Abstract: Systems and methods of face and skin sensitive image enhancement are disclosed. In one aspect, a face map that includes for each pixel of an input image a respective face probability value indicating a degree to which the pixel corresponds to a human face is calculated. A skin map that includes for each pixel of the input image a respective skin probability value indicating a degree to which the pixel corresponds to human skin is ascertained. The input image is enhanced with an enhancement level that varies pixel-by-pixel in accordance with the respective face probability values and the respective skin probability values. In another aspect, a facial content measurement value indicating a degree to which an input image contains human face content is ascertained. A tone-correction process is tuned in accordance with the facial content measurement value. The input image is enhanced in accordance with the tuned tone-correction process.

Abstract: Image forming devices, hard imaging methods, and methods of determining a transfer function are described.

Abstract: A neural network is trained with input data. The neural network is used to rescale the input data. Errors for the rescaled values are determined, and neighborhoods of the errors are used adjust connection weights of the neural network.

Abstract: A neural network is trained and used to reduce artifacts in spatial domain representations of images that were compressed by a transform method and then decompressed. For example, the neural network can be trained and used to reduce artifacts such as blocking and ringing artifacts in JPEG images.

Abstract: Noise level estimation includes examining color correlation in a digital image.

Abstract: Processing of at least one digital image includes performing first and second separable block transforms in first and second directions; modifying results of the second block transforms; and performing first and second separable inverse block transforms in the first and second directions on the modified results. Transform coefficients are re-used while performing at least one the transforms. The processing can be performed on 2-D signals such as still images and 3-D signals such as video.

Abstract: A system and method of removing background noise from a digital image of a scanned document is described. The system and method is a reversible background noise removal technique that allows a user to select whether background noise is removed or not. In addition, since the present invention divides the background noise removal operations into a two phase process, the overall efficiency of the system and method are significantly improved.

Abstract: Methods, machines, and computer-readable media storing machine-readable instructions for processing video frames are described. In one aspect, a respective set of three-dimensional forward transform coefficients is computed for each of multiple positions of a three-dimensional blocking grid relative to an input video block comprising a selected set of video frames. The sets of three-dimensional forward transform coefficients are processed. A respective three-dimensional inverse transform is computed from each set of processed forward transform coefficients. An output video block is generated based on the computed three-dimensional inverse transforms.

Abstract: Methods, machines, and computer-readable media for processing an input image with a bi-selective filter in a transform domain are described. In one aspect, a forward transform of an input image is computed. A bi-selective filter smoothes image regions with low magnitude coefficients and sharpens image regions with high magnitude coefficients. An output image is generated from the filtered forward transform.

Abstract: Format processing systems for converting the format of a document are disclosed. In this regard, a representative document processing system includes a file conversion system configured to receive information corresponding to a first document as well as receive information corresponding to a second format to which the information corresponding to the first document is to be converted. Additionally, the file conversion system is configured to retrieve information corresponding to a set of format rules, the set of format rules corresponding to the second format. The file conversion system converts the information corresponding to the first document to image data having at least one object group. Thereafter, the file conversion system converts the image data to converted data representative of the first document and exhibiting the second format. Methods and other systems also are provided.

Abstract: A method for a digital printing press includes estimating a developer voltage by applying a developer voltage estimation model to measurements of state parameters of the digital printing press.

Abstract: A neural network is trained and used to reduce artifacts in spatial domain representations of images that were compressed by a transform method and then decompressed. For example, the neural network can be trained and used to reduce artifacts such as blocking and ringing artifacts in JPEG images.

Abstract: A neural network is trained with input data. The neural network is used to rescale the input data. Errors for the rescaled values are determined, and neighborhoods of the errors are used adjust connection weights of the neural network.

Abstract: Image processing systems for converting image data corresponding to a document, where the image data exhibits a first format, are disclosed. In this regard, a representative image processing system includes a file conversion system configured to receive information corresponding to the image data as well as information corresponding to a second format to which the image data is to be converted. Additionally, the file conversion system is configured to retrieve information corresponding to a set of format rules, where the set of format rules corresponds to the second format. Thereafter, the file conversion system converts the image data to converted data representative of image data and exhibiting the second format without rescanning, reanalyzing, or reprocessing the document. Methods and other systems also are provided.

Abstract: Format processing systems for converting the format of a document are disclosed. In this regard, a representative document processing system includes a file conversion system configured to receive information corresponding to a first document as well as receive information corresponding to a second format to which the information corresponding to the first document is to be converted. Additionally, the file conversion system is configured to retrieve information corresponding to a set of format rules, the set of format rules corresponding to the second format. The file conversion system converts the information corresponding to the first document to image data having at least one object group. Thereafter, the file conversion system converts the image data to converted data representative of the first document and exhibiting the second format. Methods and other systems also are provided.

Abstract: The present invention generally provides methods and systems for printing. A statistical learning system is used to determine dot gain.

Abstract: Image processing systems for converting image data corresponding to a document, where the image data exhibits a first format, are disclosed. In this regard, a representative image processing system includes a file conversion system configured to receive information corresponding to the image data as well as information corresponding to a second format to which the image data is to be converted. Additionally, the file conversion system is configured to retrieve information corresponding to a set of format rules, where the set of format rules corresponds to the second format. Thereafter, the file conversion system converts the image data to converted data representative of image data and exhibiting the second format without rescanning, reanalyzing, or reprocessing the document. Methods and other systems also are provided.

Abstract: A method of quickly and automatically comparing a new document to a large number of previously seen documents and identifying the document type. First, provide a plurality of document type distributions, each document type distribution describes layout characteristics of an independent document type and may include a plurality of data points. Each document type distribution includes data derived from at least one basis document signature which may include data defining pixels of a low-resolution image of the independent basis document resolved to between 1 and 75 dots per inch or may include document segmentation data derived from the independent basis document. Next provide a new electronic document. Then create new document signature from the new electronic document. Next, distances between the new document signature and each of the plurality of document type distributions are calculated using an algorithm based on a Bayesian framework for a Gaussian distribution.

Abstract: A method of automatically extracting metadata from a document. The method of the invention provides a computer readable document that includes blocks comprised of words, an authority list that includes common uses of a set of words, and a neural network trained to extract metadata from groupings of data called compounds. Compounds are created with one compound describing each of the blocks. Each compound includes the words making up the block, descriptive information about the blocks, and authority information associated with some of the words. The descriptive information may include such items as bounding box information, describing the size and position of the block, and font information, describing the size and type of font the words of the block use. The authority information is located by comparing each the words from the block to the authority list.

Abstract: A method of automatically generating a software installation package. The method operates on an application program that has been ported to and debugged on a target computer system. A manifest is automatically generated, listing all application program files that must be installed on the target computer system. Then the method automatically determines which resources, in particular shared libraries, are needed by any of the listed files. Then the installation package is generated by combining the listed files, the needed resources, and any related installation materials. The needed resources are determined by generating a dependency list, comparing it with existing software installation packages, and identifying any packages that contain needed shared libraries as needed resources.