Scanr, Inc.

Internet Pictures Corporation

Hewlett-packard Development Company, L.p.

Andrew H Mutz

Paulo Ferreira

Dan Nieuwland

Joseph Molnar

Joseph R S Molnar

Oleg B Rashkovskiy

Adam D Sah

Lawrence Michael Bain

Chris P Dury

Andrew Laszlo

Rudy Ruano

David E Waller

Thomas Wang

Daniel A Stryker

Trajan E Unger

A method and a system for interpreting information in a document are provided, with the system receiving an image of a document from a remote source and converting it into multiple sets of blocks of characters. Tags indicating likely meaning of blocks are assigned to them. At least some of the blocks have an associated score representing the probability that the characters in the block correctly represent the characters in the original image. The system selects one set from multiple sets based on the scores associated to certain blocks determined by accessing remote information over the Internet.

System and method for capturing and processing business data

A method of processing information received in the form of a message from a mobile handheld device with a camera, where the message includes data representing an image of a document and an identifier of a type of said document. The method preferably provides image enhancement, information recognition and analysis selected based on the identified document type. An output of the system is preferably provided to the user in the form specified by the user, such as an e-mail.

A method and system for associating active regions with positions within displayed images in a device and display independent manner. Active regions are described by client-side image maps include in hyper-text markup language descriptions of web pages that include specifications of images to be displayed within the web pages. The specifications of images and descriptions of client-side image maps are replaced by servers with a parameterized call to an image viewer, invoked by a browser on a client computer to display the image. The browser maintains an internal description of the positions of active regions in image-relative coordinates, thereby providing dynamic viewing of web pages that include images with associated active regions while maintaining the originally-defined correspondence between the active regions and images.

Dynamic-adaptive client-side image map

A method and apparatus are provided for dewarping images. According to one aspect of the present invention, rotational motion of a scene is taken into account for purposes for performing image dewarping. The image is extracted from the scene by selecting pixel values from an environment map that correspond to a viewing plane. Velocity information associated with rotational motion of the scene is determined. Then, based upon the velocity information, a velocity-dependent transformation is determined. Finally, a perspective image is created by applying the velocity-dependent transformation to the image. In this manner, when the images is presented to a user, the appearance of visible and objectionable distortion may be reduced while maintaining the perceived geometric accuracy of the image. For example, when the scene is rotating at a high angular velocity, little or no dewarping may be performed and the image extracted therefrom may be presented essentially uncorrected. In contrast, when the scene is not rotating, the image may be fully corrected. Between these extremes of high angular velocity and no angular velocity, the amount of dewarping may be modulated to intermediate values.

Velocity-dependent dewarping of images

According to the invention, computerized methods, computer-readable medium containing computer-executable instructions, and apparatus are disclosed for presenting, manipulating, and serving immersive (i.e., panoramic) images. A browser or other display mechanism presents various views of the immersive image comprised of one or more sub-images received from a server, memory, or stored device. Additionally, a server is able to discriminate which type of Web page is provided for efficiently presenting views of an immersive image based on the capabilities of the viewing browser. In this manner, a user is able to efficiently view an immersive image without requiring a Java or other enhance capability browser. Moreover, the invention also provides for determining and presenting a reference indicator which identifies the portion of the immersive image. The reference indicator can also be manipulated to display new perspective views of the immersive image.

Presenting manipulating and serving immersive images

Growing community of inventors

Palo Alto, CA, United States of America

Andrew H Mutz