Abstract: Methods, and apparatus for performing methods, for classifying an image. Methods include determining a corresponding set of metrics for each region of two or more regions of a pattern of regions of an image, and classifying the image in response to at least the corresponding set of metrics for each of the two or more regions of the pattern of regions.

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: A forensic verification system (700) extracts a print signature via print signature extractor 710 from the boundary of a halftone contained in an image. The system (700) compares the print signature to a reference signature stored in a registry via comparator 720 to determine differences between the print signature and the reference signature. The system 700 performs a forensic-level statistical image analysis via forensic analyzer 730 on the print signature and the reference signature based on the comparison to authenticate the printed media.

Abstract: A forensic verification system (1100) extracts a print signature via a print signature extractor (1110) from an interior of a halftone contained in an image. The system (1100) utilizes a comparator (1120) 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 (1100) utilizes a forensic analyzer (1130) to perform a forensic analysis on the signatures based on the comparison to authenticate the image.

Abstract: A parallel test payload includes a bit sequence configured to be segmented into a plurality of sub-sequences having variable bit length carriers. Respective carriers are represented uniformly in each one of the plurality of sub-sequences.

Abstract: Techniques pertaining to printing a document are disclosed. A computer server may receive decoded document metadata and locate a document in a document repository using the document metadata. The server may determine whether the document metadata is indicative of a most recent version of the document and, if not, retrieve the most recent version of the document. The server may also create a tag for the retrieved most recent version of the document comprised of up to date document metadata in which the tag data is embedded in a graphic that is merged with the most recent version of the document. The server may create a print job for the most recent version of the document and send the print job to a network enabled printer over a network connection.

Abstract: In one example, a first directive is received at a system. The directive is to embed, into content selected via a printer application accessed at a network-connected printer, a network address. A carrier image that includes the network address in encoded form is generated. A second directive, to provide first content to the printer, is received via the application. The carrier image is merged into the first content. After the merging, the merged first content is sent to the printer for printing.

Abstract: Methods and systems are provided for tracing the source of a printed document. A method may include receiving a print job for printing a page having page content, generating a log of the print job, encoding the log using a mule image to produce a data-bearing halftone image, merging the data-bearing halftone image with the page content, and printing the merged data-bearing halftone image and page content to produce a printed document.

Abstract: Examples disclosed herein relate to compressing an image by resizing an image and compressing the resized image based on frequency content. A processor may resize an image to a target size if the pixel area of the image is greater than the sum of the target pixel area plus a resizing tolerance. The processor may compress the image using a first data removal rule for a portion of the image of a first frequency range and using a second data removal rule for a portion of the image of a second frequency range.

Abstract: An example provides a system and method of robust alignment and payload recovery for data-bearing images. The method includes digitizing a printed version of a stegatone, computing the transformation parameters of the stegatone, and processing individual local regions of the stegatone to determine local transformation parameters. The method also includes performing an alignment evaluation to compute a metric value that represents the quality of a local alignment between a reference halftone and the stegatone. Further, the method includes selecting alignment parameters based on optimization of the metric value, mapping the shift of clustered-dots in each cell in comparison to the reference halftone, and recovering the payload by decoding the stegatone.

Abstract: A method and apparatus for removing blur in an image is disclosed. The blur in the image is caused by relative motion between the imaging device and the object being imaged. A set of differences between the pixel values in the image is calculated. The set of differences in pixel values are divided into two groups, wherein the first group of differences in pixel values corresponds to differences in pixel values due to noise, and the second group of differences in pixel values corresponds to differences in pixel values due to noise and motion. An estimate of the motion blur is determined using the second group of differences in pixel values. The estimate of the blur is then used to remove the blur from an image.

Abstract: A system for creating a data-bearing image can include a reference image generator configured to apply a clustered-dot halftone screen to a continuous-tone image. The resulting reference halftone image includes carrier cells in which a pixel cluster can be shifted to at least two shift positions in the carrier cell. The system also includes a payload encoder configured to segment the data payload and encode data segments into one of the carrier cells by shifting the cluster to one of the shift positions. The system also includes an output device configured to output the resulting data-bearing halftone image.

Abstract: Candidate redeye areas (24) are determined in an input image (20). In this process, a respective set of one or more redeye metric values (28) is associated with each of the candidate redeye areas (24). Candidate face areas (30) are ascertained in the input image (20). In this process, a respective set of one or more face metric values (34) is associated with each of the candidate face areas (30). A respective joint metric vector (78) is assigned to each of the candidate redeye areas (24). The joint metric vector (78) includes metric values that are derived from the respective set of redeye metric values (28) and the set of face metric values (34) associated with a selected one of the candidate face areas (30). Each of one or more of the candidate redeye areas (24) is classified as either a redeye artifact or a non-redeye artifact based on the respective joint metric vector (78) assigned to the candidate redeye area (24).

Abstract: A VDP workflow system and method are disclosed. The system includes an image memory to store a photograph image. The system also includes a VDP document tool to access the photograph image from the image memory and to generate a VDP document comprising the photograph image. The system further includes a red-eye removal tool to process the VDP document to discover red-eye artifacts and to remove the red-eye artifacts from the photograph image on the VDP document based on a programmable red-eye sensitivity value.

Abstract: An example provides a system and method of robust alignment and payload recovery for data-bearing images. The method includes digitizing a printed version of a stegatone, computing the transformation parameters of the stegatone, and processing individual local regions of the stegatone to determine local transformation parameters. The method also includes performing an alignment evaluation to compute a metric value that represents the quality of a local alignment between a reference halftone and the stegatone. Further, the method includes selecting alignment parameters based on optimization of the metric value, mapping the shift of clustered-dots in each cell in comparison to the reference halftone, and recovering the payload by decoding the stegatone.

Abstract: A blur resistant barcode is disclosed. The blur resistant barcode comprise a plurality of parallel lines and spaces where information is encoded in the barcode by variations in the thicknesses of the plurality of parallel lines and by variations in the spacing between the plurality of parallel lines. The blur resistant barcode has at least one blur resistant feature that has a thickness in an axis of motion greater than a maximum thickness of any one of the plurality of parallel lines. The axis of motion is perpendicular to the plurality of parallel lines.

Abstract: A parallel test payload includes a bit sequence configured to be segmented into a plurality of sub-sequences having variable bit length carriers. Respective carriers are represented uniformly in each one of the plurality of sub-sequences.

Abstract: A machine-implemented method of processing an input image includes receiving user input that manually identifies a location in the input image that corresponds to a potential redeye artifact. A set of detected redeye artifacts in the input image is received. One of the detected redeye artifacts that is closest to the manually identified location is identified. The identified detected redeye artifact is stored in a list of redeye artifacts that are identified with manual assistance if the identified detected redeye artifact is within a threshold distance from the manually identified location.

Abstract: A payload recovery system includes a reference halftone image of a data-bearing halftone image and a reference map of the data-bearing halftone image. The system further includes a cell alignment system for receiving a scanned image of a hard copy of the data-bearing halftone image and for generating an aligned scan of the scanned image using the reference halftone image and the reference map. A raw payload recovery system determines possible shift positions of each carrier cell of the aligned scan using a shift rule and the reference map; and a reconstructed data-bearing halftone image is generated by the raw payload recovery system using the possible shift positions and the reference halftone. The system also includes a recovered raw payload generated by the raw payload recovery system using the shift rule and the reference map.

Abstract: A blur resistant barcode is disclosed. The blur resistant barcode comprise a plurality of parallel lines and spaces where information is encoded in the barcode by variations in the thicknesses of the plurality of parallel lines and by variations in the spacing between the plurality of parallel lines. The blur resistant barcode has at least one blur resistant feature that has a thickness in an axis of motion greater than a maximum thickness of any one of the plurality of parallel lines. The axis of motion is perpendicular to the plurality of parallel lines.