Method and apparatus for removing noise from a digital image
AssigneeAdobe Systems Incorporated
InventorDennis G. Nicholson
Life of this patent
Estimating the term…
Abstract
One embodiment of the present invention provides a system that removes noise from an image. During operation, the system first identifies blobs in the image, wherein a blob is a set of contiguous pixels which possibly represents a character or a portion of a character in the image. Next, the system analyzes the blobs to dynamically determine a “noise threshold” for the blobs. The system then removes blobs from the image which are below the noise threshold.
Claims21
A method for removing noise from an image, comprising:
- receiving the image;
- identifying blobs in the image, wherein a blob is a set of contiguous pixels which possibly represents a character or part of a character in the image;
- analyzing the blobs to determine a noise threshold, wherein blobs smaller than the noise threshold are likely to be noise;
- and
- removing blobs which are smaller than the noise threshold from the image.
A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for removing noise from an image, the method comprising:
- receiving the image;
- identifying blobs in the image, wherein a blob is a set of contiguous pixels which possibly represents a character or part of a character in the image;
- analyzing the blobs to determine a noise threshold, wherein blobs smaller than the noise threshold are likely to be noise;
- and
- removing blobs which are smaller than the noise threshold from the image.
An apparatus that removes noise from an image, comprising:
- a blob-identification mechanism configured to identify blobs in the image, wherein a blob is a set of contiguous pixels which possibly represents a character or part of a character in the image;
- a threshold-determination mechanism configured to analyze the blobs to determine a noise threshold, wherein blobs smaller than the noise threshold are likely to be noise;
- and
- a blob-removal mechanism configured to remove blobs which are smaller than the noise threshold from the image.
Dependencies are inferred from the claim text.