Xerox Corporation

Michael E Meyers

Xing Li

Francis Kapo Tse

Whynn Victor Lovette

John Stewart Ceci

Ramesh Nagarajan

Anthony Michael Frumusa

Robert Michael Chapin

Gordon Francis Lupien, Jr

John F Seward, Jr

Brian C Hawkins

Mehdi M Mansoori

Keg transporter

A method and apparatus are provided for processing image data. A peak count and a valley count are determined within a window which includes a plurality of subwindows. An overall count is determined using the greater of the peak count and the valley count for each subwindow. The image data may then be classified based on this determination.

Image segmentation apparatus and method

The present invention generally relates to a digital scanner for scanning images. More specifically, the present invention is directed to a method and apparatus for accurately scanning documents and for processing digital data to provide digital images stored in memory, which can be retrieved for printing on support material or for displaying on a display screen.

Digital scanner for capturing and processing images

A method and apparatus are provided for classifying image data. A neighborhood average gray value may be determined for the input image data. A threshold value may then be determined based on the neighborhood average gray value. Pixels are evaluated to determine if a gray level difference between the pixel and the neighborhood average gray level is greater than the threshold.

A system for processing segmentation tags to generate a block level tag representative of a group of segmentation tags. The system includes first and second statistic compilation circuits, each of the compilation circuits being connected to receive segmentation tags and compile a statistic for a plurality of the received segmentation tags. An address controller connected to the first and second statistic compilation circuits operates to select one of the first and second compilation circuits to receive the segmentation tags.

Block level analysis of segmentation tags

Apparatus and methods in accordance with an exemplary embodiment of the invention convert RGB video to at least one video output of Lab video, YCbCr video, with or without gamma correction, and Srgb video, with or without gamma correction. This conversion increases the flexibility of image information communication by enabling RGB video to be provided to a device that can only handle one of Lab, Srgb and/or YCbCr video.

Methods and apparatus for transforming RGB video

The present invention provides a method and apparatus for classifying image data. A video peak/valley counter may count peaks and valleys within a window of the input image data. The apparatus and method checks whether any peaks or valleys are located within a neighborhood of a pixel under consideration.

The present invention provides a method and apparatus for classifying image data. A white class detector may receive input image data and determine a white class of a specified pixel based on local roughness, peak or count or valley count and a brightness. A pattern detection device may detect a pattern of pixels across a scan line or matrix of input data and compare the pattern with a plurality of predetermined pixel patterns.

The present invention provides a method and apparatus for classifying image data. A video average may be determined from the image data. Peak detection may then be limited to an area within the image data where the video average is above a first threshold. Valley detection may be limited to an area where the video average is below a second threshold.

A method and apparatus are provided for classifying image data. A peak/valley detection device may count peaks and valleys within a window. A local roughness of the image data may be determined and the data may be classified based on the peak/valley count and the local roughness.

Growing community of inventors

Fairport, NY, United States of America

Michael E Meyers