A method for detecting an object in a digital image including the steps of performing color quantization on a model image including the object and on a search image that potentially includes the object, generating a plurality of search windows, computing spatial-color joint probability functions of each model and search image, where the color co-occurrence edge histogram is chosen to be the spatial-color joint probability function, assessing the similarity of each search image to the model, and ...

Computer based method and apparatus for evaluating a graphic image file for the presence of objectionable visual content. The graphic image file comprises a number of pixels each having spectral components defined in accordance with a color model (such as RGB). Relative weighting of the spectral components of each pixel is performed to classify each pixel as either not representing human skin or as possibly representing human skin. For those sets of adjacent pixels that possibly represent human ...

A method for scene classification of a digital image includes extracting pre-determined camera metadata tags from the digital image. The method also includes obtaining estimates of image class based on the extracted metadata tags. In addition, the method includes obtaining estimates of image class based on image and producing a final estimate of image class based on a combination of metadata-based estimates and image content-based estimates.

When a photo album for an event such as a wedding ceremony is generated, images to be inserted in image insertion areas in a template can be selected easily. A professional photographer photographs a bride and groom on the wedding day and obtains a plurality of images. Characteristic quantities of scenes represented by the images are calculated, and the images are classified in image groups of respective scenes. The scenes, image groups and image insertion areas of the template for album are rel...

Color data which is obtained by capturing an image of a color chart by an image capturing apparatus under a first light source, and depends on the first light source is acquired. Target data which is based on colorimetry data of the color chart under a second light source, and depends on the second light source is acquired. The target data which depends on the second light source is converted into target data which depends on the first light source. A color processing parameter corresponding to ...

A method for creating a reduced sized view-map of an autostereoscopic source image is disclosed. The method comprises creating a mathematical model for mapping the autostereoscopic source image into a first view-map, mapping the autostereoscopic source image into the first view-map, wherein the first view-map comprises a source-view image value and a plurality of pixel locations comprising an origin pixel, scanning the first view-map for at least one pixel location whose source-view image value ...

Methods, apparatus, and computer-readable mediums for recognizing or identifying the location of characters within a computer image or display are provided. These methods, apparatuses, and computer-readable mediums make use of dynamic link libraries ("DLLs") and application program interfaces ("APIs") to locate, indicate the state of, and return the coordinates of specified characters or text within an image or display. The returned state and coordinates of the characters may also be used in con...

A blob identifier uses edge continuity signal to analyze how to combine the current pixel into an existing blob or into the background image, or start a new blob. The blob identifier outputs a list of blob identifiers on a line-by-line basis.

A method of interactively using a computer to select a sensor combination for analyzing images of a scene in order to distinguish between objects or patterns. Two or more images are acquired, each image from a different sensor. One or more regions of interest (ROIs) are then defined in the scene. A parallel axis plot is then used to display pixel traces of pixels from the ROI, with each axis of the plot representing one of the images. One or more axes may then be constrained, by selecting a rang...

The present invention enables to increase the speed of recognizing characters on an undefined-size postal matter such as a flat mail. The flat mail often has an address area different in color or pattern from the flat mail itself. The present invention provides an image input apparatus including pickup means of monochromatic-mode CCD 31 having a fine resolution capable of recognizing characters and pickup means of color-mode CCD 30 having a rough resolution only sufficient for detecting an addre...