Method and system for touch shape recognition, related screen apparatus, and computer program product

• US 9,239,643 B2
• Filed: 10/04/2013
• Issued: 01/19/2016
• Est. Priority Date: 10/04/2012
• Status: Active Grant

• Current Assignee: STMicroelectronics SRL (STMicroelectronics NV)
• Original Assignee: STMicroelectronics SRL (STMicroelectronics NV)
• Inventors: Capra, Alessandro, Battiato, Sebastiano, Farinella, Giovanni Maria, Guarneri, Nunziata Ivana, Cristaldi, Francesco
• Primary Examiner(s): OSORIO, RICARDO
• Application Number:
  US14/045,905
• Publication Number:
  US 20140098045A1
• Time in Patent Office: 837 Days
• Field of Search: 345/156, 345173-174
• US Class Current: 1/1
• CPC Class Codes: G06F 2203/04104 Multi-touch detection in digitiser, i.e. details about the simultaneous detection of a plurality of touching locations, e.g. multiple fingers or pen and finger
• CPC Class Codes: G06F 3/041 Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
• CPC Class Codes: G06F 3/0416 Control or interface arrangements specially adapted for digitisers

Abstract

An embodiment of a method of recognizing finger detection data in a detection data map produced by a touch screen includes converting the data from the x, y, z space into a three-descriptor space including: a first coordinate representative of the number of intensity peaks in the map, a second coordinate representative of the number of nodes (i.e., pixels) absorbed under one or more of the intensity peaks. A third coordinate may be selected as the angular coefficient or slope of a piecewise-linear approximating function passing through points having the numbers of nodes absorbed under the intensity peaks ordered in decreasing order over said intensity peaks, which permits singling out finger data with respect to non-finger data over the whole of the touch screen. The third coordinate may be also selected as an adjacency value representative of the extent the intensity peaks are adjacent to one another, which permits singling out finger data produced over a portion of the touch screen with respect to non-finger data produced over another portion of the touch screen.

Claims

1. A method, comprising:

recognizing finger detection data in a detection data map produced by a touch screen, wherein the data are arranged in an (x, y, z) space associating a node having coordinates (x, y) in the data map and a detection intensity value z, the recognizing including,

converting the data from the (x, y, z) space into a three-descriptor space having three coordinates including,

a first coordinate representative of the number of intensity peaks in the map,

a second coordinate representative of the number of nodes absorbed under the intensity peaks, and

a third coordinate selected as either,

an angular coefficient of an approximating line passing through points representative of the numbers of nodes absorbed under the intensity peaks ordered in decreasing order, and

an adjacency value representative of the extent the intensity peaks are adjacent to one another.

2. The method of claim 1, further comprising selecting the third coordinate as the angular coefficient, and at least one of:

selecting the second coordinate as the maximum of the numbers of nodes absorbed under the intensity peaks,

singling out, in the data converted from the (x, y, z) space into the three-descriptor space, finger data with respect to non-finger data over the whole of the touch screen.

3. The method of claim 2, wherein determining the angular coefficient comprises:

ordering the number of nodes absorbed under the intensity peaks as an ordered decreasing series,

approximating the ordered decreasing series with a piecewise-linear approximating function including a plurality of linear portions having respective angular coefficients, and

determining the angular coefficient as the average value of the respective angular coefficients.

4. The method of claim 1, further comprising selecting the third coordinate as the adjacency value representative of the extent the intensity peaks are adjacent to one another, and at least one of:

selecting the second coordinate as either of the number of nodes absorbed under an isolated intensity peak or the sum of the numbers of nodes absorbed under a plurality of adjacent intensity peaks,

singling out, in the data converted from the (x, y, z) space into the three-descriptor space, finger data produced over a portion of the touch screen with respect to non-finger data produced over another portion of the touch screen.

5. The method of claim 4, further comprising distinguishing, in the data converted from the (x, y, z) space into the three-descriptor space:

simple objects having a first coordinate representative of a single intensity peak and a third coordinate representative of the absence of adjacent peaks, and

composed objects having a first coordinate representative of plural intensity peaks and a third coordinate representative the presence of adjacent peaks.

6. The method of claim 5, further comprising determining the third coordinate by:

identifying for the intensity peaks in the detection data map respective sets of nodes absorbed thereunder, whereby each intensity peak and the respective set of absorbed nodes forms a blob,

locating adjacent nodes between the blobs thus formed,

determining adjacency values for the blobs as a function of the number of adjacent nodes thus located.

7. The method of claim 6, further comprising at least one of:

setting to zero the adjacency value for an isolated blob having no adjacent nodes with other blobs,

setting the adjacency value for a plurality of adjacent blobs as the sum of the numbers of adjacent nodes in the adjacent blobs.

8. The method of claim 7, further comprising:

converting from the (x, y, z) space into the three-descriptor space a detection data map produced by a touch screen; and

subjecting the detection data map converted from the (x, y, z) space into the three-descriptor space to a likelihood test with a plurality of test models including models of finger detection data to be recognized as produced in a training phase including conversion from the (x, y, z) space into the three-descriptor space.

9. The method of claim 8, wherein the training phase includes obtaining the test models via fitting through a Gaussian Mixture fitting to model data maps.

10. The method of claim 9, wherein, in the training phase, the fitting follows conversion from the (x, y, z) space into the three-descriptor space.

11. The method of claim 10, wherein the likelihood test comprises a Log-Likelihood test.

12. The method of any of claim 11, wherein the likelihood test comprises:

a plurality of individual tests each resulting in a respective likelihood value with a respective one of the test models;

a maximum likelihood check of the likelihood values resulting from the plurality of individual tests for identifying the one of the individual tests yielding the maximum likelihood value, whereby the test model producing the maximum likelihood value is held to be representative of the data in the detection data map produced by the touch screen.