METHODS AND SYSTEMS FOR REDUCING MEMORY FOOTPRINTS ASSOCIATED WITH CLASSIFIERS

• US 20140079315A1
• Filed: 01/22/2013
• Published: 03/20/2014
• Est. Priority Date: 09/14/2012
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Kozitsky, Vladimir, Burry, Aaron Michael, Paul, Peter
• Granted Patent: US 9,025,865 B2
• Time in Patent Office: Days
• US Class Current: 382/159
• CPC Class Codes: A47C 7/14 of adjustable shape; elastically mounted ; adaptable to a user contour or ergonomic seating positions movably-coupled seat and backrests with elastic adjustment means A47C1/03261; elastically-mounted back-rests or backrest-seat units in the base frame A47C7/44
• CPC Class Codes: B60N 2/02 the seat or part thereof being movable, e.g. adjustable adjustable arm-rests B60N2/75; adjustable head-rests B60N2/806
• CPC Class Codes: B60N 2/02253 characterised by the transmission between the electric motor and the seat or seat parts
• CPC Class Codes: B60N 2/1803 with independent front and/or rear adjustment
• CPC Class Codes: B60N 2/1835 pivoting about an axis located in the front
• CPC Class Codes: B60N 2/1864 Gear wheel driven mechanism
• CPC Class Codes: G06F 18/2113 by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 10/771 Feature selection, e.g. selecting representative features from a multi-dimensional feature space
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/18133 regional/local feature not essentially salient, e.g. local binary pattern

Abstract

Methods and systems for reducing the required footprint of SNoW-based classifiers via optimization of classifier features. A compression technique involves two training cycles. The first cycle proceeds normally and the classifier weights from this cycle are used to rank the Successive Mean Quantization Transform (SMQT) features using several criteria. The top N (out of 512 features) are then chosen and the training cycle is repeated using only the top N features. It has been found that OCR accuracy is maintained using only 60 out of 512 features leading to an 88% reduction in RAM utilization at runtime. This coupled with a packing of the weights from doubles to single byte integers added a further 8× reduction in RAM footprint or a reduction of 68× over the baseline SNoW method.

Claims

1. A method for reducing the required footprints associated with classifiers, said method comprising:

employing classifier weights from a training cycle to rank features utilizing particular criteria;

selecting at least one top feature among said features; and

repeating said training cycle using only said at least one top feature in order to thereafter determine if additional features among said features should be included or excluded to reduce said footprints associated with said classifiers.

2. The method of claim 1 wherein said features comprise SMQT features.

3. The method of claim 1 wherein said classifiers comprise SNoW classifiers.

4. The method of claim 1 further comprising analyzing a classifier matrix associated with said classifiers to determine a relative importance of said features across spatial locations.

5. The method of claim 1 further comprising ranking said features by employing particular criteria.

6. The method of claim 5 wherein said particular criteria comprises a count of non-zero weights with respect to said feature, said feature comprising at least a particular feature plane.

7. The method of claim 5 wherein said particular criteria comprises a mean/median value of weights associated with a feature plane of said feature.

8. The method of claim 5 wherein said particular criteria comprises a highest weight feature plane associated with said feature with respect to at least one pixel location with a highest value of non-zero weight.

18. The processor-readable medium of claim 7 wherein said features comprise SMQT features.

9. A system for reducing the required footprints associated with classifiers, said system comprising:

a processor;

a data bus coupled to said processor; and

a computer-usable medium embodying computer program code, said computer-usable medium being coupled to said data bus, said computer program code comprising instructions executable by said processor and configured for;

employing classifier weights from a training cycle to rank features utilizing particular criteria;

selecting at least one top feature among said features; and

repeating said training cycle using only said at least one top feature in order to thereafter determine if additional features among said features should be included or excluded to reduce said footprints associated with said classifiers.

10. The system of claim 9 wherein said features comprise SMQT features.

11. The system of claim 9 wherein said classifiers comprise SNoW classifiers.

12. The system of claim 9 wherein said instructions are further configured for analyzing a classifier matrix associated with said classifiers to determine a relative importance of said features across spatial locations.

13. The system of claim 9 wherein said instructions are further configured for ranking said features by employing particular criteria.

14. The system of claim 13 wherein said particular criteria comprises a count of non-zero weights with respect to said feature, said feature comprising at least a particular feature plane.

15. The system of claim 13 wherein said particular criteria comprises a mean/median value of weights associated with a feature plane of said feature.

16. The system of claim 13 wherein said particular criteria comprises a highest weight feature plane associated with said feature with respect to at least one pixel location with a highest value of non-zero weight.

17. A processor-readable medium storing code representing instructions to cause a process for reducing the required footprints associated with classifiers, said code comprising code to:

employ classifier weights from a training cycle to rank features utilizing particular criteria;

select at least one top feature among said features; and

repeat said training cycle using only said at least one top feature in order to thereafter determine if additional features among said features should be included or excluded to reduce said footprints associated with said classifiers.

19. The processor-readable medium of claim 17 wherein said classifiers comprise SNoW classifiers.

20. The processor-readable medium of claim 17 wherein said code further comprises code to analyze a classifier matrix associated with said classifiers to determine a relative importance of said features across spatial locations.