Intel Corporation

Hewlett-packard Development Company, L.p.

Avi Levy

Doron Shaked

Jonathan Yen

Renato Keshet

Konstantin Levit-Gurevich

Clayton Atkins

Ziv Aviv

Chit Wei Saw

Joseph Levitas

Detecting a static graphic object (such as a logo, title, or sub-title) in a sequence of video frames may be accomplished by analyzing each selected one of a plurality of pixels in a video frame of the sequence of video frames. Basic conditions for the selected pixel may be tested to determine whether the selected pixel is a static pixel. When the selected pixel is a static pixel, a static similarity measure and a forward motion similarity measure may be determined for the selected pixel. A temporal score for the selected pixel may be determined based at least in part on the similarity measures. Finally, a static graphic object decision for the selected pixel may be made based at least in part on the temporal score.

Method of detecting logos, titles, or sub-titles in video frames

A filtering system and method are disclosed, to perform simultaneous, de-noising, and details enhancement tasks of a video image. The efficient filtering system includes multiple filters, which operate on a portion of the video image that has been partitioned into multiple rings. Using the filtering system, complex mathematical operations are avoided.

Method for adaptive image enhancement

In one embodiment, an image processor may be used to manipulate a hue value to obtain an updated hue value, manipulate a saturation value to obtain an updated saturation value based on the updated hue value and the saturation value, and if updated pixel data including the updated hue value and the updated saturation value is an illegal value, adjust a luma value. Other embodiments are described and claimed.

Methods and apparatus for enhancing color data

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.

Automatically extracting graphical bar codes

Fiducial mark patterns for graphical bar codes (i.e., images that contain inconspicuous graphical modulations that encode embedded information) that are characterized by high detection robustness and good local deformation tracking are described. In one bar coding method, a base image is modulated with a graphical encoding of a message to produce a graphical bar code, and a fiducial mark pattern comprising a plurality of dots arranged to track one or more reference locations and local deformation across the graphical bar code is generated. In another bar coding method, fiducial mark candidates are identified in a fiducial mark pattern, a fiducial mark path is computed based upon one or more of the identified fiducial mark candidates, and one or more reference locations are identified based upon the computed fiducial mark path.

Fiducial mark patterns for graphical bar codes

Systems and methods of graphically demodulating a graphical bar code (i.e., an image that contains inconspicuous graphical modulations that encode information embedded in an original base image) are described. The graphical bar code may be graphically demodulated automatically without foreknowledge of the original unmodulated base image, but rather based upon a base image that is derived based upon intrinsic features of the graphical bar code.

Growing community of inventors

Tivon, Israel

Avi Levy