Xerox Corporation

Dhevendra Alagan Palanivel

Sainarayanan Gopalakrishnan

Xing Li

Sudhagar Subbaian

Vignesh Doss

Rajasekar Kanagasabai

Clara Cuciurean-Zapan

Ramesh Nagarajan

Anand Arokia Raj Antony Muthu Rayar

Sunil Kumar

A computer-implemented method and system for processing a document page is based on text and non-text detections in an image path. An object block is generated for each image content identified within an input page. the blocks are extracted from the input document for downstream processing. Then, the object blocks are classified based on whether the content is text or non-text. The extracted non-text objects&#x2014;which are specified by their bounding boxes&#x2014;are processed separately from the rest of the content. The processing is performed on the text content blocks in parallel. However, when error diffusion is employed, the error diffusion is performed sequentially on the non-text content blocks to avoid stitching artifacts between individually error diffused patches in non-text areas.

Performance improvement with object detection for software based image path

A document processing system produces a digital representation of an original image by determining a background level for white space of the original image. Using the background level, the system identifies pixels not belonging to the white space. The system generates a binary image of the original image based from the identified pixels. The system then identifies image content surrounded by the white space in the original image using the binary image. Next, the system generates a block for each image content and extracts each block from the original image. After processing each block, the system reapplies the processed blocks to a blank canvas to generate the digital representation.

Method to improve performance in document processing

System(s) and method(s) for text enhancement in printing material saving mode are described. In an example, a method comprises identifying a type of a pixel based on edge tag data associated with the pixel, where the edge tag data is indicative of whether the pixel is an edge pixel or a non-edge pixel. The method further comprises determining at least one material saving parameter based on the type of the pixel. Further, the method comprises modifying a quantization error value based on the at least one material saving parameter. The method further comprises distributing the modified quantization error to a set of unprocessed pixels.

Text enhancement in printing material saving mode

System(s) and method(s) for controlling a rate of consumption of printing material are described. The method includes receiving an image to be printed or copied and converting the image into a plurality of pixels. A value of a pixel, from among the plurality of pixels, is compared with a predefined threshold value. When the value of the pixel is below the predefined threshold value, a black pixel indicative of a pixel with printing material is generated. An error between the value of the pixel and a value of the black pixel is determined. The error value is multiplied by a gain value and then the weighted value of resultant is distributed among neighborhood pixels. The gain value is varied to control the rate of consumption of the printing material, as the consumption of the printing material is reduced when the gain value is increased.

Methods and systems for usage control of printing material

The present disclosure discloses methods and systems (a multi-function device or a digital printer) having capabilities for an object enhancement. In an example, the MFD includes a digital front end module to detect edge of the object and direction of the edge. Following the detection of the edge, the digital front end module classify the pixels of the edge into two categories, for example, which define that whether the edge pixels are created by black-to-white transition or white-to-black transition. Based on the classification of the edge pixels, the digital front end module performs the object enhancement either in black-to-white transition or in white-to-black transition.

Methods and devices for enhancing edges of a graphic object

A method, non-transitory computer readable medium and apparatus for generating an output image are disclosed. For example, the method includes receiving an image, applying a first filter, applying a second filter, calculating a difference between the image with the second filter that was applied and the image with the first filter that was applied and transmitting the difference to a sharpening module and a segmentation module to generate the output image.

Filter configuration for software based image path

An electronic document image of a document is captured using a camera of a handheld device. A user interface of the handheld device displays an instruction to place the handheld device on the document and to change the magnification of the electronic document image on the user interface until the electronic document image and the document are the same size. The handheld device automatically determines the original size of the document based on the magnification that made the electronic document image and the document the same size when the handheld device was on the document. The handheld device converts the electronic document image into an original size document image file based on the original size of the document.

Detecting sizes of documents scanned using handheld devices

Disclosed herein is a system, method and computer implemented method of facilitating generation of a digital representation of one or more physical objects. The method may include scanning a first part of the one or more physical objects to obtain image data corresponding to the first part. The scanning may be performed based on a first set of values corresponding to one or more parameters. The image data corresponding to the first part may be a digital representation of the first part. The method may further include determining a size of image data corresponding to the first part. Additionally, the method may include displaying information based on the size of the image data corresponding to the first part, prior to receiving image data corresponding to a second part of the one or more physical objects.

Methods and systems facilitating generation of digital representations of objects

A method and a system for image compression are disclosed. An image is converted to a halftoned image. The one or more halftoned lines in the halftoned image comprise one or more pixels. A first transformed image is generated from the halftoned image based on shifting of the one or more pixels, associated with the one or more halftoned lines in the halftoned image, by a first value. A second transformed image is generated from the first transformed image based on shifting of the one or more pixels, associated with the one or more halftoned lines in the first transformed image, by a second value. Further, a compressed image is generated based on compression of the second transformed image. The compressed image is stored in a storage device. Another method and system for image conversion are disclosed that converts the compressed image back to the first transformed image.

Method and system for compressing and converting an image during printing

Embodiments of the present disclosure disclose methods and systems for halftone frequency detection in a halftone image. The method includes receiving a first window, a second window, and the halftone image having a predetermined resolution; assigning an active value to a max variable and a min variable associated with each pixel within a first pixel neighborhood defined by the first window based on a pixel intensity value being compared with a three-way threshold set determined based on values a plurality of predetermined statistical parameters; estimating a first frequency estimate and the second frequency estimate based on a number of pixels having active values in the max variable and the min variable respectively within a second pixel neighborhood defined by the second window; and determining the halftone frequency based on the first frequency estimate value, the second frequency estimate value, and the predetermined resolution.

Systems and methods for halftone frequency detection

Various embodiments for methods and systems for processing documents are disclosed. A size of at least a part of a content in an electronic document is determined. Size of the part of the content is modified based at least on a pre-determined threshold value for size and the determined size. Further, various embodiments for methods and systems for processing N-Up documents are disclosed. One or more page images from an N-Up document are extracted based on an analysis of a content distribution in the N-Up document. A size of a content in at least a part of extracted one or more page images is determined. The size of the content is modified in accordance to a pre-determined threshold value receive from a user.

Modifying the size of document content based on a pre-determined threshold value

In systems and methods, an original image was previously converted to a lower bit count per pixel. The resulting image included pixel error based on the lower bit count per pixel. The conversion used an error weighting matrix (which diffuses the pixel error of each pixel to adjacent pixels). Methods and systems produce an output image from the lower bit count per pixel image using the error weighting matrix to determine, for each pixel, the amount of error added because of the adjacent pixels during the conversion process. Then, such methods and systems remove, from each pixel, the amount of error that was previously added based on the adjacent pixels. After removing the amount of error added based on the adjacent pixels from all pixels in the input image, an output image is reconstructed using a filter, such as a low pass filter.

Inverse halftoning using inverse projection of predicted errors for multi-bit images

Some embodiments are directed to a method of automatically modifying a scanned image of a page from an input document comprising a plurality of pages. First, scanned images of the plurality of pages are obtained. Next, a user selection for an output orientation of an output document and optionally value of N for an N-Up operation is received. Thereafter, input orientation of each scanned image is detected. Then, the scanned image is rotated, based on the detected input orientation, the output orientation and the value of 'N' if provided by the user. Next, the rotated scanned image content is resized so that it fits on a page. Finally, the output document is prepared that includes pages in the output orientation.

Methods and systems for automated orientation detection and correction

A method and system generates a reconstructed gray scale image of pixels from a binary image of pixels by reverse propagating an error, in a diffused manner, to the pixels of the binary image to create pixels representing a reconstructed gray scale image. The reverse propagation of the error determines if a current pixel has a first predetermined value; sets an error value to a first error value if the current pixel has the first predetermined value; sets the error value to a second error value if the current pixel does not have the first predetermined value; and propagates a diffused error value to a pixel neighboring the current pixel to create an error diffused pixel, the diffused error value being a product of the set error value and a weighting coefficient associated with the pixel neighboring the current pixel. A Gaussian filter may be utilized to filter the pixels representing a gray scale image to create a filtered reconstructed gray scale image of pixels.

Method and system for inverse halftoning utilizing inverse projection of predicted errors

Methods and systems divide an image into image blocks, determine a number of high-variation blocks within valid image blocks, determine a page variance measure by dividing the number of high-variation blocks by the total number of valid image blocks, and classify the image as comprising a halftone and/or text image if the page variance measure exceeds a halftone threshold. Such methods and systems classify the image as being a continuous tone image if the page variance measure does not exceed the halftone threshold and a text index is below a text index threshold, and classify the image as being a continuous tone and text image if the page variance measure does not exceed the halftone threshold and the text index is not below the text index threshold. Further, such methods and systems select an image processing mode based on such image classifications.

Growing community of inventors

Chennai, India

Dhevendra Alagan Palanivel