COMPUTER-IMPLEMENTED METHOD, A COMPUTER PROGRAM PRODUCT AND A COMPUTER SYSTEM FOR IMAGE PROCESSING
First Claim
1. A computer-implemented method for image processing, the method comprising:
- receiving (701) at least one user image (506);
identifying a plurality of image classification elements of the user image by;
assigning an initial classification to the user image, wherein the initial classification is based on temporal data associated with the user image;
determining at least one image label that globally describes content of the user image;
calculating a label correctness value for each image label;
recognizing (705) at least one image component (508, 510) of the user image;
calculating a component correctness value for each image component (508, 510);
correlating (708) the image label and the image component (508, 510) using the label correctness value and the component correctness value, whereby a correlated image label and a correlated image component are identified;
applying a rule to determine a category of the user image, wherein the rule is based on at least one of the following;
the temporal data, the correlated image label and the correlated image component; and
producing a final classification of the user image including the following image classification elements;
the initial classification, the correlated image label, the correlated image component, and the category.
1 Assignment
0 Petitions
Accused Products
Abstract
The present description refers in particular to a computer-implemented method, a computer program product and a computer system for image processing, the method comprising: receiving at least one user image; identifying a plurality of image classification elements of the user image by: assigning an initial classification to the user image, wherein the initial classification is based on temporal data associated with the user image; determining at least one image label that globally describes content of the user image; calculating a label correctness value for each image label; recognizing at least one image component of the user image; calculating a component correctness value for each image component; correlating the image label and the image component using the label correctness value and the component correctness value, whereby a correlated image label and a correlated image component are identified; applying a rule to determine a category of the user image, wherein the rule is based on at least one of the following: the temporal data, the correlated image label and the correlated image component; and producing a final classification of the user image including the following image classification elements: the initial classification, the correlated image label, the correlated image component, and the category.
-
Citations
14 Claims
-
1. A computer-implemented method for image processing, the method comprising:
-
receiving (701) at least one user image (506); identifying a plurality of image classification elements of the user image by; assigning an initial classification to the user image, wherein the initial classification is based on temporal data associated with the user image; determining at least one image label that globally describes content of the user image; calculating a label correctness value for each image label; recognizing (705) at least one image component (508, 510) of the user image; calculating a component correctness value for each image component (508, 510); correlating (708) the image label and the image component (508, 510) using the label correctness value and the component correctness value, whereby a correlated image label and a correlated image component are identified; applying a rule to determine a category of the user image, wherein the rule is based on at least one of the following;
the temporal data, the correlated image label and the correlated image component; andproducing a final classification of the user image including the following image classification elements;
the initial classification, the correlated image label, the correlated image component, and the category. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A client-server system operable to process images, the system comprising:
-
a client (202), the client (202) comprising; a receiving module operable to receive a user image (506); a client image processing module (212) operable to assign an initial classification to the user image, wherein the initial classification is based on temporal data associated with the user image (506); a server (204), the server (204) comprising; a server communication module (222) operable to receive the user image (506) from the client (202); a scene detector (404) operable to identify an image label that globally describes the user image (506) and further operable to calculate a label correctness value for the image label; an object identifier (406) operable to recognize an image component (508, 510) of the user image (506) and further operable to calculate a component correctness value for the image component (508, 510); a correlation module (408) operable to correlate the image label and the image component (508, 510) using the label correctness value and the component correctness value, and further operable to identify a correlated image label and a correlated image component; a categorization module (412) operable to apply a rule in order to determine a category of the user image (506), wherein the rule is based on at least one of the following;
the temporal data, the correlated image label, and the correlated image component; anda final classification module operable to produce a final classification based on the initial classification, the correlated image label, the correlated image component and the category; wherein the server communication module (222) is further operable to send the following to the client;
the final classification and a reference to the user image (506).
-
Specification