented character to be a candidate character. The method further includes comparing the transformed segmented character to the candidate character by calculating a comparison score. If the calculated score is within a predetermined range, the segmented character is identified with the candidate character. The method may be implemented in either of computer hardware configured to perform the method, or in computer software embodied in a non-transitory, tangible, computer-readable storage medium. Also disclosed are corresponding computer program product and data processing system.

Abstract: Techniques for performing page verification of a document are provided. The techniques include performing a recognition technique on a document to recognize one or more objects in the document, excluding the one or more recognized objects from the document, and performing page verification of the document, wherein page verification comprises visual inspection of the document excluding the one or more recognized objects.

Abstract: A method for correcting results of OCR or other scanned symbols. Initially scanning and performing OCR classification on a document. Clustering character/symbol classifications resulting from the OCR based on shapes. Creating super-symbols based on at least a first difference in the shapes of the clustered characters/symbols exceeding a first threshold. A carpet of super-symbols, emphasizing localized differences in similar symbols, is displayed for analysis testing.

Abstract: A method and system for monitoring a workstation. The system includes a monitoring system for monitoring activity on a workstation and an analysis module for comparing a monitored activity to specified activities in a work profile. The system may include an alert generator for generating an alert if the monitored activity does not conform to the work profile. The work profile may be a user profile of specified activities allowed to be performed by a user, and/or a transaction profile of a sequence of specified activities to be performed in a transaction by a user. The monitoring system includes an inputs monitor for monitoring inputs by the user into the workstation, a screen monitor which extracts content from a screen display viewed by a user, and a physical presence monitor to determine if a user is at his workstation.

Abstract: A computer implemented method for correcting distortion in an image of a page includes identifying a set of high quality (HQ) words in undistorted regions of one or more images of pages having content related to the content of the page. At least one distorted word in the image the page is identified such that each distorted word corresponds to a high quality word of the set. A global transformation function is generated for application to the image of the page so as to tranform the distorted word into its corresponding high quality word. The global transformation function is applied to pixels of the image of the page.

Abstract: Disclosed embodiments of the invention provide automated global optimization methods and systems of OCR, tailored to each document being digitized. A document-specific database is created from an OCR scan of a document of interest, which contains an exhaustive listing of words in the document. Images of each word, taken from all the fonts encountered, are entered into the database and mapped to a corresponding textual representation. After entry of a first instance of an image of a word written in a particular font, each new occurrence of the word in that font can be quickly recognized by image processing techniques. The disclosed methods and systems may be used in conjunction with adaptive character recognition training and word recognition training of the OCR engines.

Abstract: A method, system, and computer program product for font reproduction in electronic documents are provided. The method includes: receiving an image of a printed document; extracting pairs of consecutive characters from the image of the printed document; storing the extracted pairs as images of the characters; and reproducing the printed document as an electronic document with text of overlapping extracted character pair images. Extracting pairs of consecutive characters includes extracting adjacent horizontal characters, extracting spaced horizontal characters, and extracting spaced vertical characters. Reproducing the printed document as an electronic document includes reproducing the spacing between words and between lines using the spaced horizontal characters and the spaced vertical characters as anchors in the reproduced document.

Abstract: A method and system for monitoring a workstation. The system includes a monitoring system for monitoring activity on a workstation and an analysis module for comparing a monitored activity to specified activities in a work profile. The system may include an alert generator for generating an alert if the monitored activity does not conform to the work profile. The work profile may be a user profile of specified activities allowed to be performed by a user, and/or a transaction profile of a sequence of specified activities to be performed in a transaction by a user. The monitoring system includes an inputs monitor for monitoring inputs by the user into the workstation, a screen monitor which extracts content from a screen display viewed by a user, and a physical presence monitor to determine if a user is at his workstation.

Abstract: Techniques for performing page verification of a document are provided. The techniques include performing a recognition technique on a document to recognize one or more objects in the document, excluding the one or more recognized objects from the document, and performing page verification of the document, wherein page verification comprises visual inspection of the document excluding the one or more recognized objects.

Abstract: A novel and useful method of processing digital images to correct distortion caused by a sheet-fed scanner. The method of the present invention derives a model which estimates the distortion. Match points are detected in the digital image and compared to match points of pre-defined templates. Treating the relative locations of the detected match points as polar coordinates (as opposed to Cartesian coordinates) enables a model to be derived to correct the distortion. In the event that there are multiple distortions to the digital image the digital image is partitioned into segments, with a separate model derived for each segment.

Abstract: A system is presented for scanning entire books or document all at once using an adaptive process where the book or document has known fonts and unknown fonts. The known fonts are processed through a verification system where sure words and error words are determined. Both the sure words and error words are sent to OCR training where they are re-OCR'ed and repeatedly verified until they meet a predetermined quality criteria. Characters or words not meeting the predetermined quality criteria receive additional OCR training until all the characters and words pass the predetermined quality criteria. Unknown fonts are scanned and clustered together by shape. Outliers in the shapes are manually keyed-in. Those symbols that are manually classified go to OCR training and then to the known type optimization process.

Abstract: Disclosed embodiments of the invention provide automated global optimization methods and systems of OCR, tailored to each document being digitized. A document-specific database is created from an OCR scan of a document of interest, which contains an exhaustive listing of words in the document. Images of each word, taken from all the fonts encountered, are entered into the database and mapped to a corresponding textual representation. After entry of a first instance of an image of a word written in a particular font, each new occurrence of the word in that font can be quickly recognized by image processing techniques. The disclosed methods and systems may be used in conjunction with adaptive character recognition training and word recognition training of the OCR engines.

Abstract: A method for correcting results of OCR or other scanned symbols that initially scans a document, performs OCR classification on the scanned document. Clustering of characters/symbols classifications that results from the OCR based on shapes is followed by the creation of super-symbols based on at least first differences in the shapes of the clustered characters/symbols exceeding a first threshold. A carpet of the super symbols is displayed for analysis testing and that provides a display that emphasizes localized differences in similar symbols.

Abstract: A system is presented for scanning entire books or document all at once using an adaptive process where the book or document has known fonts and unknown fonts. The known fonts are processed through a verification system where sure words and error words are determined. Both the sure words and error words are sent to OCR training where they are re-OCR'ed and repeatedly verified until they meet a predetermined quality criteria. Characters or words not meeting the predetermined quality criteria receive additional OCR training until all the characters and words pass the predetermined quality criteria. Unknown fonts are scanned and clustered together by shape. Outliers in the shapes are manually keyed-in. Those symbols that are manually classified go to OCR training and then to the known type optimization process.

Abstract: A method for verifying authenticity of a vehicle, including programming a device to sequentially change a device element to an altered device element according to a change device element algorithm, and attaching the device to the vehicle. The method also includes generating the altered device element, and verifying that the altered device element matches an expected device element generated by the algorithm.

Abstract: A system/method is presented for scanning entire books or document all at once using an adaptive process where the book or document has known fonts and unknown fonts. The known fonts are processed through a verification system where sure words and error words are determined. Both the sure words and error words are sent to OCR training where they are re-OCR'ed and repeatedly verified until they meet a predetermined quality criteria. Characters or word not meeting the predetermined quality criteria receive additional OCR training until all the characters and words pass the predetermined quality criteria. Unknown fonts are scanned and clustered together by shape. Outliers in the shapes are manually key-in. Those symbols that are manually classified go to OCR training and then to the known type optimization process.

Abstract: A method for automatic sorting includes receiving an item in a sequence of items to be sorted, each such item marked with a respective machine-readable identifying code and with respective characters in a location relative to the code that varies from one item to another in the sequence. A position of the code on the item is determined and, responsive to the position of the code, the location of the characters on the item is found. The characters are processed to determine a destination of the item.