JP2016177343A - Signal processing apparatus, input device, signal processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To identify whether a touch sensor has been input by a touch with a finger of a user or other causes.SOLUTION: A signal processing apparatus identifying whether the touch sensor has been input by a touch or not, on the basis of a signal obtained from the touch sensor includes: detection value acquisition means which acquires sensor data formed of a plurality of sensor detection values, from the touch sensor having a plurality of sensors; key point determination means which determines a key point indicating a touch position, from the sensor data; feature quantity calculation means which calculates feature quantity of the key point, from a partial area including the key point; an identifier which has learned a feature quantity to be obtained by a touch and a feature quantity to be obtained by others than the touch; and identifying means which identifies whether the touch sensor has been input by a touch or not, by use of the feature quantity calculated by the feature quantity calculation means.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a technique for identifying whether an input to a touch sensor is a touch.

  Conventionally, an input device using a touch sensor has been widely used. Touchpads are widely used in notebook computers and the like, and in recent years, they are also used in remote operation devices that perform operations such as vehicle car navigation systems, audio, and air conditioners. A touch panel (touch screen) is used in a smart phone, a tablet terminal, a car navigation system, or the like.

  Patent Document 1 discloses a technique for automatically correcting a shift between a touch position intended by a user and a detection position detected by the input apparatus in an input apparatus using a touch panel. Specifically, the user's touch panel operation is recorded and learned by estimating the user's physical characteristics such as how to hold the input device, the size of the finger, the dominant hand, and the user's touch habit. By doing so, the touch position intended by the user is estimated.

  Patent Document 2 discloses a touch sensor that can accurately detect a touch position even when there is electrical noise emitted from a display panel. In Patent Document 2, a shield electrode that shields the display panel and the electrode of the touch sensor is used, and the configuration of the shield electrode is devised to suppress erroneous detection of the touch position due to noise while keeping the touch sensor thin. ing.

JP 2008-242958 A JP 2014-164327 A

  According to the technique disclosed in Patent Document 1, it is possible to increase the detection accuracy of the touch position. However, if the influence of noise cannot be removed when noise is applied to the touch sensor, the touch sensor erroneously detects the touch even though the user is not performing a touch operation.

  According to the technique of Patent Literature 2, it is possible to suppress erroneous detection when electrical noise is applied. However, there are various factors other than electrical noise that cause erroneous detection of the touch sensor. For example, a touch that is not intended by the user is erroneously detected when a water droplet or a metal touches the touch sensor, or when the user's palm touches the touch sensor without intention. End up.

  In view of the above problems, an object of the present invention is to identify whether an input to a touch sensor is due to a touch by a user's finger or due to other factors.

In order to achieve the above object, a signal processing apparatus according to an aspect of the present invention includes the following arrangement. That is, a signal processing device according to an aspect of the present invention indicates a detection value acquisition unit that acquires sensor data including detection values of a plurality of sensors from a touch sensor having a plurality of sensors, and indicates a touch position from the sensor data. From the key point determining means for determining the key point, the feature amount calculating means for calculating the feature amount of the key point from the partial area including the key point, the feature amount obtained by touch and the feature amount obtained by other than touch in advance And a learning discriminator, and a discriminating unit that discriminates whether or not an input to the touch sensor is a touch using the feature amount calculated by the feature amount calculating unit.

  The discriminator is created in advance by a learning process using, as teacher data, a feature amount of sensor data obtained by a user's touch and a feature amount of sensor data obtained by other than the touch. In this way, by using a discriminator that has been learned and generated in advance by supervised learning, it is possible to identify whether or not the input is due to a user's touch based on sensor data obtained from the touch sensor.

  The feature amount of the sensor data in the present invention can be calculated based on gradients in a plurality of directions of detected values in a partial region including key points. The gradient in the plurality of directions may be, for example, 4 directions or 8 directions, but may be other.

  The feature amount of the sensor data in the present invention may be calculated based on a weighted sum of gradient information composed of gradients in a plurality of directions for each sensor included in the partial region including the key point. The weights in the weighted sum are preferably made different according to the gradient direction. For example, for the gradient in the right direction, the sum is calculated only for the sensor located on the right side (left side) of the key point and the sensor located at the same left and right position as the key point, and weighted for the sensor located on the left side (right side) of the key point. To zero or minus. As for the upward gradient, only the sensor above and below the key point and the sensor at the same vertical position as the key point are summed, and the sensor below the key point (upper side) Sets the weight to zero or negative.

  In addition, the feature amount of the sensor data in the present invention is preferably calculated based on the time change of the sensor data. The time change of the sensor data can be expressed as a difference between the present time and sensor data before a predetermined time. With respect to the difference between the present time and the sensor data before a predetermined time, the feature amount can be calculated using the gradient as described above. Also, the feature amount can be calculated using a difference between the gradient obtained from the current sensor data and the gradient obtained from the sensor data a predetermined time ago. The dynamic characteristics of the touch motion can be expressed by taking into account the time change of the sensor data.

  Further, the feature amount in the present invention may be a combination of values respectively obtained from a plurality of partial areas.

  The partial areas having a plurality of sizes are preferably rectangular areas having different sizes around the key point. Although the size of the finger and the way of touch differ depending on the user, the feature amount is calculated using partial areas of a plurality of sizes, so that it can be accurately identified regardless of the size of the user's finger and the way of touch.

  The touch sensor includes a plurality of row direction electrodes and a plurality of column direction electrodes, and the partial region includes a plurality of columns having a predetermined width in the row direction or a plurality of predetermined widths in the column direction. It is also preferable that it includes at least one of regions composed of rows. When the sensor detection value is acquired by scanning each electrode, and the electromagnetic noise is applied to the touch sensor, the sensor detection value varies with a specific pattern corresponding to the scanning method. Therefore, application of electromagnetic noise can be detected with high accuracy by employing the above-described region.

  Moreover, it is also preferable that the key point determining means in the present invention determines a position where the detected value has a maximum value within an area of a predetermined size as the key point.

  Further, the signal processing device according to the present invention further includes a threshold determination unit that determines whether or not a detection value of each sensor is equal to or greater than a threshold, and the key point determination unit determines that a detection value smaller than the threshold is a key point. It is also preferred that no be detected. By this threshold processing, even when electromagnetic noise is applied and the sensor detection value takes the maximum value due to the influence of the noise, it can be determined that it is not a key point.

  Another aspect of the present invention is an input device including a touch sensor having a plurality of sensors and the signal processing device.

  The present invention can be understood as a signal processing apparatus including at least a part of the above means. The present invention can also be understood as a signal processing method for executing at least a part of the processing performed by the above means. The present invention can also be understood as a computer program for causing a computer to execute this method, or a computer-readable storage medium in which this computer program is stored non-temporarily. Each of the above means and processes can be combined with each other as much as possible to constitute the present invention.

  According to the present invention, it is possible to identify whether the input to the touch sensor is due to touch by a user's finger or due to other factors.

It is a figure which shows the functional block of an input device provided with a touch sensor. It is a figure which shows the structure of a touch sensor and a signal acquisition part. It is a flowchart which shows the flow of a discriminator preparation process. It is a flowchart which shows the flow of the identification process of sensor data. It is a flowchart which shows the flow of a keypoint extraction process. It is a flowchart which shows the flow of a feature-value acquisition process. It is a figure explaining a feature-value acquisition process. It is a figure explaining the detection area set around a key point in the case of feature-value acquisition. It is a figure explaining the differential filter for acquiring the brightness | luminance gradient of a sensor detector. It is a figure explaining the weighting coefficient at the time of calculating a weighted average gradient vector. It is a figure explaining another example of a detection area.

(First embodiment)
<Configuration>
The input device 1 according to the present embodiment will be described with reference to FIGS. As illustrated in FIG. 1, the input device 1 according to the present embodiment includes a touch sensor 10 and a micro control unit (MCU) 20.

  In the present embodiment, a projected capacitive touch sensor is used as the touch sensor 10. The touch sensor 10 may be a touch pad or a touch screen (touch panel) used in combination with a display panel.

The MCU 20 includes a processor (arithmetic unit), a memory, an input / output interface, and the like, and when the processor executes a program stored in the memory, the signal acquisition unit 21, the key point extraction unit 22, the feature amount acquisition unit 23, and the identification The functions of the device 24 and the output unit 25 are provided. The MCU 20 may provide functions other than the above functions. Note that some or all of these functions may be realized by a dedicated circuit such as an ASIC.

  FIG. 2 is a diagram showing the configuration of the touch sensor 10 and the signal acquisition unit 21 in detail. The touch sensor 10 includes a plurality of column direction electrodes X0 to X9 and a plurality of row direction electrodes Y0 to Y9 arranged in a matrix. Each intersection of the column direction electrodes X0 to X9 and the row direction electrodes Y0 to Y9 constitutes a capacitor. When the user touches the touch sensor 10, the capacitance of the capacitor at the touch position changes, so that the touch position can be detected based on the charge / discharge current accompanying the change in the capacitance. That is, the touch sensor 10 is a mutual capacitive touch sensor. The capacitor formed at the intersection of the column direction electrode and the row direction electrode is regarded as a sensor for detecting a touch, and the touch sensor 10 can be said to be a touch sensor having a plurality of sensors.

  Here, the number of column-direction electrodes and the number of row-direction electrodes is assumed to be ten, but the number may be arbitrary, and the number of row-direction electrodes and column-direction electrodes does not need to be the same. Moreover, although the shape of the electrode is shown as a rectangle (strip shape) here, a rhombus electrode may be used.

  The column direction electrodes X0 to X9 are connected to the drive unit 211 of the signal acquisition unit 21 through wiring, and the row direction electrodes Y0 to Y9 are connected to the detection unit 212 of the signal acquisition unit 21 through wiring. The drive unit 211 generates a drive signal in accordance with a control signal from the controller 213, selects the column direction electrodes X0 to X9 one by one, and applies the drive signal. The detection unit 212 selects the row direction electrodes Y0 to Y9 one by one in accordance with the control signal from the controller 213, and flows to the row direction electrodes Y0 to Y9 according to the drive signal applied to the column direction electrodes X0 to X9. Charge / discharge current is acquired as an output signal. The detection unit 212 detects the capacitance of the capacitor configured at the intersection of the column direction electrodes X0 to X9 and the row direction electrodes Y0 to Y9 based on output signals acquired from the row direction electrodes Y0 to Y9. The detection signal indicating the capacitance of each capacitor is output. Hereinafter, the capacitance value of each capacitor is referred to as a sensor detection value, and data including sensor detection values of all capacitors is referred to as sensor data.

  The MCU 20 determines from the sensor detection value acquired by the signal acquisition unit 21 from the touch sensor 10 whether or not an input by a user's touch operation has been performed, and obtains and outputs a touch position when the touch operation has been performed. Do

<Processing>
Hereinafter, processing performed by the MCU 20 will be described. The processing content is divided into a learning phase and an identification phase. The learning phase is a stage in which the discriminator 24 is created by supervised learning using sensor data obtained by a user's touch and data obtained by noise other than touch. The identification phase is a stage in which it is determined whether or not the input to the touch sensor 10 is due to a touch using the classifier 24.

[1. Learning phase]
FIG. 3 is a flowchart showing the flow of classifier creation processing in the learning phase. Below, although this process is demonstrated as what MCU20 performs, you may perform the said process with apparatuses other than MCU20.

First, the MCU 20 acquires sensor data from the touch sensor 10 via the signal acquisition unit 21 (S101), and correct data indicating whether the input to the touch sensor 10 is due to a user's touch or noise. Is acquired (S102). Here, it is assumed that the correct data is acquired after the sensor data is acquired, but this order may be reversed. Alternatively, sensor data may be acquired from the touch sensor 10 in advance, stored in association with correct answer data, and sensor data and correct answer data may be acquired simultaneously by reading these data.

[[Keypoint extraction process]]
Next, the key point extraction unit 22 acquires key points (feature points) from the sensor data (S103). Details of the key point extraction processing S103 are shown in FIG. In the key point extraction process S103, the following steps S301 to S303 are performed on all pixels (positions) (loop L1). Since sensor data is a set of detection values (capacitance changes) of a plurality of sensors (capacitors) arranged in a matrix, hereinafter, the position of the sensor detection value in the sensor data is also referred to as a pixel. The term pixel is also used when referring to a sensor corresponding to a sensor detection value. For example, an adjacent pixel refers to a sensor adjacent to a certain sensor.

  The key point extraction unit 22 determines whether or not the sensor detection value is greater than or equal to a threshold value (S301). If the sensor detection value at the target position is less than the threshold value (S301-NO), it is determined that the target pixel is not a key point. On the other hand, if the sensor detection value of the target pixel is equal to or greater than the threshold value (S301-YES), the key point extraction unit 22 determines whether the sensor detection value of the target pixel is a maximum value in a predetermined peripheral region centered on the position. It is determined whether or not (S302). If the sensor detection value of the target pixel is not the maximum value (S302-NO), it is determined that the target pixel is not a key point. On the other hand, if the sensor detection value of the target pixel has a maximum value (S302-YES), the key point extraction unit 22 extracts the pixel as a key point (S303).

  Note that the threshold value in the threshold processing of step S301 is a value that can be determined that touch input is not performed on the touch sensor 10 if the sensor detection value is less than that. In order to prevent omission of touch detection, the threshold value is preferably not excessively increased.

  In addition, the size of the predetermined peripheral area in the local maximum determination in step S302 may be determined by the resolution of the touch sensor 10, and may be a square area having a size of 3 × 3 or 5 × 5, for example.

[[Feature value calculation processing]]
When key points are extracted, the feature amount acquisition unit 23 calculates feature amounts for the respective key points (S104). FIG. 6 is a flowchart showing the flow of the feature quantity calculation process S104, and FIG. 7 is a diagram for explaining the feature quantity calculation process S104. In the feature amount calculation processing S104, as shown in FIG. 7, a plurality of detection areas D1 to Dn are set for one key point K, and average gradient vectors G1 to Gn of sensor detection values are calculated for each detection area. Then, the feature amount S is calculated from these average gradient vectors.

The feature amount acquisition process S104 will be described in detail with reference to the flowchart of FIG. The feature amount is calculated for each of the key points detected in step S103 (loop L2). The feature amount acquisition unit 23 sets a detection area having a plurality of sizes with the key point as a center for the key point to be processed. FIG. 8 shows an example of the detection area. FIG. 8A shows a detection area D1 having a size of 3 × 3 with the key point K as the center. FIG. 8B shows a detection area D2 having a size of 5 × 5 with the key point K as the center. The reason for setting the detection areas having a plurality of sizes in this manner is that the range in which the capacitance changes varies depending on the size of the user's finger and the manner of touching. FIG. 8C shows sensor data when touched with a thin finger, and FIG. 8D shows sensor data when touched with a thick finger. By setting a detection area corresponding to a plurality of touching methods and acquiring a feature amount based on the detection area, the feature can be accurately expressed by any finger or touching method.

  Here, only two detection areas are shown as examples, but the number n of detection areas set in step S401 may be any number. The range in which the capacitance changes depending on the touch varies depending on the assumed finger size, touch heel, and the like. A detection area corresponding to each range may be set according to an assumed input. The number n of detection areas may be 1.

  In addition, here, a square centering on the processing target key point is given as an example of the detection area. However, the detection area is not necessarily a square, and may be any shape such as a rectangle (rectangle), a circle, or an ellipse. Also good. Further, the direction of the detection area may be changed according to the gradient direction at the key point.

  Next, the feature quantity acquisition unit 23 executes the processes of steps S402 to S403 for each set detection area (loop L3). The feature amount acquisition unit 23 calculates gradient information (gradient vector) including gradients in eight directions for each pixel in the detection area (S402). 9A to 9C show examples of differential filters for calculating the right direction gradient, the upward direction gradient, and the upper right direction gradient, respectively. Here, the difference between the sensor detection value at a position away from the predetermined number of pixels in the gradient direction to be calculated and the sensor detection value at the key point is calculated as the gradient value in the gradient direction. In this example, two pixels are adopted as the predetermined number of pixels, but the value of an adjacent pixel may be used, or the value of a pixel separated by three or more may be used. The predetermined number of pixels may be changed according to the size of the detection area. Further, here, the forward difference is adopted, but a backward difference or a central difference may be adopted. A Sobel filter, a pre-witt filter, or the like may be employed.

The feature quantity acquisition unit 23 calculates a weighted average gradient vector of the gradient information (gradient vector) obtained for all positions in the detection area (S403). The weighted average gradient vector for the detection area Dn is a vector having as an element the weighted average of the gradient values for each direction, as shown in the following equation.

Here, g ₀ (x, y) to g ₇ (x, y) are gradient values in eight directions at the position (x, y). w _{0 to} w ₇ are weighting factors for each of the eight directions. The sum (sigma) covers the entire detection area Dn.

  A different value (pattern) is used for the weighting factor for each gradient direction. For example, with respect to the rightward gradient, as shown in FIG. 10B, the weight coefficient is set to 1 only for pixels that are the same as the x position of the key point or on the left side, and the other pixels are set to 0. The sensor detection value has a maximum at a key point as shown in FIG. FIG. 10 is a diagram showing sensor detection values obtained from the sensor at the same y position as the key point, with the key point as the center. Therefore, the sign of the right gradient value is reversed between the right side and the left side of the key point. Therefore, it is possible to prevent the gradient values having different signs from being canceled by averaging the gradient values only for the pixels that are the same as the x position of the key point or the left side thereof. Regarding the right gradient, the same effect can be obtained even if the weighting factor is set to 1 only for pixels that are the same as the x position of the key point or on the right side, and the other pixels are set to 0. Although the weighting factors are 1 and 0 here, a value between 0 and 1 may be adopted.

When the average gradient vector is calculated for all the detection areas, the feature amount acquisition unit 23 calculates the feature amount of the key point from these average gradient vectors (S404). Here, as shown in the following formula, a vector obtained by combining elements of the average gradient vector obtained for each detection area is defined as a feature amount S.

[[Classifier generation processing]]
In the learning process in step S105, the touch sensor is obtained by performing machine learning using the feature amount obtained from the sensor data of the touch input and the feature amount obtained from the sensor data of noise acquired as described above. A discriminator is created that identifies whether the input to is due to touch. As the discriminator, any known method such as a neural network, a support vector machine (SVM), a subspace method, or discriminant analysis can be adopted. The discriminator 24 is generated by the learning process in step S105.

[2. Identification phase]
FIG. 4 is a flowchart showing the flow of sensor data processing in the identification phase. This process is performed by the MCU 20.

  The MCU 20 acquires sensor data from the touch sensor 10 via the signal acquisition unit 21 (S201). The key point extraction unit 22 extracts key points from the sensor data (S202). The key point extraction process is the same as the process in the learning process (FIG. 5), and thus description thereof is omitted. When key points are extracted, the feature amount acquisition unit 23 calculates feature amounts for the respective key points (S203). Since the feature amount calculation process is the same as the process in the learning process (FIGS. 6 and 7, etc.), the description thereof is omitted.

  Next, the feature quantity calculated for each key point is input to the discriminator 24, and it is identified whether or not this feature quantity is obtained by touch input (S204). When it is determined that the result of the identification process is “touch input” (S204—YES), the MCU 20 executes a process when a touch operation is performed (S206). Specifically, an output with the position of the key point as the touch position is output from the output unit 25, and processing corresponding to this touch operation is executed. On the other hand, when the identification result is not “touch input” (S204—NO), the MCU 20 executes processing when noise is detected (S207). Typically, the sensor data is ignored and no processing is performed.

<Advantageous effects of this embodiment>
According to the present embodiment, it can be determined whether the input to the touch sensor is due to a user touch or due to noise. At this time, detection areas of a plurality of sizes corresponding to the assumed finger size etc. are set around the key point, and the gradient of the sensor detection value obtained from each is used as the feature amount. Whether the input is touch input or not can be identified with high accuracy regardless of the size of the screen or the wrinkle of the touch. Therefore, erroneous detection can be prevented even when electromagnetic noise is applied to the touch sensor or water wetness occurs.

  Further, when acquiring a touch position candidate (key point), a position where the sensor detection value is equal to or greater than the threshold value is detected, and a position where the sensor detection value becomes maximum due to noise can be excluded. Note that it is not necessary to exclude all maximum values based on noise by this threshold processing. Since it is possible to discriminate between touch and noise by processing using the discriminator at the subsequent stage, the threshold for key point extraction may be reduced.

  Moreover, since noise (including electromagnetic noise) can be detected by signal processing, erroneous detection can be suppressed even if the shield performance of the touch sensor is not high. Therefore, erroneous detection can be suppressed even when an inexpensive touch sensor is used.

(Second Embodiment)
The second embodiment is basically the same as the first embodiment, but the detection area that is set when acquiring the feature amount is different from that of the first embodiment. In the second embodiment, as shown in FIG. 8, a square detection area centered on the key point is used. In the present embodiment, as shown in FIG. 11A, an area corresponding to a plurality of columns of column direction electrodes including key points and having a predetermined width in the row direction is used as a detection area. Although FIG. 11A shows a detection area having a width of three rows, the width of the detection area may be other than three rows. Further, as in the first embodiment, a plurality of detection areas having different widths may be employed.

  The advantage of adopting such a detection area will be described. When electromagnetic noise is applied to the touch sensor 10, the capacitance of the touch sensor changes even when there is no touch input, and the sensor detection value has a value corresponding to the electromagnetic noise. FIG. 11B shows sensor detection values when electromagnetic noise is applied. The intensity of the electromagnetic noise varies with time, and the touch sensor 10 reads the sensor detection value for each selected column, so that a predetermined sensor detection value can be obtained for each column direction electrode even when there is no input by touch. Therefore, by setting the detection area to be an area composed of a plurality of column electrodes, it is possible to accurately represent the characteristics when electromagnetic noise is applied, and to detect the application of electromagnetic noise more accurately.

  Note that a region corresponding to a plurality of row-direction electrodes including key points and having a predetermined width in the column direction may be used as the detection area. Even if the detection area is set in this way, for the same reason as described above, it is possible to accurately represent the feature when electromagnetic noise is applied as a feature amount, and to detect the application of electromagnetic noise more accurately. be able to.

  The feature amount may be obtained using only the detection area composed of a plurality of column-direction electrodes or row-direction electrodes described in this embodiment, or in addition to the square detection area used in the first embodiment. You may use the detection area demonstrated by the form. It is also preferable to use each of a plurality of square detection areas used in the first embodiment, a detection area composed of a plurality of columns, and a detection area composed of a plurality of rows used in the present embodiment. By using a plurality of types of detection areas, the amount of calculation increases, but it is possible to identify touch input and noise more accurately.

(Third embodiment)
The third embodiment is basically the same as the first embodiment, but the feature amount calculation method is different from that of the first embodiment. In the first embodiment, the feature amount is obtained based only on the sensor data acquired at a certain time point. However, in the present embodiment, the feature amount is calculated using the sensor data before a predetermined time. The sensor data before a predetermined time may be sensor data one frame before, or may be sensor data several frames before.

  In the present embodiment, a feature amount calculation process (FIG. 6) similar to that of the first embodiment is executed for the difference between the current sensor data and the sensor data a predetermined time ago (for example, one frame before). , Get feature values for key points. Note that the key point extraction processing is performed based on the current sensor data as in the first embodiment.

Note that the feature amount may be acquired only from the time change of the sensor data described in the present embodiment, or the feature amount may be acquired from both the current sensor data itself and the time change of the sensor data. In the latter case, vector information obtained by combining the weighted average gradient vector obtained from the current sensor data and the weighted average gradient vector obtained from the temporal change of the sensor data may be used as the feature amount.

  In the above description, the feature amount is calculated by performing the feature amount calculation process described in the first embodiment on the difference between the current sensor data and the sensor data before a predetermined time. The feature amount may be calculated by another method as long as it reflects the change. For example, the feature amount calculation process described in the first embodiment may be performed on each of the current sensor data and the sensor data before a predetermined time, and the temporal change (difference) of the obtained result may be used as the feature amount. .

  According to the present embodiment, by using time-series changes in sensor data, not only the shape of the touch but also the temporal change in the shape of the touch can be acquired as a feature amount, and the dynamic characteristics of the touch operation can be expressed. .

(Fourth embodiment)
In the first embodiment, the discriminator identifies only whether the input to the touch sensor is due to touch or noise, but in this embodiment, the cause of noise is also identified. Factors of noise include, for example, electromagnetic noise, contact of conductors such as water droplets and metal, and unintended contact of the palm. However, noise factors other than those listed here can be assumed, and those listed here may be classified more finely or larger.

  In the present embodiment, for each of the above factors and touch input, a feature amount may be calculated based on sensor data obtained from the touch sensor, and supervised learning may be performed to create a discriminator. The classifier may be one multi-class classifier or a plurality of two-class classifiers.

  According to the present embodiment, it is possible not only to determine that the input to the touch sensor is due to a factor other than touch, but also to understand what factor other than touch occurs. Therefore, in the present embodiment, in the noise detection process S207 that is performed when it is determined that the input to the touch sensor is a factor other than touch, a process according to the noise factor can be performed. For example, when it is determined by the discriminator that contact with water droplets has occurred, the user can be instructed to wipe the water of the touch sensor.

(Other)
The above embodiments can be appropriately combined and implemented within a technically consistent range. Further, the present invention can be implemented with appropriate modifications within the scope of the technical idea of the present invention.

  In the above description, the projected capacitive touch sensor has been described as an example. However, any touch sensor that can obtain a plurality of detection signals according to the touch area for one touch can be used. A sensor is available. For example, a touch sensor including a plurality of independent contact sensors can be used in the present invention.

  The feature value calculation method described above is merely an example, and other feature values may be employed. For example, SIFT feature values, SURF feature values, HoG feature values, and the like can be employed.

  In the above description, the signal processing for the sensor data obtained from the touch sensor is described as being performed in the microcontroller. However, when the input device using the touch sensor is connected to a computer, the above signal is used. Processing may be performed by a CPU included in the computer. For example, a device driver may perform the above signal processing.

1: Input device 10: Touch sensor 20: MCU (micro control unit)
21: Signal acquisition unit 22: Key point extraction unit 23: Feature amount acquisition unit 24: Discriminator 25: Output unit

Claims (13)

A signal processing device for identifying whether or not an input to a touch sensor is based on a touch from a signal obtained from the touch sensor,
Detection value acquisition means for acquiring sensor data consisting of detection values of the plurality of sensors from a touch sensor having a plurality of sensors;
Key point determination means for determining a key point indicating a touch position from the sensor data;
A feature amount calculating means for calculating a feature amount of the key point from a partial region including the key point;
Using a discriminator previously learned from a feature quantity obtained by touch and a feature quantity obtained by other than touch, and a feature quantity calculated by the feature quantity calculation means, it is discriminated whether or not the input to the touch sensor is a touch. Identification means for
A signal processing apparatus comprising: The feature amount is calculated based on gradients in a plurality of directions of detection values in the partial region.
The signal processing apparatus according to claim 1. The feature amount is calculated based on a weighted sum of gradient information including gradients in a plurality of directions for each sensor included in the partial region.
The signal processing apparatus according to claim 2. The feature amount is calculated based on a time change of the sensor data.
The signal processing apparatus according to claim 1. The feature amount is composed of a combination of values respectively obtained from a plurality of partial areas.
The signal processing device according to claim 1. The partial areas of the plurality of sizes include rectangular areas having different sizes around the key points.
The signal processing apparatus according to claim 5. The touch sensor comprises a plurality of row direction electrodes and a plurality of column direction electrodes,
The partial region includes at least one of a region composed of a plurality of columns having a predetermined width in the row direction and a region composed of a plurality of rows having a predetermined width in the column direction.
The signal processing apparatus according to claim 5 or 6. The key point determination means determines a position where the detected value has a maximum value in an area of a predetermined size as the key point.
The signal processing device according to claim 1. Further comprising a threshold determination means for determining whether or not the detection value of each sensor is equal to or greater than a threshold;
The key point determination means does not detect a detection value smaller than the threshold as a key point;
The signal processing device according to claim 1. The discriminator is for discriminating whether the feature amount is obtained by touch or a plurality of factors other than touch,
The identification means identifies a factor of input to the touch sensor;
The signal processing device according to claim 1. A touch sensor having a plurality of sensors;
A signal processing device according to any one of claims 1 to 10,
An input device comprising: A signal processing method performed by a signal processing device for identifying whether an input to a touch sensor is a touch input from a signal obtained from a touch sensor,
A detection value acquisition step of acquiring sensor data consisting of detection values of the plurality of sensors from a touch sensor having a plurality of sensors;
A key point determination step for determining a key point indicating a touch position from the sensor data;
A feature amount calculating step of calculating a feature amount of the key point from a partial region including the key point;
Using a discriminator previously learned from a feature quantity obtained by touch and a feature quantity obtained by other than touch, and a feature quantity calculated in the feature quantity calculation step, it is discriminated whether or not the input to the touch sensor is a touch. An identification step to
Including a signal processing method.   The program for making a computer perform each step of the method of Claim 12.

Images