Recordation of handwriting and hand movement using electromyography

• US 20070140562A1
• Filed: 12/19/2006
• Published: 06/21/2007
• Est. Priority Date: 12/21/2005
• Status: Active Grant

• Current Assignee: Michael Linderman
• Original Assignee: Michael Linderman
• Inventors: Linderman, Michael
• Granted Patent: US 8,280,169 B2
• Time in Patent Office: Days
• US Class Current: 382/187
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32

Abstract

Handwriting activity is recorded by use of electromyography (EMG) signals detected from muscles at several locations on the hand. The EMG signals are sensed and registered. The sensed signals are processed and stored, after which the signals are analyzed to reconstruct handwriting activity into a digital format. Machine edible text is generated and displayed along with a graphical depiction of the handwriting.

Claims

1. A method to record and/or reconstruct 3D motion images of a moving hand using electromyography (EMG) signals.

2. The method of claim 1, comprising:

using data acquisition apparatus, data processing apparatus and a handwriting reconstruction routine to reconstruct handwriting activity in a digital format by applying a pattern classification and recognition algorithm to the EMG signals, said algorithm used in conjunction with pattern recognition;

using a set of sensors, at least a subset of which mounted as sensor electrodes to a mini glove; and

providing a routine that generates machine editable text.

3. A method for rendering intelligence based on sensed hand movements, the method comprising:

sensing electromyography (EMG) signals from the set of sensors;

interpreting the EMG signals to reconstruct a plurality of movements associated with writing activity to render a pattern of strokes corresponding to handwriting activity;

rendering an output from the plurality of movements; and

storing the rendered output.

4. The method of claim 3 wherein the interpreting the EMG signals includes using a pattern classification and recognition algorithm to provide the rendered output.

5. The method of claim 3 further comprising matching the corresponding textual component with reconstructed text patterns.

6. The method of claim 3 further comprising a modifying the interpretation in accordance with user corrections of previously generated outputs.

7. The method of claim 3 further comprising a modifying the generation of the concordance between the generated plurality of probabilities in accordance with user corrections of previously generated outputs.

8. A system for reconstructing handwriting activity to a digital format, the system comprising:

a user interface including a glove with a plurality of sensors thereon, including sensors capable of electromyography (EMG) detection of muscle activity in the fingers;

a sense interpreter receiving EMG signals from the sensors as sensed hand movement data;

a unit generating a reconstruction of line movements corresponding to the sensed hand movement data;

a recognition unit coupled to respond to said unit generating a reconstruction of line movements, capable of convening said scribe movements into corresponding computer recognizable codes in said sequential order, each of said codes representing a corresponding textual component.

9. The system of claim 8 further comprising:

the recognition unit implementing a pattern classification and recognition algorithm to reconstruct scribe movements corresponding to hand movements;

the recognition unit including a handwriting recognition module capable of providing the corresponding textual component.

10. The system of claim 9 further comprising an editing module capable of matching the corresponding textual component with text patterns.

11. The system of claim 9 further comprising a training module capable of modifying the recognition unit in accordance with user corrections of previously generated outputs.

12. The system of claim 8 further comprising:

the recognition unit including a mapping module, capable of converting the reconstructed scribe movements to a format corresponding to handwriting patterns;

the recognition unit including a handwriting recognition module capable of providing the corresponding textual component.

13. A method to record a handwriting activity, comprising:

registering electromyography (EMG) signals from one or more muscles at selected locations;

a routine that processes and stores said signals in memory for the purposes of handwriting recording;

a routine that analyzes said signals and reconstructs handwritten text and/or drawing in a digital format;

a routine that generates machine-editable text;

a routine that displays at least one of either a combination of handwritten text and machine editable text or drawing on a computer device;

14. Machine readable digital media including instructions for the routines as set forth in claim 13.

15. A system to record a handwriting activity, comprising:

means for registration of electromyography (EMG) signals from one or more muscles at selected locations; and

means for reconstructing at least one of either a combination of handwritten text and machine editable text or a drawing to a digital format from said EMG signals;

means for generating a display corresponding to the digital format.

16. The system of claim 15 wherein said means for generating a display corresponding to the digital format generates a display of machine-editable text corresponding to the digital format and in the case of a drawing generates the drawing in an editable format.

17. The system of claim 15 wherein;

the means for registration of EMG signals comprises sensors, electrodes, amplifiers, bandpass filters, multiplexer, analog to digital converter, processing unit; and

the means for registration of EMG signals includes a routine to improve signal to noise ratio.

18. The system of claim 17 wherein the processing unit includes data processing equipment including a central processing unit and a memory unit suitable for data processing.

19. The system of claim 15 comprising a thin mini glove for housing the means for registration, processing, and storing of EMG signals to record a handwriting activity.

20. A system for reconstructing handwriting activity to a digital format of claim 15, wherein the means for registration comprises a processor provided as a chipset including at least one monolithic integrated circuit, the processor executing the routine that reconstructs.