Abstract: The subject application is directed to a facial image enhancement system and method. Image data, including data representing at least one facial area, is first received. Following receipt of the image data, face region data is isolated from the image data. Luminance data and chrominance data are generated corresponding to the facial area data. A smoothing algorithm is thereafter applied to the generated luminance data, which generates smoothed luminance data. Mapping data is then generated according to at least one non-skin tone region of the image data. Enhanced image data is then generated according to the smoothed luminance data, chrominance data, and mapping data.

Abstract: Systems and methods of detecting and correcting redeye in an image are described. In one aspect, pixels of the input image are segmented based on projections of color values of the pixels onto two-dimensional thresholding planes. Candidate redeye pixel areas are identified in the input image based on the segmented pixels of the input image.

Abstract: Systems and methods of detecting and correcting redeye in an image are described. In one aspect, pixels of the input image are segmented based on projections of color values of the pixels onto two-dimensional thresholding planes. Candidate redeye pixel areas are identified in the input image based on the segmented pixels of the input image.

Abstract: Systems and methods of classifying pixels into a nonhuman animal integument class are described. In one aspect, values of features in a discriminant space are determined for respective pixels of the input image. The pixels are classified into a nonhuman animal integument class based on the respective feature values and a mapping that segments the discriminant space into one or more regions of feature values representing pixels associated with a nonhuman animal integument characteristic and one or more regions of feature values representing pixels unassociated with the nonhuman animal integument characteristic.

Abstract: Systems and methods for extracting a graphical bar code (i.e., an image that contains inconspicuous graphical modulations that encode embedded information) from an input image are described. In one aspect, estimates of position coordinates for a detected graphical bar code candidate are computed. An objective function is optimized based on the computed position coordinates to obtain final position coordinate estimates for the graphical bar code candidate. Non-graphical bar code regions are trimmed from the input image based on the final position coordinates for the graphical bar code candidate to produce a trimmed graphical bar code candidate for decoding.

Abstract: In one aspect, a metadata-based classification result is obtained based on metadata associated with an image. A histogram-based classification result is determined based on a histogram of intensity values derived from the image. The image is classified into a scene type class based on the metadata-based classification result and the histogram-based classification result. In another aspect, a first condition is applied on a first one of metadata associated with an image corresponding to a measure of amount of light received in capturing the image to obtain a first metadata-based classification result. A second condition is applied on a second one of the metadata corresponding to a measure of brightness of the image to obtain a second metadata-based classification result. The image is classified into a scene type class based on the first and second metadata-based classification results.

Abstract: Peteye is the appearance of an unnatural coloration (not necessarily red) of the pupils in an animal appearing in an image captured by a camera with flash illumination. Systems and methods of detecting and correcting peteye are described. In one aspect a classification map segmenting pixels in the input image into peteye pixels and non-peteye pixels is generated based on a respective segmentation condition on values of the pixels. Candidate peteye pixel areas are identified in the classification map. The generating and the identifying processes are repeated with the respective condition replaced by a different respective segmentation condition on the pixel values.

Abstract: There is disclosed a method of processing a digital image, which includes assigning an image quality classification to the image on the basis of an analysis of at least a portion of the image to detect whether one or more defects exist in the image.

Abstract: A preliminary set of candidate red-eye pixel areas is identified based on computed pixel redness measures. Candidate red-eye pixel areas having computed redness contrasts relative to respective neighboring pixel areas less than a prescribed redness contrast threshold are filtered from the preliminary set. Candidate red-eye pixel areas located in areas of the digital image having computed grayscale contrasts relative to respective neighboring pixel areas less than a prescribed grayscale contrast threshold also are filtered from the preliminary set. In another aspect, a final pixel mask identifying red-eye pixels and non-red-eye pixels in the candidate red-eye area is generated.

Abstract: Systems and methods for generating and decoding authenticatable graphical bar codes are described. In one aspect, a corroborative signed message is generated from information to be encoded, and a base image is modulated with a graphical encoding of the signed message to produce a marked image. In another aspect, a signed message is extracted from a marked image based upon a comparison of the marked image and a base image. The extracted signed message is decoded to produce a decoded message. Information encoded in the marked image is extracted from the decoded message and authenticated.

Abstract: A digital image search and retrieval system includes a query parser and a response composer. The query parser is configured to parse a query obtained from a client, the query including at least one metadata criterion, search a metadata database for one or more digital images satisfying the metadata criterion, and search a digital image database for the one or more digital images. The response composer is configured to compose a response including the one or more digital images from the digital image database and their corresponding metadata from the metadata database, and enable the client to render the response in accordance with one or more user preferences.

Abstract: An exemplary method for providing an optimized digital image comprises obtaining digital image data by a digital image capture device, based on the digital image data, automatically determining at least two setting types, and a plurality of setting values therefor, for capturing a plurality of digital images, automatically capturing the plurality of digital images using the digital image capture device, each image being captured with at least one setting value different than another image, and providing an optimized digital image based on the plurality of digital images. In one exemplary embodiment, the optimized image is selected from the plurality of digital images. In another exemplary embodiment, the optimized image is synthesized based on the plurality of digital images.

Abstract: A method for determining an indication of how well-focused an image is. An image is divided into a plurality of blocks. At least one local measure is determined for at least one block of the plurality of blocks. At least one global figure-of-merit is determined for the image based on the local measure. An indication of focus is determined based on the global figure-of-merit.

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: Payment indicia generating schemes are described that enable users to customize the appearance of the payment indicium and to accommodate a wide variety of validation processing environments, while providing a substantial defense against fraudulent photocopy attack. In some embodiments, a corroborative digital token is generated from payment information, and a base image is modulated with a graphical encoding of the corroborative digital token to produce a payment indicium. In some embodiments, a payment indicium containing embedded payment information is rendered on a printing surface with a printing characteristic that degrades with photographic reproductions such that the embedded payment information is extractable from an original rendering of the payment indicium but is un-extractable from a photographic reproduction of an original rendering of the payment indicium.

Abstract: Systems and methods for generating graphical bar codes (i.e., images that contain inconspicuous graphical modulations that encode embedded information) by halftoning with embedded graphical encoding are described. In one aspect, a graphical bar code is generated by halftoning regions of an original image. The original image regions incorporate errors diffused among regions of the original image and computed based at least in part upon modulations in the graphical bar code corresponding to a graphical encoding of a message. In another aspect, a graphical bar code is decoded by generating a base image having halftone regions representative of an original image. Regions of the base image are compared probabilistically to a set of graphical code words to obtain a sequence of graphical code words corresponding to a graphical encoding of a message. The sequence of graphical code words is decoded to produce a decoded message.

Abstract: Systems and methods for automatically extracting a graphical bar code (i.e., an image that contains inconspicuous graphical modulations that encode embedded information) are described. In accordance with this automatic extraction scheme, a graphical bar code may be isolated from a composite image in a way that preserves the information-containing graphical modulations encoding the embedded information and avoids corrupting artifacts, such as markings contained in the composite image. The resulting extracted graphical bar code readily may be processed into a format that is tailored to the requirements of a decoding system that may be particularly sensitive to noise, such as extraneous markings and image corruption. In addition, this automatic extraction scheme robustly handles missed and incorrect detections.

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: Systems and methods of detecting and correcting redeye in an image are described. In one aspect, pixels of the input image are segmented based on projections of color values of the pixels onto two-dimensional thresholding planes. Candidate redeye pixel areas are identified in the input image based on the segmented pixels of the input image.

Abstract: Systems and methods of detecting and correcting redeye in an image are described. In one aspect, the input image is sub-sampled to generate a thumbnail image, redeye pixel areas are detected in the thumbnail image. In another aspect, an input image having lines of pixels with original color values is processed. One or more redeye pixel areas corresponding to respective areas in the input image are detected. Each pixel in the input image corresponding to the detected redeye pixel areas is classified as a redeye pixel or a non-redeye pixel on a line-by-line basis without reference to pixels in adjacent lines. The original color values of pixels in the input image classified as redeye pixels are corrected.