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: 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: 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 for generating a panoramic image that enables a user to obtain panoramic photographs with a digital camera without the aid of a computer system or specialized lenses. A digital camera according to the present techniques captures a series of image frames as a user pans the digital camera through a panoramic image scene and combines the captured image frames while the image frames are being captured.

Abstract: Systems and methods of extracting from an input image a graphical bar code containing graphically encoded information are described. In one aspect, a document template is matched to the input image. The document template is selected from a set of document templates each having a respective predetermined page layout corresponding to a respective document type and including a predetermined graphical bar code location. The input image is cropped based on information relating to the graphical bar code location in the page layout of the document template matched to the input image to produce a cropped graphical bar code candidate for decoding.

Abstract: A method and system for halftoning images that uses error diffusion with partial dots is provided. First, an input picture element (input pixel) that has a picture level (e.g., gray level) is received. Next, a reproducible gray level is generated based on the gray level of an input pixel. Then, a corrected gray level is generated based on the gray level of an input pixel and an error amount (e.g., error propagated or diffused from adjacent areas or pixels). A determination is made whether the corrected gray level is in a predetermined relationship with a threshold. When the corrected gray level is in a predetermined relationship with the threshold, the reproducible gray level (i.e., partial dot size) is provided as output. When the corrected gray level is not in a predetermined relationship with the threshold, a zero value is provided as output.

Abstract: A system and method for enhancing digital images containing both text and pictorial content (“mixed document images”) utilizes an estimated illumination surface for a given digital image to correct the undesirable effect of non-uniform illumination. The estimated illumination surface is based on the luminance values of the edge pixels of the given image that are on the dark side of text edges. In an alternative embodiment, the luminance values of the edge pixels that are on the lighter side of the detected text edges are used to generate the estimated illumination surface. The estimated illumination surface is applied to the digital image to compensate for illumination variations in the image due to non-uniform illumination. In addition to non-uniform illumination correction, the system and method enhances the mixed document images by sharpening and/or darkening edges of text contained in the images.

Abstract: A method analyzes an image to be scanned and analyzes at least part of the image pixel-by-pixel. During or after a preview scan, a characteristic is assigned to a plurality of pixels in the image and pixels are grouped according to similar characteristics. A representation of a least one of the characteristics corresponding to a group of pixels is communicated to the scanner. For example, the pixels may be analyzed to determining if the pixel is black or white. The pixels may also be analyzed to determining if a pixel is on an edge between black and white. Black pixels that are adjacent each other can be grouped together, and white pixels that are adjacent each other can also be grouped together. A region of an image with a relatively high number of black and white groups can be characterized as black and white text only. That characterization can then be used to properly set a scanner, for example, without user intervention, so that the final scan of the image can be done at 300 dpi with a low bit depth.

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: A system and method capable of performing language translation of a graphical representation of a first language character string within captured image data of a natural image by extracting image data corresponding to the graphical representation of the text from the captured image data. The extracted graphical representation is then converted into first language encoded character data that, in turn, is translated into a second language data. The translated text and the captured image can then be displayed together by overlaying the translated text over the graphical representation of the character string in the captured image.

Abstract: A system and method for enhancing scanned document images utilizes an estimated background luminance of a given digital image to remove or reduce visual “see-through” noise. The estimated background luminance is dependent on the luminance values of the edges pixels of detected text edges of the image. In one embodiment, the estimated background luminance is generated using only the edge pixels that are on the lighter side of the detected edges. In addition to the see-through removal, the system and method may further enhance the scanned document images by removing color fringes and sharpening and/or darkening edges of text contained in the images.

Abstract: Disclosed are systems and methods to identify text-like pixels from an image by providing an image and classifying line segments of pixels within the image by edge-bounded averaging.

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 &ggr; curve.

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.

Abstract: A method and system for halftoning images that uses error diffusion with partial dots is provided. First, an input picture element (input pixel) that has a picture level (e.g., gray level) is received. Next, a reproducible gray level is generated based on the gray level of an input pixel. Then, a corrected gray level is generated based on the gray level of an input pixel and an error amount (e.g., error propagated or diffused from adjacent areas or pixels). A determination is made whether the corrected gray level is in a predetermined relationship with a threshold. When the corrected gray level is in a predetermined relationship with the threshold, the reproducible gray level (i.e., partial dot size) is provided as output. When the corrected gray level is not in a predetermined relationship with the threshold, a zero value is provided as output.

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.