Identifying computer graphics from digital photographs
AssigneeNew Jersey Institute of Technology
InventorsYun-Qing Shi, Wen Chen
Life of this patent
Estimating the term…
Abstract
Computer graphics may be detected in digital images by extracting a first set of features from an input digital image, extracting a second set of features from a prediction-error image derived from the input digital image, and applying a classification algorithm to the first set of features and the second set of features to determine if the combined sets of features indicate that the input digital image corresponds to computer graphics.
Claims21
A method of identifying computer graphics in digital images, the method comprising:
- extracting a first set of features from an input digital image, said extracting comprising:
- applying a discrete transformation to decompose the input digital image into a set of sub-bands;
- and
- obtaining sets of moments of characteristic functions associated with the sub-bands and with the input digital image, wherein said sets of moments are used to form said first set of features;
- extracting a second set of features from a prediction-error image derived from said input digital image;
- and
- applying a classification algorithm to said first set of features and said second set of features to determine if the combined sets of features indicate that the input digital image corresponds to computer graphics.
A processor-readable medium containing software code that, when executed by a processor, causes the processor to implement a method of identifying computer graphics in digital images, the method comprising:
- extracting a first set of features from an input digital image, said extracting comprising:
- applying a discrete transformation to decompose the input digital image into a set of sub-bands;
- and
- obtaining sets of moments of characteristic functions associated with the sub-bands and with the input digital image, wherein said sets of moments are used to form said first set of features;
- extracting a second set of features from a prediction-error image derived from said input digital image;
- and
- applying a classification algorithm to said first set of features and said second set of features to determine if the combined sets of features indicate that the input digital image corresponds to computer graphics.
Dependencies are inferred from the claim text.