Clara Cuciurean-Zapan - Fairport NY Ramesh Nagarajan - Fairport NY Robert P. Loce - Webster NY Jeffrey D. Kingsley - Macedon NY
Assignee:
Xerox Corporation - Stamford CT
International Classification:
G06K 936
US Classification:
382284, 382294, 345435, 348584
Abstract:
The methods and apparatus of this invention model and reconstruct binarized images. A grayscale image is modeled using a template matching approach. Each binarized grayscale image value is characterized by a unique set of templates which are rotations of each other. The set of templates allows construction of a look-up table between patterns and grayscale values. The look-up table is provided with a limited number of entries. As a result, the number of entries in the look-up table is reduced. The look-up table thus obtained is used for reconstructing the original grayscale image from the binarized image. The generated image quality is good in comparison with conventional methods. The process may be applied to various halftoning processes including error-diffusion processes.
Systems And Methods For Template Matching Of Multicolored Images
Robert P. Loce - Webster NY Michael S. Cianciosi - Rochester NY Ying-Wei Lin - Penfield NY
Assignee:
Xerox Corporation - Stamford CT
International Classification:
G06K 900
US Classification:
382162, 382209
Abstract:
Systems and methods for template matching of multicolored images provide an image conversion process that respectively views two, three or four input color planes through an input observation window. Single plane vectors are obtained that represent the color planes. The obtained single plane vectors are combined into a multi-plane vector that may be used in a look-up table for descreening or resolution enhancement, for example. Various interactions between color planes may be taken into account to provide optimum color space conversion. Additional information obtained by using the multi-plane vector allow performance of image processes with optimized accurate color values.
Systems And Methods For Rotating High Addressability Images
Robert P. Loce - Webster NY David Glassman - Rochester NY Henry P. Jankowski - Rochester NY
Assignee:
Xerox Corporation - Stamford CT
International Classification:
G06K 1500
US Classification:
382254, 358 19
Abstract:
Image rotation systems and methods optimally rotate high addressability binary images by transforming the high addressability image to a quasi-grayscale image having normal addressability. A degree of low-pass filtering may be used in conjunction with resampling the image in the process of generating the normal addressability image for rotation. The quasi-grayscale image is then rotated. The rotated quasi-grayscale image is then converted back to a high addressability binary image using a high addressability halftoning process. The systems and methods provide a process wherein high addressability binary images are rotated without introducing gray-level contours or pattern artifacts such as moirÃ. Further, the apparatus and method provide compact rotation of high addressability images. The density and edge integrity of the processed image are maintained without introducing false contours.
Yeqing Zhang - Penfield NY Robert P. Loce - Webster NY Martin E. Banton - Fairport NY
Assignee:
Xerox Corporation - Stamford CT
International Classification:
G06K 936
US Classification:
358 19, 358 114
Abstract:
A method to compact a diffuse gray edge that is two pixels wide to a state where it is one pixel wide so that it may be well rendered with anti-alias rendering. The method identifies an observation window within continuous tone image data. The method then operates on the pixels within the observation window by: compacting horizontal features within the observation window; compacting vertical features within the observation window; and compacting corner features within the observation window.
Systems And Methods For Designing Image Processing Filters Using Templates
Image conversion systems and methods optimally perform filter design. The filter design allows for template-based image processing filters to be optimized to criteria based on visual perception. Different weights may be assigned based on different pixel errors. Possible weighting schemes in accordance with the systems and methods of the invention include a function of the distance to ideal pixels and a function of the value of neighboring pixels. The method provides better image quality. The method is useful for resolution enhancement and image restoration in particular.
Method And Apparatus For Automatic Image Segmentation Using Template Matching Filters
Ronald E. Jodoin - Pittsford NY Robert P. Loce - Webster NY Reiner Eschbach - Webster NY
Assignee:
Xerox Corporation - Stamford CT
International Classification:
G06K 934
US Classification:
382173, 382217, 358462
Abstract:
The present invention is a method and apparatus for automatic image segmentation using template matching filters. The invention generally segments differing binary textures or structures within an input image by passing one or more structures while removing other structures. More particularly, the method and apparatus segment a stored binary image using a template matching filter that is designed to pass therethrough, for example, text regions while removing halftone regions.
Method And Apparatus For Using Rotatable Templates Within Look-Up Tables To Enhance Image Reproduction
The present invention is a method and apparatus for improving the appearance of electronic images, and more specifically, to the efficient use of template rotation within a template matching process to enhance such images. The invention reduces the number of entries that are stored in a look up table by eliminating identical patterns that differ only by the angle at which they are output. The appropriate templates are then rotated it by the required angle for output subsequent to their retrieval from the lookup table.
Compact Rendering For Processing Binary High Addressability Images
Robert P. Loce - Webster NY Yeqing Zhang - Penfield NY Leon C. Williams - Walworth NY Michael Branciforte - Rochester NY
Assignee:
Xerox Corporation - Stamford CT
International Classification:
G06K 936
US Classification:
382276, 382299, 358 12
Abstract:
A method of processing a high addressability binary image comprises converting the high addressability binary image to gray-scale image data; manipulating the gray-scale image data; and rendering the manipulated gray-scale image to a high addressability format using a compact rendering process.
S & W Services
Service Coordinator
Patterson Dental May 2014 - Mar 2015
Service Coordinator
Apple Transportation Apr 2012 - Sep 2014
Dispatcher and Driver
Griffith Energy Services, Inc. Feb 2007 - Oct 2012
Customer Service and Office Administrator