Threshold-based comparison
First Claim
1. A method of visual object comparison for a database of visual objects, comprising the steps of:
- a) applying primitives to a first visual object to extract a first feature vector, each primitive providing at least one primitive value to the first feature vector;
b) applying primitives to a second visual object to extract a second feature vector, each primitive providing at least one primitive value to the second feature vector;
c) providing an ordering value for each primitive to order the primitives;
d) comparing one of the primitive values from the first feature vector with the corresponding primitive value of the second feature vector according to the ordering so as to obtain a primitive score;
e) applying a primitive weight to the primitive score to determine a weighted primitive score;
f) summing the weighted primitive score into a summed total score; and
g) repeating steps d-f until the summed total score crosses a selected threshold.
10 Assignments
0 Petitions
Accused Products
Abstract
A system and method for content-based search and retrieval of visual objects. A base visual information retrieval (VIR) engine utilizes a set of universal primitives to operate on the visual objects. An extensible VIR engine allows custom, modular primitives to be defined and registered. A custom primitive addresses domain specific problems and can utilize any image understanding technique. Object attributes can be extracted over the entire image or over only a portion of the object. A schema is defined as a specific collection of primitives. A specific schema implies a specific set of visual features to be processed and a corresponding feature vector to be used for content-based similarity scoring. A primitive registration interface registers custom primitives and facilitates storing of an analysis function and a comparison function to a schema table. A heterogeneous comparison allows objects analyzed by different schemas to be compared if at least one primitive is in common between the schemas. A threshold-based comparison is utilized to improve performance of the VIR engine. A distance between two feature vectors is computed in any of the comparison processes so as to generate a similarity score.
-
Citations
10 Claims
-
1. A method of visual object comparison for a database of visual objects, comprising the steps of:
-
a) applying primitives to a first visual object to extract a first feature vector, each primitive providing at least one primitive value to the first feature vector; b) applying primitives to a second visual object to extract a second feature vector, each primitive providing at least one primitive value to the second feature vector; c) providing an ordering value for each primitive to order the primitives; d) comparing one of the primitive values from the first feature vector with the corresponding primitive value of the second feature vector according to the ordering so as to obtain a primitive score; e) applying a primitive weight to the primitive score to determine a weighted primitive score; f) summing the weighted primitive score into a summed total score; and g) repeating steps d-f until the summed total score crosses a selected threshold. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A software system for visual object comparison of a database of visual objects, the system comprising:
-
means for applying primitives to a first visual object to extract a first feature vector, each primitive providing at least one primitive value to the first feature vector; means for applying primitives to a second visual object to extract a second feature vector, each primitive providing at least one primitive value to the second feature vector; means for providing an ordering value for each primitive to order the primitives; and means for thresholding including; a) comparing one of the primitive values from the first feature vector with the corresponding primitive value of the second feature vector according to the ordering so as to obtain a primitive score, b) applying a primitive weight to the primitive score to determine a weighted primitive score, c) summing the weighted primitive score into a summed total score, and d) repeating a-c until the summed total score meets a selected threshold.
-
-
10. A program storage device storing instructions that when executed by a computer perform a method for a threshold based visual object comparison of a database of visual objects, the method comprising:
-
a) applying primitives to a first visual object to extract a first feature vector, each primitive providing at least one primitive value to the first feature vector; b) applying primitives to a second visual object to extract a second feature vector, each primitive providing at least one primitive value to the second feature vector; c) providing an ordering value for each primitive to order the primitives; d) comparing one of the primitive values from the first feature vector with the corresponding primitive value of the second feature vector according to the ordering so as to obtain a primitive score; e) applying a primitive weight to the primitive score to determine a weighted primitive score; f) summing the weighted primitive score into a summed total score; and g) repeating steps d-f until the summed total score meets a selected threshold.
-
Specification