Abstract: In various embodiments, methods, systems, and computer program products for capturing and processing digital images captured by a mobile device are disclosed. The claimed algorithms are specifically configured to perform and facilitate loan application processing by capturing an image of a document using a mobile device, and analyzing the image (optionally in conjunction with additional data that may also be captured, determined, or otherwise provided to the loan application process) to determine loan-relevant information. Select loan-relevant information may be extracted, compiled, and/or analyzed to facilitate processing of the loan application. Feedback may be provided to facilitate facile application processing, e.g. by ensuring all requisite information is submitted with the loan application. Image capture and document detection are preferably performed using the mobile device, while all other functions may be performed using the mobile device, a remote server, or some combination thereof.

Abstract: A system is described for detecting the presence of non-uniformity patterns and providing output indicative of a severity of each type of non-uniformity pattern. The system includes a computerized rating tool that assists a user in efficiently and consistently assigning expert ratings (i.e., labels) to a large collection of training images representing samples of a given product. In addition, the rating software develops a model that allows a computerized inspection system to detect the presence of non-uniformity patterns in a manufactured web material in real time and provide output indicative of a severity level of each pattern on a continuous scale. The system also includes algorithmic and hardware approaches to significantly that increase the throughput of the inspection system.

Abstract: A comprehensive system to enhance the aesthetic quality of the photographs captured by mobile consumers provides on-site composition and aesthetics feedback through retrieved examples. Composition feedback is qualitative in nature and responds by retrieving highly aesthetic exemplar images from the corpus which are similar in content and composition to the snapshot. Color combination feedback provides confidence on the snapshot to contain good color combinations. Overall aesthetics feedback predicts the aesthetic ratings for both color and monochromatic images. An algorithm is used to provide ratings for color images, while new features and a new model are developed to treat monochromatic images. This system was designed keeping the next generation photography needs in mind and is the first of its kind. The feedback rendered is guiding and intuitive in nature. It is computed in situ while requiring minimal input from the user.

Abstract: A system identifies an image and determines whether the image contains inappropriate content based on first data associated with the image, second data associated with a document that contains the image or refers to the image, and/or third data associated with a group of documents with which the image is associated.

Abstract: A Mixed Media Reality (MMR) system and associated techniques are disclosed. The MMR system provides mechanisms for forming a mixed media document that includes media of at least two types (e.g., printed paper as a first medium and digital content and/or web link as a second medium). The present invention provides a system, method, and computer program product for creating an ad hoc association between users. Captured digital images of paper documents or portions associated with a user are received. Document recognition features are extracted from the captured digital image. An ad hoc association is created between the user and another user associated with an existing document recognition feature similar to the extracted document recognition features.

Abstract: An apparatus for verifying an inspection result includes an inspection result obtaining unit to obtain inspection result indicating defect amount and defect position in a scanned image, from an inspection result of defect judgment of the scanned image with respect to an inspection reference image, the defect judgment being performed through dividing at least one of the scanned image and the inspection reference image and conducting position matching of the scanned image and inspection reference image; and a verification unit to count defect amount occurring to the scanned image, to determine whether a defect pattern occurring to the scanned image matches a pre-set condition corresponding to a false detection condition causable by failure of the position matching, and to determine that defect occurring to the scanned image is a false detection when the counted defect amount is a threshold or more, and the defect pattern matches the false detection condition.

Abstract: An image forming system includes an image forming unit configured to output image data onto a recording medium; a first conveying unit configured to convey the medium; a reading unit configured to read an image from the medium; a defect determining unit configured to determine whether the read image has a defect; a device connection determining unit configured to determine whether a discharge device is directly connected to an image inspection device at the downstream side or is connected to the image inspection device via another device at the downstream side; a second conveying unit configured to convey the medium to the discharge device on a longer conveying path, when the discharge device is directly connected to the image inspection device; a defective discharge tray to which the medium having a defective image is discharged; and a normal discharge tray to which the medium having a non-defective image is discharged.

Abstract: A method of recognizing and generating a structure of a table included in an image is provided. The method includes extracting lines forming the table from among connection components forming an image, determining line intersections by using crossing functions matched with the lines, determining one of a plurality of crossing models identified based on a plurality of crossing shapes, in correspondence with each of the line intersections, and generating data about the table, which includes at least one cell determined using the determined crossing model.

Abstract: Methods, systems, and devices are described for adjudicating votes made on voter-marked paper ballots. Voter-marked paper ballots may be scanned to obtain optical image data of the voter-marked paper ballots. The optical image may be analyzed to determine the votes contained in the ballot for tabulation purposes. One or more votes on the ballot may be identified as requiring adjudication by an election official. Adjudication information, according to various embodiments, is appended to the optical images of the voter-marked paper ballots such that the image of the ballot and the image of the adjudication information may be viewed in an optical image. The optical image may be stored in a file format that allows the ballot image and the appended adjudication information to be viewed using readily available image viewers.

Abstract: An image inspection system, an image inspection method, and an image inspection program acquires a read image obtained by reading an output image, generates an inspection image for inspecting the read image based on data of a to-be-output image, acquires an inspection result including a determination whether the read image is defective, based on a difference between the inspection image and the read image, acquires coloring-material usage data indicating extent of coloring-material usage in the output image, the coloring-material usage data being read when the read image is generated, generates coloring-material usage defect rate data indicating a defect rate in association with coloring-material usage, based on the inspection result and the coloring-material usage data, and obtains coloring-material usage of the to-be-output image, based on data of pixels forming the to-be-output image.

Abstract: An optical image of a source document is captured. Two or more source document image test regions are then defined/determined. An optical image scan is performed on each source document image test region to determine if there are identifiable alpha-numeric characters or symbols present. If one or more of the source document image test regions are determined not to contain identifiable alpha-numeric characters, the captured optical image of the source document is determined to be of insufficient quality to identify and extract individual characters and symbols and it is recommended that optical images of source documents determined to be of insufficient quality to identify and extract individual characters and symbols be re-captured using an image capture device.

Abstract: In various embodiments, methods, systems, and computer program products for processing digital images captured by a mobile device are disclosed. Myriad features enable and/or facilitate processing of such digital images using a mobile device that would otherwise be technically impossible or impractical, and furthermore address unique challenges presented by images captured using a camera rather than a traditional flat-bed scanner, paper-feed scanner, or multifunction peripheral. Particularly advantageous features include robustly detecting edges of one or more documents depicted in the digital image data, and defining/locating document pages at least partially on this basis.

Abstract: A system and associated methods are provided for the evaluation of printing systems. Results may be expressed as a set of simple-to-understand alphabetic grades (e.g., A, B, C, D, F). These grades reflect the visual acceptability of prints of the image evaluation document produced by the printing system. Capabilities are provided for query and reporting of data across printing systems and over time for various attributes and factors.

Abstract: An inspection apparatus includes a receiving unit configured to receive preprint image data preprinted on a sheet and document image data printed on the preprinted sheet, a composing unit configured to compose reference image data from the received preprint image data and the received document image data, a reading unit configured to read the sheet on which both the preprint image data and the document image data has been printed, to obtain read image data, a processing unit configured to carry out predetermined image process on a first and second area corresponding to the document image data and the preprint image data of the read image data, to generate inspection image data, and an inspecting unit configured to inspect the sheet on which both the preprint image data and the document image data has been printed, by comparing the inspection image data with the reference image data.

Abstract: In one embodiment, a method includes performing optical character recognition (OCR) on an image of a financial document and at least one of: (a) correct OCR errors in the financial document using at least one of textual information from a complementary document and predefined business rules; (b) normalize data from the complementary document using at least one of textual information from the financial document and the predefined business rules; and (c) normalize data from the financial document using at least one of textual information from the complementary document and the predefined business rules. Exemplary systems and computer program products are also disclosed.

Abstract: The invention relates to a security element applied onto printing substrates (bank-notes, securities, product packagings, identity cards/labels or other similar documents) by printing, comprising a unique identifier as primary information visible to the naked eye and secondary information protecting against copying non-visible to the naked eye. The unique identifier is typically a point code. Said secondary information is represented by a structure with the largest dimension of 2 to 40 microns, and due to printing distortions arising when the security element is applied onto a printing substrate, said secondary information is non-reconstructable from the print of the security element and a statistically analyzable inherent feature is associated to it. The invention also relates to a printed matter with such an inventive security element and to a method to check authenticity of a printed matter with the inventive security element in visible light (380-750 nm).

Abstract: There is provided an object verification device capable of detecting a fraudulent entry in an arbitrary area of an object without requiring a certification mark applied by a special material. An object verification device that verifies authenticity of an object includes: an image acquisition section that acquires an image of the object; a verification area identification section that identifies a verification area of the object for which authenticity is verified; an entry part detection section that detects a plurality of entry parts within the verification area in the image; and a verification section that verifies authenticity of the object by mutually comparing the plurality of entry parts in the image.

Abstract: A printing apparatus, including a user input unit which receives a first user command to initiate a printing operation, a display unit which displays information relating to the printing operation, a printing unit which performs printing with respect to printing data, and a controller which controls the display unit to display reference information of the printing data before the printing, and which controls the printing unit to perform the printing according to a second user command.

Abstract: A method for high-speed multi-color printing includes at least one high-resolution sensor array (23), wherein an output of the high-resolution sensor array is transmitted to a controller (19); at least one low-resolution sensor array (24); wherein the controller calculates a correction for stitch; wherein the controller, based on the calculated correction, adjusts a timing of image data provided to individual print elements comprising print stations (12) to aligned an output of the print elements; and wherein the low-resolution sensor array provides full page viewing.

Abstract: A method, apparatus, and computer program product, responsive to receiving a data from a computing device connected to the computer in a cloud computing system or data center, identifies a criteria associated with the computing device, responsive to identifying the criteria, determines whether the data is authorized for transmission to a storage in the cloud computing system or data center, and responsive to determining that the data is authorized for transmission to the storage, forwards the data to the storage.

Abstract: An image processing device includes an image acquiring section for acquiring images; a mount number setting section for setting a mount number for mounts; an image dividing section for dividing the acquired images into a predetermined number of groups based on accessory information of the images, with the number of groups being equal to the mount number; and an image arranging section for arranging images included in each group after division on each corresponding mount. The image dividing section divides the images into the groups so that the number of images included in each group is not more than the upper limit number of images capable of being arranged on the corresponding mount.

Abstract: In an example, a method for automated camera flat fielding and alignment may include determining a magnification of a camera relative to a first camera axis that is generally parallel to a first print media axis by evaluating first and second magnifications between transitions from a first color to a second color on a setup plot. The method may further include determining, by a processor, a rotation of the camera relative to the first camera axis such that the first magnification is approximately equal to the second magnification.

Abstract: Embodiments of a system and method for automatic creation of a multimedia presentation or highlight collection from a collection of candidate contents are generally described herein. In some embodiments, each one of a plurality of videos or images in the candidate contents are automatically evaluated for quality, content, metadata, and desirability based on user specified inclusion factors. Inclusion factors may be utilized to generate one or more scores for the candidate contents, which provide for automatic ranking of the candidate contents. Based on scores generated from the selected inclusion factor criteria a highlight collection of images is automatically generated. The highlight collection can be included in a multimedia presentation, in the form of a memory book, slideshow, or digital narrative, and can be automatically generated from the plurality of videos or images.

Abstract: Methods for selecting metrics for substrate classification, and apparatus to perform such methods. The methods include determining a value of a metric from an image of a substrate sample for each substrate sample of a plurality of substrate samples, wherein the metric is indicative of a surface texture of each substrate sample and iteratively assigning substrate samples of the plurality of substrate samples to an aggregate of a particular number of aggregates in response to a value of the metric for each substrate sample until a convergence of clustering is deemed achieved, then determining an indication of cluster tightness of the particular number of aggregates. The methods further include selecting or ignoring the metric for substrate classification in response to the indication of cluster tightness of the particular number of aggregates.

Abstract: A document includes an authenticity-indicating feature configured such that a reproduction of the document renders the printed feature visually distinctive from an original rendering of the document. The printed feature includes printed elements arranged on the substrate in a latent image region and a background region. The printed elements in the latent image region include a plurality of regularly spaced printed shapes arranged with a spatial frequency less than about 50 per inch. The printed elements are printed with a carbon-based ink, toner, or dye, and separated from one another by contrasting regions that do not include the carbon-based ink, toner, or dye. The printed elements in the background region are at least partially surrounded by the latent image region such that, in the original rendering of the document, the plurality of regularly spaced printed shapes is not readily distinguishable from the background.

Abstract: When defects occur in four places of a print data region of a paper P1 as illustrated in FIG. 3A, four code images are formed on an interleaving paper P2 as illustrated in FIG. 3B, more specifically, four code images are formed on the interleaving paper P2 such that the positions of plural defect occurrence portions in the paper P1 are aligned with the positions of plural code images formed in the interleaving paper P2, respectively, and the sizes of the code images are made to be different depending on the defective degree of the defects occurring at the defect occurrence portions of the paper P1, specifically, the larger the defective degree is, the larger the code image is.

Abstract: The technology of the present disclosure includes computer-implemented methods, computer program products, and systems to filter images before transmitting to a system for optical character recognition (“OCR”). A user computing device obtains a first image of the card from the digital scan of a physical card and analyzes features of the first image, the analysis being sufficient to determine if the first image is likely to be usable by an OCR algorithm. If the user computing device determines that the first image is likely to be usable, then the first image is transmitted to an OCR system associated with the OCR algorithm. Upon a determination that the first image is unlikely to be usable, a second image of the card from the digital scan of the physical card is analyzed. The optical character recognition system performs an optical character recognition algorithm on the filtered card.

Abstract: A method for detecting printing defects includes, with a physical computing system, creating a matched reference image from a digital image, colors of said matched reference image being closer matched to a scanned image of said digital image. The method further includes, with said physical computing system, determining a color difference between corresponding points on said matched reference image and said scanned image; and with said physical computing system, identifying points that have said color distance greater than a predefined threshold as potential defects.

Abstract: A forensic verification system (900) extracts a print signature via a print signature extractor (910) from a captured image of a printed halftone. The system (900) utilizes a comparator (920) to compare the print signature to a reference signature stored in a registry to determine differences between the print signature and the reference signature. The system (900) utilizes a forensic analyzer (930) to perform a forensic analysis on the signatures based on the comparison to authenticate the printed halftone.

Abstract: Systems, methods, and computer readable storage mediums are provided for photograph digitization through the use of video photography and computer vision technology in accordance with various embodiments. A number of video frames are received. Each video frame includes a respective image of a physical print (or a portion thereof). For at least some of the video frames, a rating value is assigned to image of the physical print (or portions thereof). The rating value is in accordance with rating criteria. A highest quality image of the physical print is selected from among the respective images. The selection based on at least the rating value of the selected image. The highest quality image is stored as a final digital representation of the physical print.

Abstract: An image inspection apparatus for inspecting an image output on a recording medium. The image inspection apparatus includes processing circuitry that obtains data of an output-target image used by an image forming apparatus to conduct an image forming operation, generates read data from the data of the output-target image, and generates an inspection reference image from the data of the output-target image. The apparatus also performs position alignment between the read image and the inspection reference image, conducts an inspection which determines a defect in the read image based on the difference of the aligned read image and the inspection reference image, and determines whether a position alignment defect exists in the read image based on the defect detected during inspection.

Abstract: Systems and methods for detecting tape on a document are provided. In one embodiment, a method includes capturing a first image of a document. The first image is captured while at least a portion of the document is subjected to a first electromagnetic radiation. The method includes capturing a second image of the document. The second image is captured while at least a portion of the document is subjected to a second electromagnetic radiation. The method also includes comparing the first image to the second image to determine whether tape is adhered to the document.

Abstract: A novel method and a supporting system for authenticating a photograph are provided. The method for authenticating a photograph generally comprising steps for authenticating a photograph with a certifying server, typically including downloading a picture-taking software, taking at least two digital photographs of a user, comparing the at least two photographs, generating a certified photograph, and providing a link to access the certified photograph.

Abstract: In various embodiments, methods, systems, and computer program products for processing digital images captured by a mobile device are disclosed. Myriad features enable and/or facilitate processing of such digital images using a mobile device that would otherwise be technically impossible or impractical, and furthermore address unique challenges presented by images captured using a camera rather than a traditional flat-bed scanner, paper-feed scanner, or multifunction peripheral. Particularly advantageous features include robustly detecting edges of one or more documents depicted in the digital image data, and defining/locating document pages at least partially on this basis.

Abstract: A system for capturing an image of a document includes an input tray (30) for holding documents (20); an input imaging device (40) that captures an image of a first document in the input tray; wherein the input tray image of the first document is captured as an area image; transmitting the captured input tray image of the first document to an image processor (100); and transporting the first document to an output tray.

Abstract: A document scanner (10) includes an input tray (30) for holding documents (20) and an input image capture device (40) for capturing images of the documents (20)in the input tray (30) prior to transporting the document for imaging; an output tray (150) for holding documents (20) after the documents (20) exit the scanner; an output image capture device (140) for capturing images of the output tray; an image processor for determining characteristics of the output tray or characteristic of the documents (20) before imaging and after the documents (20) exit the scanner; and scanner functions are modified based on the output tray characteristics or the document characteristics.

Abstract: A method of determining the velocity of relative displacement between a substrate and an image sensor, for example the velocity of displacement of a page relative to a scanner, involves imaging a reference pattern on the substrate, using the image sensor, while the relative displacement occurs between the substrate and the image sensor. The reference pattern includes plural crossing points marked at predetermined locations on the substrate, each crossing point formed of a first line portion crossing a second line portion. Locations in the image that correspond to the crossing points are compared to the predetermined locations on the substrate and the velocity of the relative displacement between the image sensor and the substrate is determined using relationships between the predetermined locations and the detected locations in the generated image.

Abstract: An image processing apparatus according to one aspect of the present disclosure includes a first image extraction portion and a first determination portion. The first image extraction portion is configured to extract, from image data, a plurality of linear images in each of which reference pixels each having a tone in a predetermined range are continuous so as to form a straight line. The first determination portion is configured to determine, when the plurality of linear images extracted by the first image extraction portion include linear images that are spaced by a uniform distance, the linear images that are spaced by the uniform distance, as ruled lines.

Abstract: An inspection apparatus, inspection system, inspection method, and inspection control program stored in a recording medium, each of which sets a reference point in a master image and a read image read from a printed image, which is to be used for detecting the positional shift between the read image and the master image, based on determination whether a pattern previously added to the printed image for detecting the positional shift is available or can be used to effectively detect the positional shift.

Abstract: An image inspection apparatus for checking an image printed on a recording medium includes: a reference pixel obtaining unit configured to generate a reference image and obtain a first pixel value from the reference image; a print pixel obtaining unit configured to extract an image printed area and obtain a second pixel value from the image; an offset processing unit configured to add a non-image-printed area; and an image checking unit configured to compute a difference between the first image pixel value and the second image pixel value and detect an error when the difference is higher than a predetermined threshold value, wherein the non-image-printed area contains a third pixel value that is different from the first pixel value or the second pixel value, and the image checking unit suspends a determination whether or not there is an error in the image printed area associated with the non-image-printed area.

Abstract: Automated inspection method for detecting a defect in a printed image, comprising processing a raster image, sending the raster image to a print process, printing a printed image corresponding to the raster image onto a medium, capturing a target image from at least a part of the printed image at a lower resolution than the printed image, at least in a medium moving direction, converting at least a part of the raster image to a reference image, and comparing the reference image to the target image.

Abstract: A printing apparatus that can process, as a single job, a plurality of records each including a plurality of pages determines whether error information is included in an inspection result acquired from an inspection apparatus, before terminating print processing of each record. Then, if a job control unit determines that the error information is included, the printing apparatus does not perform print processing for a record that follows a print processing completed record and displays a print instruction screen that includes record information generated from the inspection result on a display unit.

Abstract: In various embodiments, methods, systems, and computer program products for processing digital images captured by a mobile device are disclosed. Myriad features enable and/or facilitate processing of such digital images using a mobile device that would otherwise be technically impossible or impractical, and furthermore address unique challenges presented by images captured using a camera rather than a traditional flat-bed scanner, paper-feed scanner, or multifunction peripheral.

Abstract: In the method and device, electronic documents are created from a batch of physical documents of varying lengths. The batch comprises sub-batches of groups of multiple multi-page physical documents with separator sheets on each group. Each separator sheet is marked with a page count for any physical documents in its group. The batch is scanned-in and the resulting image pages are used to form the electronic documents. Specifically, the image pages are analyzed in sequence to identify document sheet image pages and separator sheet image pages. When a separator sheet image page is identified, the page count on that separator sheet image page is read and electronic document(s) is/are created from sequential set(s) of document sheet image pages, which follow the separator sheet image page and have the specific page count, until the next separator sheet image page is identified. This is repeated for all separator sheet image pages identified.

Abstract: An image processing device for detecting a large number of missing dots. The image processing device comprises a print data image acquisition unit that acquires a print data image; an inkjet printer unit that prints on the back of a check; a back CIS unit that scans the back of the printed check; a print area extraction unit that extracts a print area R from the scanned image of the back of the check as an extracted image; and a missing dot detection unit determines if there are missing dots based on the print data image and the extracted image extracted by the print area extraction unit.

Abstract: Disclosed is a method (160) for identifying potential tamper in a candidate document having content affected by noise. A candidate content value for each of a plurality of sub-regions of the candidate document and an original content value for each of a plurality of sub-regions of a corresponding original document are determined. The content values are desirably determined based on at least one characteristic of the content in the corresponding sub-region. The candidate content values (330) are associated with the corresponding original content values and a distribution of the candidate content values based on the corresponding original content values is determined. The method characterizes (340) the noise in the candidate document by determining an expected content value range based on the spread of a selected part of the distribution of candidate content values. The method can then identify (350) candidate content values outside the expected content value range as potential tamper.

Abstract: An image inspection apparatus for inspecting an image output on a recording medium by scanning the recording medium as a scanned image. The inspection apparatus having a display controller that controls display of a normal read image, which includes only permissible defects for each type of defect, in the normal image display area, and that controls display of an abnormal read image, which includes at least one impermissible defect for each type of defect, in the abnormal image area. The inspection apparatus also includes a defect permissible changing unit that receives a moving operation instruction, which moves the displayed image between the normal image display area and the abnormal image display area and that, in response to receiving the moving operation instruction, changes the permissible defect level of at least one type of defect.

Abstract: An image test apparatus acquires a result of determination on a defect in a read image obtained by reading an image formed and output on a recording medium, based on a difference between the read image and a test image, acquires a sheet type of a sheet from which the read image is read, calculates a stacked position of a sheet of a defective read image in which the defect is detected among sheets stacked on a discharge tray serving as a discharge destination of the sheet of the read image, on the discharge tray based on the result of the determination on the defect in the read image and based on the acquired sheet type, and controls an indicating unit, which indicates a height at predetermined intervals in a direction in which the sheets are stacked on the discharge tray, based on the calculated stacked position.

Abstract: A method responsive to receiving a data from a computing device connected to the computer in a cloud computing system or data center, identifies a criteria associated with the computing device, responsive to identifying the criteria, determines whether the data is authorized for transmission to a storage in the cloud computing system or data center, and responsive to determining that the data is authorized for transmission to the storage, forwards the data to the storage.

Abstract: Performing automatic inspection on the results of a print job that prints variable data, including multiple printed instances of a page containing variable graphics. The inspection is to detect printing defects on a printed instance. In one embodiment, the method includes dividing the page into multiple non-overlapping areas using a page division map. The non-overlapping areas include one or more static areas that include only static graphics and one or more areas that include variable graphics. The method includes capturing an image of the printed instance and, for each of the non-overlapping areas, retrieving an indication indicating whether or not the area includes any variable graphics, retrieving a rasterized image of an instant of the area from a memory location according to the indication, and comparing the rasterized image with the captured image of the area to detect any printing defects in the area of the printed instance.