Syntactic Signal Recognizer and Pattern Recognizer

• US 20080025614A1
• Filed: 07/24/2007
• Published: 01/31/2008
• Est. Priority Date: 07/25/2006
• Status: Active Grant

• Current Assignee: James Corey Wright, Kenneth J. Hintz
• Original Assignee: James Corey Wright, Kenneth J. Hintz
• Inventors: Wright, James Corey, Hintz, Kenneth J.
• Granted Patent: US 8,358,809 B2
• Time in Patent Office: Days
• US Class Current: 382/189
• CPC Class Codes: G01S 13/885 for ground probing prospecting or detecting using electromagnetic waves G01V3/12
• CPC Class Codes: G01S 7/411 Identification of targets based on measurements of radar reflectivity G01S7/415 takes precedence
• CPC Class Codes: G01V 3/12 operating with electromagnetic waves operating with millimetre waves G01V8/005

Abstract

A pattern recognizer includes a sequential data extractor, a data pairer, and a recognition engine. The sequential data extractor extracts a region of measured data obtained from a measuring device. The measuring device is preferably capable of detecting changes in impedance. The measured data should contain position information of the changes in impedance. The data pairer associates the region of measured data with a priori pattern data that contains expected positions of the changes in impedance. The recognition engine decides whether the associated region of measured data and the a priori pattern data differ within predetermined criteria, the predetermined criteria including: non-expected impedance changes; excessive dither; and missing impedance changes.

Claims

1. ) A pattern recognizer comprising:

a) a sequential data extractor configured to extract a region of measured data from measured data, the measured data obtained using a measuring device, the measuring device capable of detecting changes in impedance, the measured data containing position information of the changes in impedance;

b) a data pairer configured to;

i) receive the region of measured data from the sequential data extractor;

ii) receive a priori pattern data, the a priori pattern data containing expected positions of the changes in impedance;

iii) associate the region of measured data and the a priori pattern data;

c) a recognition engine having a decision output, the decision output configured to indicate whether the associated region of measured data and the a priori pattern data differ within predetermined criteria, the predetermined criteria including;

i) non-expected impedance changes;

ii) excessive dither; and

iii) missing impedance changes.

2. ) The pattern recognizer according to claim 1, wherein the recognition engine is a reset finite state machine.

3. ) The pattern recognizer according to claim 1, wherein the recognition engine is a serial major-minor reset finite state machine.

4. ) The pattern recognizer according to claim 1, wherein the recognition engine is a parallel correlator.

5. ) The pattern recognizer according to claim 1, wherein the changes in impedance is a multitude of changes in impedance.

6. ) The pattern recognizer according to claim 1, wherein the pattern recognizer is implemented in a programmable logic device.

7. ) The pattern recognizer according to claim 1, wherein the pattern recognizer is implemented using a series of executable modules, each of the executable modules is embodied in a tangible computer-readable medium as a series of computer readable instructions.

8. ) The pattern recognizer according to claim 1, wherein the pattern recognizer is implemented using a tangible computer-readable medium containing a series of computer readable synthesizable modules, each of the synthesizable modules including a series of hardware description language instructions used to generate digital logic.

9. ) The pattern recognizer according to claim 1, wherein the measuring device is at least one of the following:

a) a RADAR;

b) a ground penetrating RADAR;

c) a high range resolution RADAR;

d) a synthetic aperture RADAR;

e) a sonar;

f) an ultrasonic imaging device;

g) an infrared sensor device;

h) an X-ray device; and

i) a backscatter X-ray device.

10. ) A method of pattern recognition comprising:

a) extracting a region of measured data from measured data, the measured data derived from a measuring device, the measuring device capable of detecting changes in impedance, the measured data containing position information of the changes in impedance;

b) associating the region of measured data and a priori pattern data, the a priori pattern data containing the expected positions of the changes in impedance; and

c) making a decision that indicates whether the associated region of measured data and the a priori pattern data differ within a predetermined criteria, the predetermined criteria including;

i) unanticipated changes in impedance;

ii) missing changes in impedance; and

iii) differences in the expected positions of the changes in impedance.

11. ) The method according to claim 10, wherein at least part of the decision is made using a reset finite state machine.

12. ) The method according to claim 10, wherein at least part of the decision is made using a serial major-minor reset finite state machine.

13. ) The method according to claim 10, wherein at least part of the decision is made using a parallel correlator.

14. ) The method according to claim 10, wherein the changes in impedance is a multitude of changes in impedance.

15. ) The method according to claim 10, wherein the method is implemented in a programmable logic device.

16. ) The method according to claim 10, wherein the method is implemented as a series of executable modules, each of the executable modules embodied on a tangible computer readable medium as a series of computer readable instructions.

17. ) The method according to claim 10, wherein the measuring device is at least one of the following:

a) a RADAR;

b) a ground penetrating RADAR;

c) a high range resolution RADAR;

d) a synthetic aperture RADAR;

e) a sonar;

f) an ultrasonic imaging device;

g) an infrared sensor device;

h) an X-ray device; and

i) a backscatter X-ray device.

18. ) A tangible computer-readable medium containing a series of computer readable instructions that when executed by one or more processors performs the method of claim 10.

19. ) A tangible computer-readable medium containing a series of computer readable synthesizable modules, each of the synthesizable modules including a series of hardware description language instructions used to generate digital logic, the digital logic configured to perform the method of claim 10.

20. ) A pattern recognizer comprising:

a) a sequential data extractor configured to extract a region of measured data from measured data, the measured data derived from a measuring device, the measuring device capable of detecting changes in the measured data, the measured data containing position information of the changes in the measured data;

b) a data pairer configured to;

i) receive the region of measured data from the sequential data extractor;

ii) receive a priori pattern data, the a priori pattern data containing expected positions of the changes in the measured data;

iii) generating paired data by associating the region of measured data and the a priori pattern data;

c) a recognition engine having;

i) an input, the input configured to receive the paired data; and

ii) a decision output, the decision output configured to indicate whether the associated region of measured data and the a priori pattern data differ within a predetermined criteria, the predetermined criteria including;

(1) non-expected changes in the measured data in the paired data;

(2) excessive dither in the paired data; and

(3) missing impedance changes in the paired data.

21. ) The method according to claim 20, wherein the recognition engine is a reset finite state machine.

22. ) The method according to claim 20, wherein the recognition engine is a parallel correlator.