EP0183347A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Video image recognition system
Assignee: AT&T Inc
•
Filing: 1985-09-17
•
Granted: —
•
Expires: 2005-09-17
Abstract
Abstract An image recognition system (FIG. 1) uses feature or attribute matching (104) for fast coarse selection of a group of reference images which closely resemble an unknown image and thereafter selects the best refernce imae match from that group using 2-dimensional intensity correlation or template matching (105). The system provides highly accurate image recognition without resorting to time consuming exhaustive search by template matching.
Inventors
- 👤 Arun Narayan Netravali
- 👤 Jakub Seqen
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 14:11
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/24; G06V30/248; G06V30/2504
Claims Analysis
Total Claims: 15
Claim 1
Independent Claim
132 words
A method of operating an image recognition system CHARACTERIZED BY segmenting a video image into two or more regions based on variations in intensity in said video image; screening the characteristics of each of said regions by comparing attributes of selected features of regions with reference features stored in an attribute memory and identifying one or more sets of reference features from said attribute memory which closely resemble the set of features computed from each region; retrieving one or more reference images for each region from an image memory using addresses from the screening and identifying step, and aligning and matching the intensity of each of said regions against the intensity of each of the retrieved reference images for that region to determine one reference image which most closely matches that region.
Claim 2
Independent Claim
132 words
A method of operating an image recognition system CHARACTERIZED BY segmenting a video image into two or more regions based on variations in intensity in said video image; screening the characteristics of each of said regions by comparing attributes of selected features of regions with reference features stored in an attribute memory and identifying one or more sets of reference features from said attribute memory which closely resemble the set of features computed from each region; retrieving one or more reference images for each region from an image memory using addresses from the screening and identifying step, and aligning and matching the intensity of each of said regions against the intensity of each of the retrieved reference images for that region to determine one reference image which most closely matches that region.
Claim 3
Dependent Claim
32 words
The method of claim 1 wherein said system includes positional information associated with said reference images, said system further CHARACTERIZED BY retrieving the positional information using the address of said reference image.
Claim 4
Dependent Claim
20 words
The method of claim 1 CHARACTERIZED IN THAT said segmenting step includes an edge following algorithm to identify the regions.
Claim 5
Dependent Claim
20 words
The method of claim 1 CHARACTERIZED IN THAT said segmenting step includes a difference thresholding algorithm to identify the regions.
Claim 6
Dependent Claim
20 words
The method of claim 1 CHARACTERIZED IN THAT said segmenting step includes an image thresholding algorithm to identify the regions.
Claim 7
Dependent Claim
25 words
The method of claim 1 wherein said attributes is CHARACTERIZED BY one or more attributes from a list of local feature attributes or global attributes.
Claim 8
Dependent Claim
24 words
The method of claim 1 wherein said screening and identifying step are CHARACTERIZED BY a hierarchical classification method for identifying sets of reference features.
Claim 9
Dependent Claim
32 words
The method of claim 1 wherein said aligning and matching step is CHARACTERIZED BY a two dimensional normalized correlation to determine the degree of match between the reference image and the region.
Claim 10
Dependent Claim
36 words
The method of claim 1 wherein said aligning and matching step is CHARACTERIZED BY an occluded image matching algorithm to determine the degree of match between a reference image and an occluded object in that region.
Claim 11
Dependent Claim
15 words
The method of claim 1 CHARACTERIZED IN THAT the image memory has fast sequential access.
Claim 12
Dependent Claim
15 words
The method of claim 10 CHARACTERIZED IN THAT the image memory has slow random access.
Claim 13
Dependent Claim
15 words
The method of claim 11 CHARACTERIZED IN THAT the image memory is a video disc.
Claim 14
Dependent Claim
136 words
An image recognition system CHARACTERIZED BY means for segmenting a video image into two or more regions based on variations in intensity in said video image; means for screening the characteristics of each of said regions by comparing attributes of selected features of regions with reference features stored in an attribute memory and identifying one or more sets of reference features from said attribute memory which closely resemble the set of features computed from each region; means for retrieving one or more reference images for each region from an image memory using addresses from the screening and identifying step, and means for aligning and matching the intensity of each of said regions against the intensity of each of the retrieved reference images for that region to determine one reference image which most closely matches that region.
Claim 15
Dependent Claim
136 words
An image recognition system CHARACTERIZED BY means for segmenting a video image into two or more regions based on variations in intensity in said video image; means for screening the characteristics of each of said regions by comparing attributes of selected features of regions with reference features stored in an attribute memory and identifying one or more sets of reference features from said attribute memory which closely resemble the set of features computed from each region; means for retrieving one or more reference images for each region from an image memory using addresses from the screening and identifying step, and means for aligning and matching the intensity of each of said regions against the intensity of each of the retrieved reference images for that region to determine one reference image which most closely matches that region.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.