Abstract: A system, method, and computer program product are provided for automatically segmenting input document images into regions of black text, white space, and image content. A set of scanned training documents representing the range of text and images to be processed is coarsely tagged to classify regions by content type. The training images are divided into bricks, parameters describing individual brick features are evaluated, and the bricks are classified according to the parameter values. A classification map that relates parameter values to classification codes describing content type is constructed by generating linear equations separating a parameter space into parameter regions along classification boundaries. After training, input documents are scanned and divided into bricks, and brick parameters are converted into an index into the classification map, to classify document regions by content.

Abstract: Systems and methods which provide color conversion using intelligent boundary point perturbation techniques are shown. Embodiments operate to initially select only boundary point indices for indexing data of an input color space to a color space transformation matrix representing the transformation between the input color space and an output color space. A boundary point perturbation process is applied to the initially selected boundary point indices to intelligently alter the boundary point index selections and thereby provide selection of boundary point indices having intelligent boundary point perturbation. Embodiments of the invention utilize an intelligent address generator to selectively apply constraints when indexing the input color space values to boundary points within a color look up table for transforming the input color space values to appropriate output color space values using the boundary point indices provided by the boundary point perturbation process.

Abstract: A system, method, and computer program product are provided for automatically segmenting input document images into regions of black text, white space, and image content. A set of scanned training documents representing the range of text and images to be processed is coarsely tagged to classify regions by content type. The training images are divided into bricks, parameters describing individual brick features are evaluated, and the bricks are classified according to the parameter values. A classification map that relates parameter values to classification codes describing content type is constructed by generating linear equations separating a parameter space into parameter regions along classification boundaries. After training, input documents are scanned and divided into bricks, and brick parameters are converted into an index into the classification map, to classify document regions by content.

Abstract: A system for processing images includes an image file subsystem providing a source signal representing an input image; a color transformation subsystem coupled to the image file subsystem and accepting as input the source signal and producing a target signal therefrom, and an image forming subsystem coupled to the color transformation subsystem and forming a physical manifestation of the input image in response to the target signal, the color transformation subsystem being configured to establish a memory “cube” area representative of possible source signals, to define a sub-cube portion of the memory area as representative of the source signal; to determine possible target signals corresponding to the sub-cube portion; and to determine the target signal responsive to the possible target signals. If interpolation is found to be accurate for a mini-cube portion of the sub-cube, truncation or interpolation are used to derive the target signal; otherwise, the target signal is determined directly.

Abstract: A system for processing images includes an image file subsystem providing a source signal representing an input image; a color transformation subsystem coupled to the image file subsystem and accepting as input the source signal and producing a target signal therefrom, and an image forming subsystem coupled to the color transformation subsystem and forming a physical manifestation of the input image in response to the target signal, the color transformation subsystem being configured to establish a memory "cube" area representative of possible source signals, to define a sub-cube portion of the memory area as representative of the source signal; to determine possible target signals corresponding to the sub-cube portion; and to determine the target signal responsive to the possible target signals. If interpolation is found to be accurate for a mini-cube portion of the sub-cube, truncation or interpolation are used to derive the target signal; otherwise, the target signal is determined directly.

Abstract: A system and process for digital printing divides an image area into segments, defines display lists for each segment, generates graphic primitives from page description language commands, stores the graphic primitives in the display lists, and adaptively compresses and converts the contents of display lists as memory requirements exceed available memory capacity. Display lists contain either uncompressed pixel representations, compressed pixel representations, graphic primitives, or combinations of the foregoing.

Abstract: A process for generating a look-up table for use in displaying a highlight object on a raster display and, in particular, an invertible look-up table for use in displaying a cursor on a background of a raster display.