Abstract: Connected components of dark pixels are clustered from across the image. A “most likely” representative image for each cluster of images is determined, with likelihood determined by a probabilistic model of the image capturing process. An a priori (prior) probability distributions on bitmaps may be used to determine the most likely representative images. For example, a priori probability distributions based on so-called chain codes are implemented. The representative images are used to cluster connected components. Clustering may be repeated. The output page is assembled by replacing each member of a cluster of images by that cluster's representative image.

Abstract: A method and device for creating a notarized document from a document, comprising acquiring image data of the document; generating a document data file based on the image data, the document data file comprising a exemplar table and a block table; and appending the document data file to the document.

Abstract: A method for matching an original document image with a copy image is disclosed. The original document image is defined as an ensemble of blocks, each of the blocks having neighboring blocks. A mask is formed for each of the blocks by dilating foreground pixels included in the block. A best match is searched in the copy image, for each of the blocks, using a search window, by correlating pixels in the mask with pixels in a corresponding portion in the copy image. Each of the best matches has a matching score. Each of the blocks is indicated as “unmatched” when the corresponding matching score is less than a matching threshold. A displacement vector is computed for each of the matched blocks.

Abstract: A system determines the position of an object located on a transport assembly. Sensor arrays are embedded in the transport assembly for identifying boundary locations of the object. The sensor arrays are spaced apart in an arrangement for detecting the locations at which the object crosses the sensor arrays. These locations provide a set of boundary points. The system computes the equation of a rectangle that identifies the location of the object on the transport assembly by minimizing the deviation of the set of boundary points from the boundary of the equation of the rectangle.

Abstract: Systems and methods are provided for automatically determining the font of text in a captured document image. Sequences of turns (left, right, straight) around the boundaries of connected components of black pixels in the captured document image are determined. The probabilities of the sequences of turns have come from a particular font within a library of known fonts can be determined using training set statistics. Using these probabilities, the most probable source font is selected.

Abstract: Document authentication is accomplished by acquiring document image data, generating a set of features of the document, and generating an assist channel that includes information on how to generate the set of features. The set of features and the assist channel are digitally signed and the append to the document. Document verification is accomplished by acquiring document image data and verifying the signature. If the signature is valid, aset of features of the document is generated using information contained in the assist channel appended to the document. The generated set of features is then compared to the set of features appended on the document. If the sets do not match, the document is determined to have been altered sometimes after the assist channel was appended to the document, i.e., the document is not genuine. Otherwise, the document can be considered to be genuine.

Abstract: Connected components of dark pixels are clustered from across the image. A “most likely” representative image for each cluster of images is determined, with likelihood determined by a probabilistic model of the image capturing process. An a priori (prior) probability distributions on bitmaps may be used to determine the most likely representative images. For example, a priori probability distributions based on so-called chain codes are implemented. The representative images are used to cluster connected components. Clustering may be repeated. The output page is assembled by replacing each member of a cluster of images by that cluster's representative image.

Abstract: Systems and methods for verifying a document. A document having an encoded document data portion that includes assist information and at least one digitally-signed appended one-way hash is inputted. The encoded document data file is decoded and a representation is recovered using the assist information. A verification one-way hash is generated from the recovered representation. The verification one-way hash is then compared to the appended one way hash and the authenticity of the document is verified based on the results of the comparison.

Abstract: Methods and systems for authenticating documents. Document data to be modified to contain authentication is inputted. A representation is determined from the document data. Assist information that is usable to reliably recover a determined representation is determined. A one-way hash of the representation and assist information is determined. The one-way hash is then cryptographically signed. The assist information and digitally signed one-way hash is then appended to the document.

Abstract: Xerox Docket No. D/A0037QDocument authentication is accomplished by acquiring document image data, generating a set of features of the document, and generating an assist channel that includes information on how to generate the set of features. The set of features and the assist channel are digitally signed and then append to the document. Document verification is accomplished by acquiring document image data and verifying the signature. If the signature is valid, a set of features of the document is generated using information contained in the assist channel appended to the document. The generated set of features is then compared to the set of features appended on the document. If the sets do not match, the document is determined to have been altered sometimes after the assist channel was appended to the document, i.e., the document is not genuine. Otherwise, the document can be considered to be genuine.

Abstract: A method and device for creating a notarized document from a document, comprising acquiring image data of the document; generating a document data file based on the image data, the document data file comprising a exemplar table and a block table; and appending the document data file to the document.

Abstract: A method for matching an original document image with a copy image is disclosed. The original document image is defined as an ensemble of blocks, each of the blocks having neighboring blocks. A mask is formed for each of the blocks by dilating foreground pixels included in the block. A best match is searched in the copy image, for each of the blocks, using a search window, by correlating pixels in the mask with pixels in a corresponding portion in the copy image. Each of the best matches has a matching score. Each of the blocks is indicated as “unmatched” when the corresponding matching score is less than a matching threshold. A displacement vector is computed for each of the matched blocks.

Abstract: Systems and methods are provided for automatically determining the font of text in a captured document image. Sequences of turns (left, right, straight) around the boundaries of connected components of black pixels in the captured document image are determined. The probabilities of the sequences of turns have come from a particular font within a library of known fonts can be determined using training set statistics. Using these probabilities, the most probable source font is selected.