Input object classification

• US 9,411,445 B2
• Filed: 06/27/2013
• Issued: 08/09/2016
• Est. Priority Date: 06/27/2013
• Status: Expired due to Fees

• Current Assignee: Synaptics Incorporated
• Original Assignee: Synaptics Incorporated
• Inventors: Kuan, Chia-yun, Kumar, Shwetank
• Primary Examiner(s): Eisen, Alexander
• Assistant Examiner(s): Sarma, Abhishek
• Application Number:
  US13/929,514
• Publication Number:
  US 20150002405A1
• Time in Patent Office: 1,139 Days
• Field of Search: 345173-178, 324/679
• US Class Current: 1/1
• CPC Class Codes: G06F 18/24155 Bayesian classification
• CPC Class Codes: G06F 2203/04101 2.5D-digitiser, i.e. digitiser detecting the X/Y position of the input means, finger or stylus, also when it does not touch, but is proximate to the digitiser's interaction surface and also measures the distance of the input means within a short range in the Z direction, possibly with a separate measurement setup
• CPC Class Codes: G06F 3/041 Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
• CPC Class Codes: G06F 3/0445 using two or more layers of sensing electrodes, e.g. using two layers of electrodes separated by a dielectric layer
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 40/1306 non-optical, e.g. ultrasonic or capacitive sensing

Abstract

A processing system for an input device includes a sensor module and a determination module. The sensor module includes sensor circuitry coupled to transmitter electrodes and receiver electrodes. The sensor module is configured to transmit transmitter signals with the transmitter electrode and receive resulting signals with the receiver electrodes. The determination module is configured to obtain a set of measurements for an input object detected in a sensing region of the input device from a capacitive image, and perform, based on the set of measurements, a multistage classification to obtain a classification result identifying a type of the input object. wherein the capacitive image is generated based on the resulting signals.

Claims

1. A processing system for an input device comprising:

a sensor module comprising sensor circuitry configured to be coupled to a plurality of transmitter electrodes and a plurality of receiver electrodes, wherein the sensor module is configured to transmit transmitter signals with the plurality of transmitter electrodes and receive resulting signals with the plurality of receiver electrodes; and

a determination module configured to;

obtain a set of measurements for an input object detected in a sensing region of the input device from a capacitive image, wherein the capacitive image is generated based on the resulting signals, and

perform, based on the set of measurements, a multistage classification to obtain a classification result identifying a type of the input object, wherein the multistage classification comprises;

a first classification using a first subset of the set of measurements to obtain a first output,

wherein the first classification selects, as the first output, a single subset of types from a first subset of types and a second subset of types, the first subset of types being disjoint from the second subset of types,

wherein the first subset of types comprises a finger and a palm,

wherein the second subset of types comprises a pointer instrument and a hovering palm, and

wherein the first subset of the set of measurements comprises a maximum slope, wherein the maximum slope is a maximum difference in value between adjacent pixels in the input object as represented in the capacitive image; and

a second classification using a second subset of the set of measurements, wherein the second classification comprises;

a first step performed based on the first output to obtain a second output, and

a second step performed based on the second output, wherein the second step comprises;

 

calculating a set of results of a plurality of decision functions using an average pixel value of the input object, the plurality of decision functions defined for each type in the single subset of types, and

 

selecting an optimal result from the set of results,

wherein the multistage classification distinguishes between each of a plurality of types comprising the pointer instrument, the hovering palm, the palm, and the finger, and

wherein the type of the input object is at least one of the plurality of types.

2. The processing system of claim 1, wherein the second step is performed only when the second output is the finger.

3. The processing system of claim 1, wherein the first subset of the set of measurements is different than the second subset of the set of measurements.

4. The processing system of claim 1, wherein the first subset of the set of measurements further comprises a maximum pixel value of the input object as represented in the capacitive image.

5. The processing system of claim 1, wherein the second subset of the set of measurements comprises an area of the input object and width.

6. The processing system of claim 1, wherein the first step comprises a Bayesian analysis of area of the input object, and the second step comprises:

obtaining a fisher linear discriminant of area and average pixel value, and

performing a Bayesian analysis of the fisher linear discriminant.

7. The processing system of claim 1, wherein the classification result further comprises a confidence level.

8. A method for classifying a type of input object, the method comprising:

obtaining a set of measurements for an input object detected in a sensing region of the input device from a capacitive image, wherein the capacitive image is generated based on resulting signals obtained by a sensor module; and

performing, based on the set of measurements, a multistage classification to obtain a classification result identifying the type of the input object, wherein performing the multistage classification comprises;

classifying the input object into a single subset of types using a first subset of the set of measurements,

wherein the single subset of types is selected from a first subset of types and a second subset of types, the first subset of types being disjoint from the second subset of types,

wherein the first subset of types comprises a finger and a palm,

wherein the second subset of types comprises a pointer instrument and a hovering palm, and

wherein the first subset of the set of measurements comprises a maximum slope, wherein the maximum slope is a maximum difference in value between adjacent pixels in the input object as represented in the capacitive image; and

classifying the input object to identify the type using a second subset of the set of measurements, wherein classifying the input object to identify the type comprises;

performing a first step based on the single subset of types to obtain an output, and

performing a second step based on the output, wherein the second step comprises;

 

calculating a set of results of a plurality of decision functions using an average pixel value of the input object, the plurality of decision functions defined for each type in the single subset of types, and

 

selecting an optimal result from the set of results,

wherein the multistage classification distinguishes between each of a plurality of types comprising the pointer instrument, the hovering palm, the palm, and the finger, and

wherein the type of input object is at least one of the plurality of types.

9. The method of claim 8, wherein the first subset of the set of measurements are different than the second subset of the set of measurements.

10. The method of claim 8, wherein the first subset of the set of measurements further comprises a maximum pixel value of the input object as represented in the capacitive image.

11. The method of claim 8, wherein the second subset of the set of measurements comprises an area of the input object and width.

12. The method of claim 8, wherein the second step is performed only when the second output is the finger.

13. The method of claim 8, wherein the first step comprises a Bayesian analysis of area of the input object, and the second step comprises:

obtaining a fisher linear discriminant of area and average pixel value, and

performing a Bayesian analysis of the fisher linear discriminant.

14. The method of claim 8, wherein the classification result further comprises a confidence level.

15. An input device comprising:

a plurality of transmitter electrodes configured to transmit transmitter signals;

a plurality of receiver electrodes configured to receive resulting signals from the plurality of transmitter signals; and

a processing system configured to;

obtain a set of measurements for an input object detected in a sensing region of the input device from a capacitive image, wherein the capacitive image is generated based on the resulting signals, and

perform, based on the set of measurements, a multistage classification to obtain a classification result identifying a type of the input object, wherein the multistage classification comprises;

a first classification using a first subset of the set of measurements to obtain a first output,

wherein the first classification selects, as the first output, a single subset of types from a first subset of types and a second subset of types, the first subset of types being disjoint from the second subset of types,

wherein the first subset of types comprises a finger and a palm,

wherein the second subset of types comprises a pointer instrument and a hovering palm, and

wherein the first subset of the set of measurements comprises a maximum slope, wherein the maximum slope is a maximum difference in value between adjacent pixels in the input object as represented in the capacitive image; and

a second classification using a second subset of the set of measurements, wherein the second classification comprises;

a first step performed based on the first output to obtain a second output, and

a second step performed based on the second output, wherein the second step comprises;

 

calculating a set of results of a plurality of decision functions using an average pixel value of the input object, the plurality of decision functions defined for each type in the single subset of types, and

 

selecting an optimal result from the set of results,

wherein the multistage classification distinguishes between each of a plurality of types comprising the pointer instrument, the hovering palm, the palm, and the finger, and

wherein the type of input object is at least one of the plurality of types.

16. The input device of claim 15, wherein the second step is performed only when the second output is the finger.

17. The input device of claim 15, wherein the first subset of the set of measurements further comprises a maximum pixel value of the input object as represented in the capacitive image.

18. The input device of claim 15, wherein the second subset of the set of measurements comprises an area of the input object and width.

19. The input device of claim 15, wherein the first step comprises a Bayesian analysis of area of the input object, and the second step comprises:

obtaining a fisher linear discriminant of area and average pixel value, and

performing a Bayesian analysis of the fisher linear discriminant.

20. The input device of claim 15, wherein the classification result further comprises a confidence level.