Abstract: What is provided herein is a method for automatically selecting a subset of pages from a multi-page document for image processing wherein each selected page is substantially different from all other pages according to certain features of interest and wherein the combined content of the selected pages approximately represents the content in the entire document. Selected pages are clustered wherein each page is represented by a feature vector meaningfully related to the task to be performed. A matrix of feature vectors is analyzed. Basis vectors are extracted from the matrix using rank-reduction techniques. Clustering is performed by subspace projection of page features onto the basis vectors with each page being assigned to a cluster to which that page maximally projects. Representative pages are selected from each cluster. The representative pages can then be used as input to a secondary process.

Abstract: What is disclosed is a novel system and method for encoding/decoding data in a cover contone image via halftone dot orientation modulation. Arrays of halftone threshold values are used to determine a desired orientation, e.g. 0/90°+/?45° for a given single data value of the original message to be embedded. Message data is embedded as a function of halftone dot orientation. Detection modeling of the print-scan process enables the determination of dot orientation from the image scan via statistically motivated image moments. A probabilistic model of the print-scan channel conditions received moments on input orientation. Density values of the received moments are used to determine dot orientation for each halftone cell. The embedded data is retrieved based on the determined orientations. The present method is applicable to areas of data embedding, document security, and the like.

Abstract: This disclosure provides methods, systems and apparatus for jointly optimizing node locations and corresponding output value of a color look-up-table (LUT) associated with an imaging device. According to one exemplary method, initially a set of LUT node locations are generated by solving a first optimization problem and subsequently, a set of LUT node values are generated by solving a second optimization problem.

Abstract: A system and method for resizing a digitally represented color image are presented. A color image with pixels defined by luminance and at least one chrominance value is received. For each pixel of the color image, a luminance spatial variation and respective chrominance spatial variations in the respective neighborhood of the each pixel are computed. The luminance spatial variation and the respective chrominance spatial variations are combined to produce a respective importance value for each pixel. Selected pixels are identified based upon their respective importance values and are removed by seam carving of the color image. The seam carving identifies seams of pixels based upon the respective importance values of pixels within the seams of pixels to create a resized color image. The resized color image is produced to an image output device.

Abstract: What is disclosed is a novel system and method for encoding/decoding data in a cover contone image via halftone dot orientation modulation. Arrays of halftone threshold values are used to determine a desired orientation, e.g. 0/90°+/?45° for a given single data value of the original message to be embedded. Message data is embedded as a function of halftone dot orientation. Detection modeling of the print-scan process enables the determination of dot orientation from the image scan via statistically motivated image moments. A probabilistic model of the print-scan channel conditions received moments on input orientation. Density values of the received moments are used to determine dot orientation for each halftone cell. The embedded data is retrieved based on the determined orientations. The present method is applicable to areas of data embedding, document security, and the like.

Abstract: In accordance with the disclosure, a method is provided for processing color images for rendering on a color image. The method comprises receiving a plurality of device color separations for an image intended for rendering on a color image device; forming at least one intermediate image by interleaving pixels from at least two of the device color separations, compressing the at least one intermediate image in a compression module; decompressing the at least one intermediate image in a decompression module; processing the at least one decompressed intermediate image through a multidimensional calibration transform to output a calibrated device color separation; and, the device color separations include at least three colors.

Abstract: This disclosure provides methods, apparatus and systems for performing image processing regression for approximating multidimensional color transformation. According to an exemplary method, a shaping matrix is selected to minimize a cost function associated with a local linear regression representation of the color transformation. In addition, an alternating least squares algorithm is utilized to jointly optimize regression and shaping parameters.

Abstract: A system resizes content within a document that includes a document segmenter that receives a document that contains content. The document segmenter analyzes the content within the document and segments the content into a plurality of object types. An object priority applicator determines a class value associated with each object type. A location scaler identifies a datum point for each object type within the document, wherein each datum point maintains a relative location to one another regardless of document resizing. An object sizing component resizes each object based at least in part upon the class value.

Abstract: What is disclosed is a resizing method that utilizes segmentation information to classify objects found within a document and then selects the most appropriate resizing technique for each identified object. The present method employs readily available document parsers to reliably extract objects. e.g. text, background, images, graphics, etc., which compose the document. Information obtained from a document parser is utilized to identify the document components for classification. The extracted objects are then classified according to their object type. Each of classified objects are then resized using a resizing technique having been pre-selected for the object type based on their respective abilities to resize certain types of document content over other resizing techniques. The present method advantageously extends smart or content-based scaling and is especially useful for N-up or variable-information printing.

Abstract: A method and system for automatically determining an optimal re-training interval for a fault diagnoser based on online monitoring of the performance of a classifier. The classifier generates a soft measure of membership in association with a class based on a training data. The output of the classifier can be utilized to assign a label to new data and then the members associated with each class can be clustered into one or more core members and potential outliers. A statistical measure can be utilized to determine if the distribution of the outliers is sufficiently different than the core members after enough outliers have been accumulated. If the outliers are different with respect to the core members, then the diagnoser can be re-trained; otherwise, the output of the classifier can be fed to the fault diagnoser.

Abstract: An image digest based search approach allows images within an image repository related to a query image to be located despite cropping, rotating, localized changes in image content, compression formats and/or an unlimited variety of other distortions. In particular, the approach allows potential distortion types to be characterized and to be fitted to an exponential family of equations matched to a Bregman distance. Image digests matched to the identified distortion types may then be generated for stored images using the matched Bregman distances, thereby allowing searches to be conducted of the image repository that explicitly account for the statistical nature of distortions on the image. Processing associated with characterizing image noise, generating matched Bregman distances, and generating image digests for images within an image repository based on a wide range of distortion types and processing parameters may be performed offline and stored for later use, thereby improving search response times.

Abstract: Images within an image repository related to a selected image may be located despite cropping, rotating, and/or the application of a variety of other distortions to either the selected image and/or images in the image repository. Described exemplary approaches may use image digests produced using a multi-step process. In a first step, a discrete Fourier transform may be applied to produce an M×N frequency-based image matrix from an M×N image matrix containing elements that represent spatial image pixel values. In subsequent steps, matrix approximations may be applied to reduce the M×N frequency-based image matrix and to produce an image digest that reflects the content of the image. Further, an approach is described for generating a search threshold value that may be used to determine whether images digests associated with images in a repository are sufficiently similar to a search digest to be returned in a search result.

Abstract: What is disclosed is a system and method for encoding and decoding data in a color barcode pattern using dot orientation and color separability. The spectral (wavelength) characteristics of the CMY colorants, commonly used in digital printing, and those of RGB sensors are exploited to achieve high capacity data embedding rates in color barcodes. The present method embeds independent data in two different printer colorant channels using dot orientation modulation. In the print end, dots of two colorants occupy the same spatial region. At the detector end, by using the complementary sensor channels to estimate the colorant channels, data is recovered in each colorant channel. The method approximately doubles the capacity of encoding methods based upon a single colorant channel and enables embedding rates which match or exceed that of other hardcopy barcodes known in the arts. The method is robust against inter-separation misregistration with a small symbol error rate.

Abstract: What is disclosed is a system and method for encoding and decoding data in a color barcode pattern using dot orientation and color separability. The spectral (wavelength) characteristics of the CMY colorants, commonly used in digital printing, and those of RGB sensors are exploited to achieve high capacity data embedding rates in color barcodes. The present method embeds independent data in two different printer colorant channels using dot orientation modulation. In the print end, dots of two colorants occupy the same spatial region. At the detector end, by using the complementary sensor channels to estimate the colorant channels, data is recovered in each colorant channel. The method approximately doubles the capacity of encoding methods based upon a single colorant channel and enables embedding rates which match or exceed that of other hardcopy barcodes known in the arts. The method is robust against inter-separation misregistration with a small symbol error rate.

Abstract: What is disclosed is a novel system and method for performing spatial gamut mapping on a received input color image having a plurality of pixels. A standard gamut-mapping algorithm is applied to the input color image to produce a gamut-mapped color image. A difference is computed between a selected channel of the input color image and the gamut-mapped image to produce a difference image. A local measure of complexity is derived for a given pixel in the difference image. One or more parameter values of a spatial bilateral filter are obtained from a lookup table based on the computed local measure of complexity. The spatial bilateral filter is applied, using the obtained parameter values, to the current pixel of the difference image to produce a modified pixel in a modified difference image. Thereafter, a modified gamut-mapped color image is obtained from the modified difference image and the gamut-mapped color image.

Abstract: A method and system is disclosed for characterizing a color scanner comprising generating a halftone-independent target of color patches, printing the target on a color hardcopy device, measuring the target to obtain device-independent color values, scanning the target to obtain scanner color values, and building a scanner profile that relates scanned color values to device-independent color values.

Abstract: This disclosure provides methods, apparatus and systems for performing image processing regression for approximating multidimensional color transformation. According to an exemplary method, a shaping matrix is selected to minimize a cost function associated with a local linear regression representation of the color transformation.

Abstract: A dimensionality reduction method and system for efficient color transform compression is disclosed. A multi-dimensional color transform with an n-dimensional input color space can be received. A projection operator can be derived and applied to the n-dimensional input color space to form a k-dimensional input color space. A functional approximation can be designed to the n-dimensional input color space and can be evaluated on the k-dimensional input color space to form an m-dimensional output color space. The projection operator and the approximation function can be combined to form a compressed transform by mapping the n-dimensional input color space to m-dimensional output color space. Such an approach provides a significant reduction in size of the color profile with respect to storage and speeds-up real-time computation.

Abstract: What is disclosed is a system and method for performing a background deletion that exploits both local and global context to remove background and other white space between objects with the aim of retaining structural relationships between objects in the document. A document image is received and seams are carved through the image. Seams composed of uniform background pixels are identified. Adjacent seams containing background pixels are collected into groups of seams. The background seam groups are classified according to their widths. A target number of seams to be removed for each background seam group is then determined based on the classification. Seam groups which are wider will have at least the same or a greater target number of seams to be deleted therefrom than will seam groups of narrower widths. The document image is then resized by deleting seams from the seam groups based on the assigned target number.

Abstract: A method automatically determines a workflow for a print job via analysis of PDF documents is disclosed. A job synopsis comprising hashed information of a historical print job's document content along with a PDF document-level and object-level metadata and information about workflow nodes and parameters can be stored in a database. The job synopsis of a new incoming print job can then be compared to the historical print job synopses database. If the new print job matches the historical print job within a certain predefined similarity limit, then workflow and parameter information associated with the historical job can be utilized to augment an initial workflow for the incoming print job.