Systems and methods for removing haze in digital photos
OwnerChun Ming Tsanginventor
Life of this patent
Estimating the term…
Abstract
According to embodiments of the invention, systems and methods are provided for computer-implemented removal of haze, fog, cloudiness and/or other undesired noise from digital imagery. The disclosed technology may be carried out automatically or semi-autonomously, with input from a user. Systems and methods generally involve detecting and isolating certain portions, regions, and/or objects found in a digital image. Depending on their detected depth of field and/or other parameters, certain changes are selectively implemented to reduce the appearance of the detected haze, fog, cloudiness and/or other undesired noise. User input may be employed to further improve certain characteristics of the digital image.
Claims12
A computer-implemented method for digital image de-hazing, the method comprising:
- detecting the presence of haze in an image;
- detecting that a background of the image has a narrow depth of field;
- extracting a foreground portion from the image;
- extracting a background portion of the image;
- and
- performing image processing on the extracted foreground portion.
A computer-implemented method for digital image de-hazing, the method comprising:
- detecting a presence of haze in an image;
- extracting at least one foreground object from the image;
- extracting a background portion of the image;
- displaying the at least one foreground object and the background portion to a user, each associated with a value indicating depth of field of the foreground object and a value indicating depth of field of the background portion;
- receiving input from the user to vary the value indicating depth of field of the background portion;
- and
- performing image processing on the foreground object and the background object in view of the varied value indicating depth of field of the background portion.
A computer-implemented method for digital image de-hazing, the method comprising:
- detecting a presence of haze in an image;
- extracting a first foreground object from the image, the first foreground object being associated with a first value indicating depth of field of the first foreground object;
- extracting a second foreground object from the image, the second foreground object associated with a second value indicating depth of field of the second foreground object;
- extracting a background portion of the image;
- displaying the first foreground object, the second foreground object, and the background portion, along with their respective depth of field values to a user;
- receiving an input from the user to vary the value indicating depth of field of the background portion;
- and
- performing de-hazing image processing on the foreground object and on the background object in view of the varied value indicating depth of field of the background portion.
Dependencies are inferred from the claim text.