Xerox Corporation

Other

Damien Cramet

Francois Ragnet

François Ragnet

Florent C Perronnin

Jean-Michel Renders

Scott Robert Hancock

Systems and methods include an application operating on a device. The application causes the graphic user interface of the device to display an initial instruction to obtain a full-view image that positions all of an item within a field of view of a camera on the device. The application automatically recognizes identified features of the full-view image, by using a processor in communication with the camera. After displaying the initial instruction, the application causes the graphic user interface to display a subsequent instruction to obtain a zoom-in image that positions only a portion of the item within the field of view of the camera. Also the application automatically recognizes patterns from the zoom-in image, using the processor. Furthermore the application performs an authentication process using the identified features and the patterns to determine whether the item is valid, using the processor.

Using motion tracking and image categorization for document indexing and validation

A computer-implemented system and method for controlling document image capture are provided. The method includes identifying a categorization model for categorizing image frames and configuring an image capture device, based on the identified categorization model. A flow of frames of a same document captured with the configured image capture device is received and an image representation generated for each of a plurality of frames within the flow of frames. With the identified categorization model, for each of the plurality of frames, a confidence for at least one category is assigned to the frame based on the image representation. A category is assigned to the document when a threshold confidence for one of the at least one categories is assigned. An automatic capture of an image of the document is triggered based on the assigned category.

Categorizer assisted capture of customer documents using a mobile device

A computer implemented system and method are provided for refining category scores for pages of a sequence of document pages that potentially includes document boundaries. The method uses initial category scores provided by a categorizer that considers one page at a time or concatenated pairs of pages (called bipages). The category scores represent the probability that a page belongs to a particular category. The method uses anisotropic diffusion to refine the initial page category scores using the scores of neighboring pages as a function of the probability that there is a boundary between the pages. The method may be performed iteratively.

Categorization of multi-page documents by anisotropic diffusion

A system categorizes one or more objects based at least in part upon one or more characteristics associated therewith. A first classifier includes a rule set to determine if each of the one or more objects meets or exceeds a quality threshold. A second classifier, orthogonal to the first classifier, includes a rule set to determine if each of the one or more objects meets or exceeds a quality threshold. In one embodiment, the quality threshold associated with the first classifier and the quality threshold associated with the second classifier are less than a predetermined target threshold. The result for each object of the first classifier is compared to the result of the second classifier. The object is categorized if the result of the first classifier and the result of the second classifier match. The object is uncategorized if the result of the first classifier does not match the result of the second classifier.

Categorization quality through the combination of multiple categorizers

An apparatus and method are provided for generating a representation of an image which may be used in tasks such as classification, clustering, or similarity determination. An image, such as a scanned document, in which the pixel colorant values are quantized into a plurality of colorant quantization levels, is partitioned into regions, optionally at a plurality of different scales. For each region, a runlength histogram is computed, which may be a combination of sub-histograms for each of the colorant quantization levels and optionally each of plural directions. The runlength histograms, optionally normalized, can then be combined to generate a representation of the document image.

Growing community of inventors

Grenoble, France

Damien Cramet