Abstract: Systems and methods according to the present invention provide techniques to reliably detect edges, lines and quadrilaterals, especially those with low local contrast, in color images. Edges can be detected using a color gradient operator is based on color distance with a non-linear weight determined by the consistency of local gradient orientations, thereby significantly improving the signal/noise ratio. In detecting lines, a variant of the Gradient Weighted Hough Transform can be used employing both the edge strength and orientation. Multiple non-overlapping quadrilaterals can be detected using a process which includes quality metrics (for both individual quadrilaterals and for a set of non-overlapping quadrilaterals) and a graph-searching method.

Abstract: A method analyzes an image to be scanned and analyzes at least part of the image pixel-by-pixel. Elements in the image are characterized according to a perceived characteristic and each image element having a given characteristic that is adjacent a similar or identical image element is identified. In one form, there are preferably at least three different characteristics, such as black, background and edge, by which the image elements can be characterized. In another form, image elements that are close enough to each other in physical location and close enough to each other in image characteristic are grouped together or included in a blob. Sub-blobs can be found to be part of a more predominant blob. In a further form, image elements are identified that represent an edge in the image, along with identifying those edge elements that are adjacent at least one other edge element.

Abstract: A card reader with power-saving function is used for being inserted with a memory card so that a computer can access the memory card through the card reader. When the memory card is inserted in the card reader, the card reader is enabled to operate. On the other hand, when the memory card is not inserted in the card reader, the card reader enters to a power-down mode for saving power.

Abstract: A method performed by a processing system is provided. The method comprises detecting a first pixel value associated with an artifact in a current frame of a digital video using a previous frame and a next frame and replacing the first pixel value in the first frame with a replacement value.

Abstract: A method performed by a processing system is provided. The method comprises detecting an artifact in a first frame of a digital video using a plurality of edges identified in the first frame and replacing a region that encompasses the artifact in the first frame with a corresponding region from a second frame.

Abstract: Methods, machines, and computer-readable media storing machine-readable instructions for segmenting pixels in an image are described. In one aspect, a region of background pixels is identified in the image. At least some of the background pixels in the region are located on a boundary spatially delimiting the region. One or more orientation-dependent adaptive thresholds are determined for one or more respective candidate growth directions from a given background pixel located on the region boundary. Color distances between the given background pixel and candidate pixels in a neighborhood of the given background pixel are determined. The region is grown based on application of the one or more orientation-dependent adaptive thresholds to the determined color distances.

Abstract: Embodiments of the present invention recite a system and method for creating an editable template from a document image. In one embodiment of the present invention, the spatial characteristics and the color characteristics of at least one region of a document are identified. A set of characteristics of a graphic representation within the region are then determined without the necessity of recognizing a character comprising the graphic representation. An editable template is then created comprising a second region having the same spatial characteristics and the same color characteristics of the at least one region of the document and comprising a second graphic representation which is defined by the set of characteristics of the first graphic representation.

Abstract: Methods, apparatus, and machine-readable media for segmenting and enhancing images are described. In one aspect, gradient magnitude values at respective pixels of a given image are determined. The gradient magnitude values are thresholded with a global threshold to produce thresholded gradient magnitude values. The pixels are segmented into respective groups in accordance with a watershed transform of the thresholded magnitude values. A classification record is generated. The classification record labels as background pixels ones of the pixels segmented into one of the groups determined to be largest in size and labels as non-background pixels ones of the pixels segmented into any of the groups except the largest group.

Abstract: Systems and methods according to the present invention provide techniques to automatically insert an object from one image into a region of another image. The systems and methods require little or no user interaction to allow efficient re-use and updating of existing images, presentations, documents and the like. An object and a container region are identified. Feasible placement location(s) within the container region for the object, as well as an associated scale factor, are determined. If multiple feasible placement locations are identified for a particular scale factor, then one is selected based upon predetermined criteria. The object can then be inserted into the container region and the resulting composite image stored or, alternatively, parameters can be stored which enable object insertion at a subsequent processing step.

Abstract: Systems and methods of generating and using auxiliary information for reconstructing digital images that have processed through print-scan channels are described. Auxiliary information, including values of reference pixels, is extracted from an input image. Output image data containing a representation of the input image is generated. The auxiliary information is stored in association with the output image data. The auxiliary data structure is decoded to produce decoded auxiliary information. Scanned image data that is obtained from a hard copy of the output image data is registered and color-corrected based on the decoded auxiliary information to obtain an output image corresponding to a high-quality reconstruction of the input image. The auxiliary information may include coded transform coefficient data from which the input image may be reconstructed using the registered and color-corrected output image as side information.

Abstract: A method for determining logical components of a portable document format (PDF) document is disclosed. The method includes separating the document into a plurality of layers. A PDF document is created for each of the plurality of layers. The method also includes determining a logical structure for each layer. The logical structures of the plurality of layers are combined to determine the logical components of the PDF document.

Abstract: A personalized slide show generation system is comprised of a script generator and a personalized slide show generation engine. The script generator is configured for employing a user interaction associated with an image to generate an interaction script. The personalized slideshow generation engine is coupled to the script generator and configured for utilizing the image and the interaction script to generate a personalized slide show.

Abstract: In one embodiment, the present invention is directed to a method for processing a digitally captured image that comprises an imaged document. The method comprises: detecting graphical information related to spatial discontinuities of the digitally captured image; detecting lines from the detected graphical information; computing effective area parameters for quadrilaterals associated with ones of the detected lines, wherein each effective area parameter for a respective quadrilateral equals an area of the respective quadrilateral modified by at least a corner matching score that is indicative of a number of connected edge pixels in corners of the respective quadrilateral; and selecting a quadrilateral of the quadrilaterals that possesses a largest effective area parameter.

Abstract: Image processing methods, image processing systems, and articles of manufacture are described. According to one aspect, an image processing method includes defining an image dimension corresponding to a common size of data content of a plurality of images which are associated with one another, determining a plurality of image boundaries individually corresponding to a size of the data content of a respective one of the images, comparing individual ones of the image boundaries with respect to the image dimension providing difference information for respective ones of the images and indicative of differences of the respective image boundaries with respect to the image dimension, and adjusting the images using respective difference information corresponding to respective ones of the images.

Abstract: Systems and methods according to the present invention provide techniques to automatically crop an image to a desired size and non-rectangular crop shape. A non-rectangular crop shape can, for example, be input to an image processing system. The non-rectangular crop shape is then used to process the original image to generate the desired crop.

Abstract: Two layer formatting of documents for compatibility with two layer formatting schemes while maintaining color information and edge sharpness for text. A document is divided into multiple regions based upon bodies of text having the same color. A text layer and a non-text layer are specified for each region. The text layer includes a text color along with binary values for each pixel to specify whether to use the text color or a background color. The non-text layer includes a red-green-blue value for each pixel to specify its color for both image or non-text information including the background color for the bodies of text. The text layer is compressed using a lossless compression method and the non-text layer is compressed using a lossy compression method.

Abstract: The present invention relates to a look up table method for reducing the use of memory and more particularly to a condition while the input value has higher bits than the output value. This look up table method comprises: data storing that storing the input data into memory corresponding with output data with reference to the address of output data; and data searching including reading an input data, finding a closest address to the input data, and outputting the closest address. In this present invented look-up table method, the relation curve between the output value and corresponded input value is a monotonic curve, such as a ? curve.

Abstract: A method performed by a processing system is provided. The method comprises detecting a first pixel value associated with an artifact in a current frame of a digital video using a previous frame and a next frame and replacing the first pixel value in the first frame with a replacement value.

Abstract: A method performed by a processing system is provided. The method comprises detecting an artifact in a first frame of a digital video using a plurality of edges identified in the first frame and replacing a region that encompasses the artifact in the first frame with a corresponding region from a second frame.

Abstract: A method and system for capturing images. First, a preview image of a scene is captured. Next, an automatic determination is made whether the scene is a document. When it is determined that the scene is a document, at least one camera control is set to a value that is tailored for document capture. The scene is then captured using the set camera controls. Image processing that is tailored for documents is then performed on the captured scene.