US7194114B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Object finder for two-dimensional images, and system for determining a set of sub-classifiers composing an object finder
Assignee: Carnegie Mellon University
•
Filing: 2002-10-07
•
Granted: 2007-03-20
•
Expires: 2022-10-07
Abstract
Abstract Systems and methods for determining a set of sub-classifiers for a detector of an object detection program are presented. According to one embodiment, the system may include a candidate coefficient-subset creation module, a training module in communication with the candidate coefficient-subset creation module, and a sub-classifier selection module in communication with the training module. The candidate coefficient-subset creation module may create a plurality of candidate subsets of coefficients. The coefficients are the result of a transform operation performed on a two-dimensional (2D) digitized image, and represent corresponding visual information from the 2D image that is localized in space, frequency, and orientation. The training module may train a sub-classifier for each of the plurality of candidate subsets of coefficients. The sub-classifier selection module may select certain of the plurality of sub-classifiers. The selected sub-classifiers may comprise the components of the detector. Also presented are systems and methods for detecting instances of an object in a 2D (two-dimensional) image.
Inventors
- 👤 Henry Schneiderman
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 12:15
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/20; G06V10/255; G06F; G06F18/00; G06F18/20; G06F18/21; G06F18/214; G06V10/40; G06V10/52; G06V30/00; G06V30/10; G06V30/24; G06V30/248; G06V30/2504
Claims Analysis
Total Claims: 64
Claim 1
Independent Claim
102 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: a candidate coefficient-subset creation module for creating a plurality of candidate subsets of coefficients that are statistically related through a selection process using object and non-object training examples based on the statistical dependencies within each of the plurality of candidate subsets; a training module in communication with the candidate coefficient-subset creation module for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and a sub-classifier selection module in communication with the training module for selecting certain of the plurality of sub-classifiers.
Claim 2
Independent Claim
102 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: a candidate coefficient-subset creation module for creating a plurality of candidate subsets of coefficients that are statistically related through a selection process using object and non-object training examples based on the statistical dependencies within each of the plurality of candidate subsets; a training module in communication with the candidate coefficient-subset creation module for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and a sub-classifier selection module in communication with the training module for selecting certain of the plurality of sub-classifiers.
Claim 3
Dependent Claim
27 words
The system of claim 1 , wherein the plurality of candidate subsets of coefficients comprise a plurality of candidate subsets of wavelet coefficients that are statistically related.
Claim 4
Dependent Claim
95 words
The system of claim 1 , wherein the candidate coefficient-subset creation module is for creating a plurality of candidate subsets of coefficients by: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 5
Dependent Claim
67 words
The system of claim 1 , wherein the sub-classifier selection module is for selecting certain of the plurality of sub-classifiers by: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 6
Dependent Claim
18 words
The system of claim 4 , wherein the first test is less computationally intensive than the second set.
Claim 7
Dependent Claim
24 words
The system of claim 1 , wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly.
Claim 8
Independent Claim
79 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: means for creating a plurality of candidate subsets of coefficients that are statistically related through a selection process using object and non-object training examples based on the statistical dependencies within each of the plurality of candidate subsets; means for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and means for selecting certain of the plurality of sub-classifiers.
Claim 9
Independent Claim
79 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: means for creating a plurality of candidate subsets of coefficients that are statistically related through a selection process using object and non-object training examples based on the statistical dependencies within each of the plurality of candidate subsets; means for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and means for selecting certain of the plurality of sub-classifiers.
Claim 10
Dependent Claim
27 words
The system of claim 7 , wherein the plurality of candidate subsets of coefficients includes a plurality of candidate subsets of wavelet coefficients that are statistically related.
Claim 11
Dependent Claim
95 words
The system of claim 7 , wherein the means for selecting certain of the plurality of candidate subsets of coefficients includes means for: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 12
Dependent Claim
69 words
The system of claim 7 , wherein the means for selecting certain of the plurality of candidate sub-classifiers of coefficients includes means for: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 13
Dependent Claim
18 words
The system of claim 10 , wherein the first test is less computationally intensive than the second test.
Claim 14
Dependent Claim
24 words
The system of claim 7 , wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly.
Claim 15
Dependent Claim
82 words
A computer readable medium having stored thereon instructions, which, when executed by a processor, cause the processor to: create a plurality of candidate subsets of coefficients that are statistically related through a selection process using object and non-object training examples based on the statistical dependencies within each of the plurality of candidate subsets; train a sub-classifier for a detector of an object detection program for each of the plurality of candidate subsets of coefficients; and select certain of the plurality of sub-classifiers.
Claim 16
Dependent Claim
82 words
A computer readable medium having stored thereon instructions, which, when executed by a processor, cause the processor to: create a plurality of candidate subsets of coefficients that are statistically related through a selection process using object and non-object training examples based on the statistical dependencies within each of the plurality of candidate subsets; train a sub-classifier for a detector of an object detection program for each of the plurality of candidate subsets of coefficients; and select certain of the plurality of sub-classifiers.
Claim 17
Dependent Claim
27 words
The medium of claim 13 , wherein the plurality of candidate subsets of coefficients comprise a plurality of candidate subsets of wavelet coefficients that are statistically related.
Claim 18
Dependent Claim
102 words
The medium of claim 13 , having further stored thereon instructions which when executed by the processor, cause the processor to create a plurality of candidate subsets of coefficients by: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 19
Dependent Claim
75 words
The medium of claim 13 , having further stored thereon instructions which when executed by the processor, cause the processor to select certain of the plurality of sub-classifiers by: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 20
Dependent Claim
18 words
The medium of claim 16 , wherein the first test is less computationally intensive than the second set.
Claim 21
Dependent Claim
30 words
The medium of claim 13 , having further stored thereon instructions which when executed by the processor cause the processor to select the non-object training examples by bootstrapping and randomly.
Claim 22
Independent Claim
73 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients that are statistically related through a selection process using object and non-object training examples based on the statistical dependencies within each of the plurality of candidate subsets; training a sub-classifier for each of the plurality of candidate subsets of coefficients; and selecting certain of the plurality of sub-classifiers.
Claim 23
Independent Claim
73 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients that are statistically related through a selection process using object and non-object training examples based on the statistical dependencies within each of the plurality of candidate subsets; training a sub-classifier for each of the plurality of candidate subsets of coefficients; and selecting certain of the plurality of sub-classifiers.
Claim 24
Dependent Claim
27 words
The method of claim 19 , wherein the plurality of candidate subset of coefficients includes a plurality of candidate subsets of wavelet coefficients that are statistically related.
Claim 25
Dependent Claim
88 words
The method of claim 19 , wherein creating a plurality of candidate subset of coefficients includes: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 26
Dependent Claim
61 words
The method of claim 19 , wherein selecting certain of the plurality of sub-classifiers includes: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 27
Dependent Claim
18 words
The method of claim 22 , wherein the first test is less computationally intensive than the second set.
Claim 28
Dependent Claim
31 words
The method of claim 19 , wherein training a sub-classifier for each of the plurality of candidate subsets of coefficients includes providing lighting correction after evaluation of an overcomplete wavelet transformation.
Claim 29
Dependent Claim
24 words
The method of claim 19 , wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly.
Claim 30
Independent Claim
164 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: a candidate coefficient-subset creation module for creating a plurality of candidate subsets of coefficients; a training module in communication with the candidate coefficient-subset creation module for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and a sub-classifier selection module in communication with the training module for selecting certain of the plurality of sub-classifiers, wherein the candidate coefficient-subset creation module is for creating a plurality of candidate subsets of coefficients by: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 31
Independent Claim
164 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: a candidate coefficient-subset creation module for creating a plurality of candidate subsets of coefficients; a training module in communication with the candidate coefficient-subset creation module for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and a sub-classifier selection module in communication with the training module for selecting certain of the plurality of sub-classifiers, wherein the candidate coefficient-subset creation module is for creating a plurality of candidate subsets of coefficients by: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 32
Dependent Claim
67 words
The system of claim 26 , wherein the sub-classifier selection module is for selecting certain of the plurality of sub-classifiers by: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 33
Dependent Claim
18 words
The system of claim 27 , wherein the first test is less computationally intensive than the second set.
Claim 34
Dependent Claim
22 words
The system of claim 27 , wherein the training module is for training the set of sub-classifiers based on non-object training examples.
Claim 35
Dependent Claim
24 words
The system of claim 29 , wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly.
Claim 36
Independent Claim
136 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: a candidate coefficient-subset creation module for creating a plurality of candidate subsets of coefficients; a training module in communication with the candidate coefficient-subset creation module for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and a sub-classifier selection module in communication with the training module for selecting certain of the plurality of sub-classifiers, wherein the sub-classifier selection module is for selecting certain of the plurality of sub-classifiers by: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 37
Independent Claim
136 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: a candidate coefficient-subset creation module for creating a plurality of candidate subsets of coefficients; a training module in communication with the candidate coefficient-subset creation module for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and a sub-classifier selection module in communication with the training module for selecting certain of the plurality of sub-classifiers, wherein the sub-classifier selection module is for selecting certain of the plurality of sub-classifiers by: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 38
Independent Claim
94 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: a candidate coefficient-subset creation module for creating a plurality of candidate subsets of coefficients; a training module in communication with the candidate coefficient-subset creation module for training a sub-classifier for each of the plurality of candidate subsets of coefficients based on non-object training examples that include non-object training examples selected by bootstrapping and non-object training examples selected randomly; and a sub-classifier selection module in communication with the training module for selecting certain of the plurality of sub-classifiers.
Claim 39
Independent Claim
94 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: a candidate coefficient-subset creation module for creating a plurality of candidate subsets of coefficients; a training module in communication with the candidate coefficient-subset creation module for training a sub-classifier for each of the plurality of candidate subsets of coefficients based on non-object training examples that include non-object training examples selected by bootstrapping and non-object training examples selected randomly; and a sub-classifier selection module in communication with the training module for selecting certain of the plurality of sub-classifiers.
Claim 40
Independent Claim
141 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: means for creating a plurality of candidate subsets of coefficients; means for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and means for selecting certain of the plurality of sub-classifiers, wherein the means for selecting certain of the plurality of candidate subsets of coefficients includes means for: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 41
Independent Claim
141 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: means for creating a plurality of candidate subsets of coefficients; means for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and means for selecting certain of the plurality of sub-classifiers, wherein the means for selecting certain of the plurality of candidate subsets of coefficients includes means for: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 42
Independent Claim
115 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: means for creating a plurality of candidate subsets of coefficients; means for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and means for selecting certain of the plurality of sub-classifiers, wherein the means for selecting certain of the plurality of candidate sub-classifiers of coefficients includes means for: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 43
Independent Claim
115 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: means for creating a plurality of candidate subsets of coefficients; means for training a sub-classifier for each of the plurality of candidate subsets of coefficients; and means for selecting certain of the plurality of sub-classifiers, wherein the means for selecting certain of the plurality of candidate sub-classifiers of coefficients includes means for: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 44
Independent Claim
75 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: means for creating a plurality of candidate subsets of coefficients; means for training a sub-classifier for each of the plurality of candidate subsets of coefficients based on non-object training examples, wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly; and means for selecting certain of the plurality of sub-classifiers.
Claim 45
Independent Claim
75 words
A system for determining a set of sub-classifiers for a detector of an object detection program, comprising: means for creating a plurality of candidate subsets of coefficients; means for training a sub-classifier for each of the plurality of candidate subsets of coefficients based on non-object training examples, wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly; and means for selecting certain of the plurality of sub-classifiers.
Claim 46
Dependent Claim
128 words
A computer readable medium having stored thereon instructions, which, when executed by a processor, cause the processor to: create a plurality of candidate subsets of coefficients by: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion; train a sub-classifier for a detector of an object detection program for each of the plurality of candidate subsets of coefficients; and select certain of the plurality of sub-classifiers.
Claim 47
Dependent Claim
128 words
A computer readable medium having stored thereon instructions, which, when executed by a processor, cause the processor to: create a plurality of candidate subsets of coefficients by: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion; train a sub-classifier for a detector of an object detection program for each of the plurality of candidate subsets of coefficients; and select certain of the plurality of sub-classifiers.
Claim 48
Dependent Claim
102 words
A computer readable medium having stored thereon instructions, which, when executed by a processor, cause the processor to: create a plurality of candidate subsets of coefficients; train a sub-classifier for a detector of an object detection program for each of the plurality of candidate subsets of coefficients; and select certain of the plurality of sub-classifiers by: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 49
Dependent Claim
102 words
A computer readable medium having stored thereon instructions, which, when executed by a processor, cause the processor to: create a plurality of candidate subsets of coefficients; train a sub-classifier for a detector of an object detection program for each of the plurality of candidate subsets of coefficients; and select certain of the plurality of sub-classifiers by: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 50
Dependent Claim
69 words
A computer readable medium having stored thereon instructions, which, when executed by a processor, cause the processor to: create a plurality of candidate subsets of coefficients; train a sub-classifier for a detector of an object detection program for each of the plurality of candidate subsets of coefficients based on non-object training examples; select the non-object training examples by bootstrapping and randomly; and select certain of the plurality of sub-classifiers.
Claim 51
Dependent Claim
69 words
A computer readable medium having stored thereon instructions, which, when executed by a processor, cause the processor to: create a plurality of candidate subsets of coefficients; train a sub-classifier for a detector of an object detection program for each of the plurality of candidate subsets of coefficients based on non-object training examples; select the non-object training examples by bootstrapping and randomly; and select certain of the plurality of sub-classifiers.
Claim 52
Independent Claim
128 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients; training a sub-classifier for each of the plurality of candidate subsets of coefficients; and selecting certain of the plurality of sub-classifiers, wherein creating a plurality of candidate subset of coefficients includes: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 53
Independent Claim
128 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients; training a sub-classifier for each of the plurality of candidate subsets of coefficients; and selecting certain of the plurality of sub-classifiers, wherein creating a plurality of candidate subset of coefficients includes: selecting a plurality of subsets of statistically related coefficients based on a statistical relationship between groups of two coefficients in the subsets; selecting a first subset of coefficients from the plurality of subsets of coefficients based on a first criterion; computing a second criterion based on the first criterion and the first subset; and selecting a second subset of coefficients from the plurality of subsets of coefficients based on the second criterion.
Claim 54
Dependent Claim
61 words
The method of claim 39 , wherein selecting certain of the plurality of sub-classifiers includes: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 55
Dependent Claim
18 words
The method of claim 40 , wherein the first test is less computationally intensive than the second set.
Claim 56
Dependent Claim
31 words
The method of claim 41 , wherein training a sub-classifier for each of the plurality of candidate subsets of coefficients includes providing lighting correction after evaluation of an overcomplete wavelet transformation.
Claim 57
Dependent Claim
19 words
The method of claim 42 , wherein training includes training the set of sub-classifiers based on non-object training examples.
Claim 58
Dependent Claim
24 words
The method of claim 43 , wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly.
Claim 59
Independent Claim
101 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients; training a sub-classifier for each of the plurality of candidate subsets of coefficients; and selecting certain of the plurality of sub-classifiers, wherein selecting certain of the plurality of sub-classifiers includes: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 60
Independent Claim
101 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients; training a sub-classifier for each of the plurality of candidate subsets of coefficients; and selecting certain of the plurality of sub-classifiers, wherein selecting certain of the plurality of sub-classifiers includes: performing a first test on the plurality of sub-classifiers; selecting a first set of sub-classifiers based on the first test; performing a second test on the first set of sub-classifiers; and selecting a second set of sub-classifiers from the first set based on the second test.
Claim 61
Independent Claim
71 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients; training a sub-classifier for each of the plurality of candidate subsets of coefficients, wherein training a sub-classifier for each of the plurality of candidate subsets of coefficients includes providing lighting correction after evaluation of an overcomplete wavelet transformation; and selecting certain of the plurality of sub-classifiers.
Claim 62
Independent Claim
71 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients; training a sub-classifier for each of the plurality of candidate subsets of coefficients, wherein training a sub-classifier for each of the plurality of candidate subsets of coefficients includes providing lighting correction after evaluation of an overcomplete wavelet transformation; and selecting certain of the plurality of sub-classifiers.
Claim 63
Independent Claim
69 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients; training a sub-classifier for each of the plurality of candidate subsets of coefficients based on non-object training examples, wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly; and selecting certain of the plurality of sub-classifiers.
Claim 64
Independent Claim
69 words
A method for determining a set of sub-classifiers for a detector of an object detection program, comprising: creating a plurality of candidate subsets of coefficients; training a sub-classifier for each of the plurality of candidate subsets of coefficients based on non-object training examples, wherein the non-object training examples include non-object training examples selected by bootstrapping and non-object training examples selected randomly; and selecting certain of the plurality of sub-classifiers.
References Cited (Backward Citations)
US5533177A
Cited
US5757287A
Cited
US6285393B1
Cited
US5710833A
Cited
US5642431A
Cited
US6154253A
Cited
US6038337A
Cited
US6025879A
Cited
US6081612A
Cited
US6028956A
Cited
US6256411B1
Cited
US6072893A
Cited
US6026189A
Cited
US6128397A
Cited
US6456728B1
Cited
US6421463B1
Cited
US6134339A
Cited
US20010028729A1
Cited
US20020051578A1
Cited
US20020102024A1
Cited
US20060062451A1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2010-03-19 | 2010-09-18 | 2011-03-20 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2014-03-19 | 2014-09-18 | 2015-03-20 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2018-03-19 | 2018-09-18 | 2019-03-20 | $7700.00 | Window Closed / Lapsed |