Method for the reduction of image content redundancy in large image databases
First Claim
1. A method of increasing information content for content-based image retrieval (CBIR) systems, comprising the steps of:
- providing a CBIR database, said database comprising an index for a plurality of stored digital images using a plurality of feature vectors, said feature vectors corresponding to distinct descriptive characteristics of said images, said characteristics comprising defects of said images, anomalies of said images, or both;
calculating a visual similarity parameter value based on a degree of visual similarity between features vectors of an incoming image being considered for entry into said database and feature vectors associated with a most similar of said stored images;
determining whether to store said feature vectors associated with said incoming image in said database based on said visual similarity parameter value;
when said incoming image and said feature vectors associated with said incoming image are stored in said database, determining for at least one among said incoming image and one or more associated feature vectors a storage lifetime based on said visual similarity parameter value, the storage lifetime indicating when the at least one among said incoming image and one or more associated feature vectors is deleted from said database; and
maintaining said CBIR database by deleting stored digital images from said CBIR database based on said storage lifetime associated with said stored digital image,wherein if said visual similarity parameter value of said incoming image is less than or equal to a first threshold value, assigning a short-term value to said storage lifetime associated with said incoming image;
wherein if said visual similarity parameter value of said incoming image is greater than or equal to a second threshold value, assigning a long-term value to said storage lifetime associated with said incoming image; and
wherein if said visual similarity parameter value of said incoming image is between said first threshold value and said second threshold value, assigning an intermediate-term value to said storage lifetime associated with said incoming image, wherein said second threshold value is greater than said first threshold value.
2 Assignments
0 Petitions
Accused Products
Abstract
A method of increasing information content for content-based image retrieval (CBIR) systems includes the steps of providing a CBIR database, the database having an index for a plurality of stored digital images using a plurality of feature vectors, the feature vectors corresponding to distinct descriptive characteristics of the images. A visual similarity parameter value is calculated based on a degree of visual similarity between features vectors of an incoming image being considered for entry into the database and feature vectors associated with a most similar of the stored images. Based on said visual similarity parameter value it is determined whether to store or how long to store the feature vectors associated with the incoming image in the database.
-
Citations
17 Claims
-
1. A method of increasing information content for content-based image retrieval (CBIR) systems, comprising the steps of:
-
providing a CBIR database, said database comprising an index for a plurality of stored digital images using a plurality of feature vectors, said feature vectors corresponding to distinct descriptive characteristics of said images, said characteristics comprising defects of said images, anomalies of said images, or both; calculating a visual similarity parameter value based on a degree of visual similarity between features vectors of an incoming image being considered for entry into said database and feature vectors associated with a most similar of said stored images; determining whether to store said feature vectors associated with said incoming image in said database based on said visual similarity parameter value; when said incoming image and said feature vectors associated with said incoming image are stored in said database, determining for at least one among said incoming image and one or more associated feature vectors a storage lifetime based on said visual similarity parameter value, the storage lifetime indicating when the at least one among said incoming image and one or more associated feature vectors is deleted from said database; and maintaining said CBIR database by deleting stored digital images from said CBIR database based on said storage lifetime associated with said stored digital image, wherein if said visual similarity parameter value of said incoming image is less than or equal to a first threshold value, assigning a short-term value to said storage lifetime associated with said incoming image; wherein if said visual similarity parameter value of said incoming image is greater than or equal to a second threshold value, assigning a long-term value to said storage lifetime associated with said incoming image; and wherein if said visual similarity parameter value of said incoming image is between said first threshold value and said second threshold value, assigning an intermediate-term value to said storage lifetime associated with said incoming image, wherein said second threshold value is greater than said first threshold value. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A content-based image retrieval (CBIR) system, comprising:
-
at least one processor for extracting a plurality of feature vectors from a digital image, said feature vectors corresponding to particular descriptive characteristics of said image, the processor for implementing a clustering method to index said feature vectors into a hierarchical search tree; a database storing said feature vectors associated with a plurality of said digital images communicably coupled to an image storage manager module, said image storage module identifying a visual similarity parameter value based on a degree of visual similarity between features vectors of an incoming digital image being considered for entry into said database and feature vectors of a most similar of said plurality of said digital images, and determining whether to store said incoming said feature vectors associated with said incoming image in said database based on said visual similarity parameter value; and wherein the processor retrieves at least one of said stored images, said processor for retrieving at least on image having feature vectors comparably related to said feature vectors associated with said query image wherein the processor determines for at least one among said incoming image and one or more associated feature vectors a storage lifetime based on said visual similarity parameter value when said incoming image and said feature vectors associated with said incoming image are stored in said database, the storage lifetime indicating when the at least one among said incoming image and one or more associated feature vectors is deleted from said database, wherein the processor maintains said database by deleting stored digital images from said database based on said storage lifetime associated with said stored digital image, wherein if said visual similarity parameter value of said incoming image is less than or equal to a first threshold value, said processor assigns said storage lifetime associated with said incoming image with a short-term value; wherein if said visual similarity parameter value of said incoming image is greater than or equal to a second threshold value, said processor assigns said storage lifetime associated with said incoming image with a long-term value; and wherein if said visual similarity parameter value of said incoming image is between said first threshold value and said second threshold value, said processor assigns said storage lifetime associated with said incoming image with an intermediate-term value, wherein said second threshold value is greater than said first threshold value. - View Dependent Claims (15, 16, 17)
-
Specification