Methods, systems, and computer readable media for performing image compression
AssigneeThe University of North Carolina at Chapel Hill
InventorsJan-Michael Frahm, David Paul Perra
Life of this patent
Estimating the term…
Abstract
Methods, systems, and computer readable media for performing image compression are disclosed. According to one exemplary method, the method includes identifying a canonical image set from a plurality of images uploaded to or existing on a cloud computing and/or a storage environment. The method also includes computing an image representation for each image in the canonical image set. The method further includes receiving a first image. The method also includes identifying, using the image representations for the canonical image set, one or more reference images that are visually similar to the first image. The method further includes compressing the first image using the one or more reference images.
Claims19
A method for performing image compression, the method comprising:
- identifying a canonical image set from a plurality of images uploaded to or existing on a cloud computing environment and/or a storage environment;
- computing an image representation for each image in the canonical image set;
- receiving a first image;
- identifying, using the image representations for the canonical image set, one or more reference images that are visually similar to the first image, wherein identifying the one or more reference images includes:
- computing a first image representation for the first image, compressing the first image representation using a binarizing process, and performing, using the first image representation, a k-nearest neighbor(s) (KNN) search over the image representations for the canonical image set, wherein each of the image representations includes a GIST descriptor represented as a binarized string;
- and
- compressing the first image using the one or more reference images.
A system for performing image compression, the system comprising:
- a memory;
- and
- an image compression module (ICM) implemented using a memory, the ICM configured to identify a canonical image set from a plurality of images uploaded to a cloud computing environment and/or a storage environment, to compute an image representation for each image in the canonical image set, to receive a first image, to identify, using the image representations for the canonical image set, one or more reference images that are visually similar to the first image, wherein identifying the one or more reference images includes:
- computing a first image representation for the first image, compressing the first image representation using a binarizing process, and performing, using the first image representation, a k-nearest neighbor(s) (KNN) search over the image representations for the canonical image set, wherein each of the image representations includes a GIST descriptor represented as a binarized string, and to compress the first image using the one or more reference images.
A non-transitory computer readable medium having stored thereon executable instructions that when executed by a processor of a computer control the computer to perform steps comprising:
- identifying a canonical image set from a plurality of images uploaded to or existing on a cloud computing environment and/or a storage environment;
- computing an image representation for each image in the canonical image set;
- receiving a first image;
- identifying, using the image representations for the canonical image set, one or more reference images that are visually similar to the first image, wherein identifying the one or more reference images includes:
- computing a first image representation for the first image, compressing the first image representation using a binarizing process, and performing, using the first image representation, a k-nearest neighbor(s) (KNN) search over the image representations for the canonical image set, wherein each of the image representations includes a GIST descriptor represented as a binarized string;
- and
- compressing the first image using the one or more reference images.
Dependencies are inferred from the claim text.