Abstract: The present invention relates to hiding codes in input data, e.g., such as still imagery and motion pictures. One claim recites: embedding an N-bit code with a source signal, N being at least one. The embedding proceeds, for each bit of the N-bit code, according to the following: mapping the bit to a portion of the source signal; changing values of at least two data values associated with the portion in accordance with the bit. The act of changing embeds the N-bit code in a manner that is generally imperceptible to a human observer of the source signal. A related claim recites that the portion includes a data value, and the above method further includes changing the value of the data value in accordance with said bit of the code, an amount of the changing being adjusted based on the value. Of course, other claims and combinations are provided as well.

Abstract: A method and apparatus for detecting text in real-world images comprises calculating a cascade of classifiers, the cascade comprising a plurality of stages, each stage including one or more weak classifiers, the plurality of stages organized to start out with classifiers that are most useful for ruling out non-text regions, and removing regions classified as non-text regions from the cascade prior to completion of the cascade, to further speed up processing.

Abstract: A method and apparatus for detecting text in real-world images comprises calculating a cascade of classifiers, the cascade comprising a plurality of stages, each stage including one or more weak classifiers, the plurality of stages organized to start out with classifiers that are most useful for ruling out non-text regions, and removing regions classified as non-text regions from the cascade prior to completion of the cascade, to further speed up processing.

Abstract: The presently claimed invention relates generally to creative works and determining whether two or more creative works correspond. One claim recites a method including the acts of: (a) identifying plural local extrema within a two dimensional array of data signal that corresponds to a first creative work; (b) storing information relating to the plural local extrema identified in act (a) in a computer database for future reference; (c) thereafter, identifying plural local extrema within a two dimensional array of data signal that corresponds to a second creative work; and (d) determining correspondence between information relating to the plural local extrema identified in act (c) with the stored information, to thereby determine whether the first creative work and second creative work correspond. Of course, other claims and combinations are provided as well.

Abstract: The present invention relates to hiding codes in input data. In one embodiment, a method is provided including: obtaining input data associated with image or visual information; selecting portions of the input data to hide a plural-bit code based at least in part on predetermined data; and modifying selected portions of the input data to hide the plural-bit code at least in part on changing one or more values of the input data at or around the selected portions. Other embodiments are described and claimed as well.

Abstract: A digital image is processed to hide information, by generally inconspicuous adjustments thereof. These adjustments can define a pattern that extends across some or all of the image. Desirably, the pattern is adapted to the particular image being encoded, so as to better conceal the encoding.

Abstract: A method and apparatus for detecting text in real-world images comprises calculating a cascade of classifiers, the cascade comprising a plurality of stages, each stage including one or more weak classifiers, the plurality of stages organized to start out with classifiers that are most useful for ruling out non-text regions, and removing regions classified as non-text regions from the cascade prior to completion of the cascade, to further speed up processing.

Abstract: The present invention relates to hiding codes in input data. In one embodiment, a method is provided including: obtaining input data associated with image or visual information; selecting portions of the input data to hide a plural-bit code based at least in part on predetermined data; and modifying selected portions of the input data to hide the plural-bit code at least in part on changing one or more values of the input data at or around the selected portions. Other embodiments are described and claimed as well.

Abstract: A digital image is processed to hide information, by generally inconspicuous adjustments thereof. These adjustments can define a pattern that extends across some or all of the image. Desirably, the pattern is adapted to the particular image being encoded, so as to better conceal the encoding.

Abstract: A digital image is processed to hide information, by generally inconspicuous adjustments thereof. These adjustments can define a pattern that extends across some or all of the image. Desirably, the pattern is adapted to the particular image being encoded, so as to better conceal the encoding.

Abstract: A method and system for embedding signatures within visual images in both digital representation and print or film. A signature is inseparably embedded within the visible image, the signature persisting through image transforms that include resizing as well as conversion to print or film among the pixels of an original image. The pixel values of the signature points and surrounding pixels are adjusted by an amount detectable by a digital scanner. The adjusted signature points form a digital signature which is stored for future identification of subject images derived from the image. In one embodiment, a signature is embedded within an image by locating relative extrema in the continuous space of pixel values and selecting the signature points from among the extrema. Preferably, the signature is redundantly embedded in the image such that any of the redundant representations can be used to identify the signature.

Abstract: A digital image in which hidden information has been encoded, is processed to discern the hidden information. This processing can include identifying geometric distortions of the image (e.g., cropping, scaling, rotation), and compensating for such identified distortions.

Abstract: A digital image is processed to hide information, by generally inconspicuous adjustments of pixel values. Desirably, the processing is adapted to the particular image being encoded, so as to better conceal the encoding. The method may include determining a relative ability of a pixel to be adjusted inconspicuously, by reference to values of at least two neighboring pixels.

Abstract: A digital image in which hidden information has been encoded, is processed to discern the hidden information. This processing can include identifying geometric distortions of the image (e.g., cropping, scaling, rotation), and compensating for such identified distortions.

Abstract: A digital image is processed to hide information, by generally inconspicuous adjustments thereof. These adjustments can define a pattern that extends across some or all of the image. Desirably, the pattern is adapted to the particular image being encoded, so as to better conceal the encoding.

Abstract: A digital image is processed to hide information, by generally inconspicuous adjustments of pixel values. Desirably, the processing is adapted to the particular image being encoded, so as to better conceal the encoding. The method may include determining a relative ability of a pixel to be adjusted inconspicuously, by reference to values of at least two neighboring pixels.

Abstract: A method and system for embedding signatures within visual images in both digital representation and print or film. A signature is inseparably embedded within the visible image, the signature persisting through image transforms that include resizing as well as conversion to print or film among the pixels of an original image. The pixel values of the signature points and surrounding pixels are adjusted by an amount detectable by a digital scanner. The adjusted signature points form a digital signature which is stored for future identification of subject images derived from the image. In one embodiment, a signature is embedded within an image by locating relative extrema in the continuous space of pixel values and selecting the signature points from among the extrema. Preferably, the signature is redundantly embedded in the image such that any of the redundant representations can be used to identify the signature.

Abstract: A method and system for embedding signatures within visual images in both digital representation and print or film. A signature is inseparably embedded within the visible image, the signature persisting through image transforms that include resizing as well as conversion to print or film among the pixels of an original image. The pixel values of the signature points and surrounding pixels are adjusted by an amount detectable by a digital scanner. The adjusted signature points form a digital signature which is stored for future identification of subject images derived from the image. In one embodiment, a signature is embedded within an image by locating relative extrema in the continuous space of pixel values and selecting the signature points from among the extrema. Preferably, the signature is redundantly embedded in the image such that any of the redundant representations can be used to identify the signature.