Abstract: A method for improving mixed raster compression segmentation utilizes a second stage of a process to generate the MRC Selector plane by operating on a multibit selector (GraySel) signal which is produced by a first stage process. The first stage methods used to generated the GraySel can be PDL or scan oriented. The binary Selector signal produced by the second stage minimizes the compression noise evident in the reconstructed image. This second stage processing relies on knowing the size of the JPEG minimum coded unit (MCU) which will be used to compress the segmented Foreground and Background planes. The idea is to move false (soft) edges away from the real (hard) edges by as large a distance as possible up to the point where they fall off the boundary of the MCU block. Thus a soft edge which occurs between two hard edges is either eliminated or repositioned to the midpoint and a soft edge between a hard edge and the MCU boundary is moved to the boundary.

Abstract: Reduced size images may be generated by separating dimensions that span the original image into a plurality of groups so that data in each group of one or more dimensions may be processed differently from data of other groups. For example, for two-dimensional images, pixels of selected lines may be completely discarded or skipped while pixels of remaining lines may be processed along the x-dimension to obtain data of the reduced size image. The main advantages include very fast and efficient implementation, minimal storage requirements, and good image quality.

Abstract: A foreground erosion method is used to meet thin (but unbroken) text requirements using linear YCC segmentation. The method uses a fixed value subtracted from a gray selector signal, thereby thinning/eroding the foreground. In cases where the pixel would be converted from foreground to background, this is only done if a neighborhood test verifies that the thinning won't result in broken lines. The foreground erosion method attempts to match a couple of templates wherein if a match is found, then the adjustment is performed.

Abstract: A method and a system for separating an image signal into a set of image planes. The system comprises a min-max module, a dynamic threshold module and a separation module. The min-max module receives the image signal, searches for a minimum and maximum within at least one window centered on a current pixel in the image signal. The dynamic threshold module computes, for the window, based on the respective minimum and maximum received from the min-max module and the current pixel, a respective indicator representing the distance and direction of the current pixel relative to a respective threshold plane, and outputs a control signal based on the indicator. The separation module separates the image signal into the set of image planes in accordance with the control signal by including a representation of the current pixel in at least one of the image planes.

Abstract: A Statistics Module (STS) is disclosed for collecting essential statistics about an image content for the purpose of applying various image enhancement operations such as page background removal and automatic neutral detection to determine if the page is gray or colored. The Statistics Module uses the blurred signal BLR from a De-Screen Module in order to eliminate some of the scanner noise. The output is a special 3D color histogram array.

Abstract: A method and a system for computing the function value of an input node based on function values of known nodes. A database of known nodes and their corresponding function values is formed. The known nodes are located such that a distance between any two adjacent known nodes is an integer power-of-two number. The database is searched for a first node such that the input node is located between the first node and an adjacent second node. The difference ? between the input node and the first node is computed. Then ? is shifted to the right by k positions, k being the logarithm in base 2 of the distance between the first and second nodes. The input node function value is computed by combining the first node function value with the product of the shifted ? and the difference between the function values of the second and first nodes. When used in MRC context, the above method and system is applied to each of the color MRC planes individually, instead of the merged output.

Abstract: A method of generating a binary Sel plane for image compression is disclosed. The method first generates a 2 bit gray selector (GraySel). This 2 bit selector is then processed in a second stage to produce a binary Sel decision which minimizes the compression noise evident in the reconstructed image. The method used here to generate the 2 bit GraySel applies a set of prioritized rules over a small 3×3 window that is well suited for segmenting synthetic, PDL generated images that are typically free of scanner noise. The method not only marks the proper sense of the selector when it is known, but also include a 3rd state that indicates that the selector decision is weak or unknown. This weak decision can then be optimized in the second stage process based on strong edges information in the neighborhood.

Abstract: A method and a system for de-screening an image signal. The system comprises a filter bank, a control module and a blend module. The filter bank filters the image signal and produces a set of filter output signals. The control module generates at least one control signal based on the image signal and some of the filter output signals. The blend module dynamically blends the filter output signals in accordance with the control signal to produce a de-screened output signal.

Abstract: A Gamut Enhance Module (GME) is disclosed for applying 3 independent Tone Reproduction Curves (TRC) to each of the color components of an input image. The implementation is done via three independent and fully programmable 1D lookup tables. The input to the Gamut Enhance Module is the output DSS from a Scaling Module (SCL), representing a scaled and de-screened version of the source image. The output is a gamut-mapped signal GME. The GME unit includes special logic to neutralize (set to gray) or preserve input colors.

Abstract: A method and a system for separating an image signal into a set of image planes. The system comprises a min-max module, a dynamic threshold module and a separation module. The min-max module receives the image signal, searches for a minimum and maximum within at least one window centered on a current pixel in the image signal. The dynamic threshold module computes, for the window, based on the respective minimum and maximum received from the min-max module and the current pixel, a respective indicator representing the distance and direction of the current pixel relative to a respective threshold plane, and outputs a control signal based on the indicator. The separation module separates the image signal into the set of image planes in accordance with the control signal by including a representation of the current pixel in at least one of the image planes.

Abstract: A method and a system for separating an image signal into a set of image planes in accordance with a control signal. The system comprises a selector module, an edge processing module and a foreground/background separation module. The selector module receives the control signal and produces a selector signal. The edge processing module receives the selector signal and produces a decision signal. The foreground/background separation module receives the image signal and the decision signal, and outputs a foreground signal and a background signal, a representation of the current pixel of the image signal being included in at least one of the foreground signal and the background signal in accordance with the decision signal.

Abstract: A method and a system for controlling de-screening of documents. The control system is included in a de-screening system including a bank of filters. The filter bank receives an image signal and produces a set of filter output signals. The control system comprises a contrast module, a halftone estimate module and a pixel control module. The contrast module receives a filter output signal from a filter having a large filter span and produces a contrast signal. The halftone estimate module receives the image signal and a filter output signal from a filter having a small filter span and produces an estimated frequency signal and a halftone weight signal. Based on the contrast signal, the estimated frequency signal and the halftone weight signal, the pixel control module produces a control signal which includes information regarding which of the filter output signals are to be blended and the proportion of blending.

Abstract: The image data is analyzed to identify blobs having similar characteristics. Various blobs are gathered together and placed into a foreground plane based on one or more color characteristics and/or spatial characteristics. Each blob gathered onto a foreground plane has a color that is similar to a color associated with that foreground plane. One or more portions of the image data that is not mapped into any foreground plane may be mapped into a background plane.

Abstract: The image data is initially processed in a manner that is similar to that used to convert the image data into 3-layer mixed raster content format. After the image data is initially processed through a first stage of the three-layer segmentation process, rather than completing the segmentation into foreground and background planes, the image data is analyzed to identify regions having similar image characteristics. These regions are grouped together in cluster if they share color characteristics and are spatially close. The clusters are then sorted according to their size, and placed into a binary foreground plane based on one or more color characteristics. Each cluster gathered into a binary foreground plane having the same color as the color of the cluster.

Abstract: Reduced size images may be generated by separating dimensions that span the original image into a plurality of groups so that data in each group of one or more dimensions may be processed differently from data of other groups. For example, for two-dimensional images, pixels of selected lines may be completely discarded or skipped while pixels of remaining lines may be processed along the x-dimension to obtain data of the reduced size image. The main advantages include very fast and efficient implementation, minimal storage requirements, and good image quality.

Abstract: A highly efficient method and system for eliminating halftone screens from scanned documents while preserving the quality and sharpness of text and line-art is disclosed. The method and system utilizes a single channel screen frequency estimator module, which generates a screen frequency estimate for image data. The module generates a signal based on the highly filtered image signal at low contrast levels, and based on a reliable estimate to the halftone frequency at higher contrast levels. The single channel screen estimate module has adequate performance in resolution ranges from 300 to 600 dpi.

Abstract: Image data is analyzed line by line to identify pixels having similar color and edge characteristics. The pixels on one line are linked to pixels on another line, if they share similar characteristics. The linked pixels are then grouped together in regions and the average color of the region is calculated. An image map is generated that identifies the regions to which the pixels belong, along with a final table of the regions appearing in the image.

Abstract: A blob identifier uses edge continuity signal to analyze to how to combine the current pixel into an existing or into the background image, or start a new blob. The blob identifier outputs a lists of blob identifiers on a line-by-line basis.

Abstract: The image data is processed into a background plane and a plurality of foreground planes. Holes are inserted onto the background plane, in regions which are assigned to a foreground plane. The background plane is sub-sampled, and holes remaining in the sub-sampled image are filled with the average color of the non-zero sub-sampled pixels over pre-determined blocks such as JPEG blocks. If a block is entirely made of holes, the block is filled with a constant color that is propagated from the average color of a previous block. The resulting background plane is far smoother than the original image data and thus can be effectively sub-sampled and highly compressed without adverse deterioration in reconstructed image quality.

Abstract: A method and a system for dynamically thresholding an image signal. The system comprises a computing block. The computing block receives the image signal and a minimum and a maximum within each of a set of windows centered on the current pixel in the image signal, and computes, for each of the windows, based on the current pixel and the respective minimum and maximum, a respective indicator representing the distance and direction of the current pixel relative to a respective threshold plane, and outputs a control signal based on the indicators.