TWI712920B - Character recognition method and touch control module using the same - Google Patents

Abstract

A character recognition method is suitable for a touch module, wherein the touch module includes a touch screen, a sensing unit, and a calculation unit. The sensing unit is electrically connected to the touch screen, and the calculation unit The sensing unit is electrically connected. The character recognition method includes: the sensing unit detects an initial coordinate of a user's finger touching the touch screen; the calculation unit executes a mark recording step to obtain a turning point coordinate set; the sensing unit detects the The finger leaves an end coordinate of the touch screen; and the calculation unit performs character recognition according to the start coordinate, the turning point coordinate group, and the end coordinate.

Description

Character recognition method and touch control module using the same

The present invention relates to a character recognition method suitable for a touch module, in particular to a character recognition method that strengthens recognition features through turning points.

At present, most gesture or character recognition models on the market are designed based on the direction code recognition method. The model first presets the direction code database of a letter or character based on empirical data, after the user’s finger actually touches the touch screen , Analyze the data of the touch part and determine the direction of the stroke, and get a set of direction code data according to the direction. If the finally collected direction code group completely corresponds to the direction code database of a character, the model will The touch gesture will be recognized as the character. In the above process, it is necessary to decompose the touch data of the finger into vector combinations of the direction code, and compare these vector combinations with the database to determine whether there are corresponding characters. However, due to the complexity of this type of algorithm, it requires high-performance hardware to consume huge computing resources to afford it; in addition, it is easier for different users to start and end pens and special writing habits when writing. Different gesture data needs to be subjected to a limit test to determine whether they are the same character, and similar combinations of direction codes actually belong to two different characters and so on.

In order to solve the above problems, a novel character recognition method is urgently needed in this field.

One purpose of the present invention is to disclose a character recognition method suitable for a touch module, which can enhance recognition features through turning points and reduce misrecognition.

Another object of the present invention is to disclose a touch module, which can enhance recognition features through turning points and reduce false recognition.

To achieve the above objective, a character recognition method suitable for a touch module is proposed. The touch module includes a touch screen, a sensing unit, and a calculation unit. The sensing unit is electrically connected to the touch. The screen is controlled and the computing unit is electrically connected to the sensing unit. The character recognition method includes:

The sensing unit detects an initial coordinate of a user's finger touching the touch screen;

The calculation unit executes a mark recording step to obtain a turning point coordinate group;

The sensing unit detects an end point where the finger leaves the touch screen; and

The calculation unit performs character recognition according to the start coordinate, the turning point coordinate group, and the end coordinate;

Among them, the coordinate recording steps include:

Obtain a previous coordinate, a relay coordinate, and a current coordinate, where the relay coordinate is the coordinate of the finger on the touch screen before the current coordinate one time interval, and the previous coordinate is the relay coordinate before the time interval The coordinates of the finger on the touch screen;

Calculate a first angle according to the previous coordinates and the relay coordinates;

Calculate a second angle based on the relay coordinates and the current coordinates; and

Judging whether a difference between the first angle and the second angle is greater than a threshold;

Wherein, when the difference is greater than the threshold, the calculation unit records the relay coordinates in the turning point coordinate group; when the current coordinates are not equal to the end point coordinates, the calculation unit updates the previous coordinates after the time interval , The relay coordinates, the current coordinates, the first angle, and the second angle.

In an embodiment, the turning point coordinate group includes a plurality of turning point coordinates, and the character recognition method further includes:

Calculate the Euclidean distance between every two adjacent turning point coordinates in the plurality of turning point coordinates; and

Determine whether each Euclidean distance is less than a stroke threshold.

In an embodiment, the turning point coordinate group includes a plurality of turning point coordinates, and the character recognition method further includes:

Calculate an included angle between every three adjacent turning point coordinates in the plurality of turning point coordinates; and

Determine whether each included angle is greater than an included angle threshold.

In an embodiment, calculating the first angle according to the previous coordinates and the relay coordinates includes:

Calculate a first vector from the previous coordinate to the relay coordinate, where the first angle is the angle between the first vector and the horizontal axis.

In an embodiment, calculating the second angle according to the relay coordinates and the current coordinates includes:

Calculate a second vector from the relay coordinate to the current coordinate, where the second angle is the angle between the second vector and the horizontal axis.

To achieve the above objective, the present invention further provides a touch module, which includes a touch screen, a sensing unit and a calculation unit to perform a character recognition method, wherein the sensing unit is electrically connected to the touch screen, And the computing unit is electrically connected to the sensing unit, and the character recognition method includes:

The sensing unit detects an initial coordinate of a user's finger touching the touch screen;

The calculation unit executes a mark recording step to obtain a turning point coordinate group;

The sensing unit detects an end point where the finger leaves the touch screen; and

The calculation unit performs character recognition according to the start coordinate, the turning point coordinate group, and the end coordinate;

Among them, the coordinate recording steps include:

Obtain a previous coordinate, a relay coordinate, and a current coordinate, where the relay coordinate is the coordinate of the finger on the touch screen before the current coordinate one time interval, and the previous coordinate is the relay coordinate before the time interval The coordinates of the finger on the touch screen;

Calculate a first angle according to the previous coordinates and the relay coordinates;

Calculate a second angle based on the relay coordinates and the current coordinates; and

Judging whether a difference between the first angle and the second angle is greater than a threshold;

Wherein, when the difference is greater than the threshold, the calculation unit records the relay coordinates in the turning point coordinate group; when the current coordinates are not equal to the end point coordinates, the calculation unit updates the previous coordinates after the time interval , The relay coordinates, the current coordinates, the first angle, and the second angle.

In an embodiment, the turning point coordinate group includes a complex array of turning point coordinates, and the character recognition method further includes:

Calculate the Euclidean distance between every two adjacent sets of turning point coordinates in the complex array of turning point coordinates; and

Determine whether each Euclidean distance is less than a stroke threshold.

In an embodiment, the turning point coordinate group includes a complex array of turning point coordinates, and the character recognition method further includes:

Calculate an included angle between every three adjacent sets of turning point coordinates in the complex array of turning point coordinates; and

It is determined whether each included angle is less than an included angle threshold.

In an embodiment, calculating the first angle according to the previous coordinates and the relay coordinates includes:

Calculate a first vector from the previous coordinate to the relay coordinate, where the first angle is the angle between the first vector and the horizontal axis.

In an embodiment, calculating the second angle according to the relay coordinates and the current coordinates includes:

Calculate a second vector from the relay coordinate to the current coordinate, where the second angle is the angle between the second vector and the horizontal axis.

In order to enable your reviewer to further understand the structure, features and purpose of the present invention, the drawings and detailed descriptions of preferred specific embodiments are attached as follows.

Please refer to FIGS. 1 and 2. FIG. 1 shows a block diagram of an embodiment of the touch module of the present invention, and FIG. 2 shows a flowchart of an embodiment of the character recognition method of the present invention. The touch module 1 provided by the present invention includes a touch screen 11, a sensing unit 12, and a calculation unit 13, wherein the sensing unit 12 is electrically connected to the touch screen 11, and the calculation unit 13 is electrically connected to the The sensing unit 12, and the character recognition method includes: the sensing unit 12 detects that a finger of a user touches an initial coordinate of the touch screen 11 (step a); the calculation unit 13 performs a mark recording step to Obtain a turning point coordinate group (step b); the sensing unit 12 detects an end coordinate of the finger leaving the touch screen 11 (step c); and the calculation unit 13 according to the start coordinate, the turning point coordinate group, and Character recognition is performed on the end point coordinates (step d).

Specifically, when the touch module 1 is activated and the user wants to perform gesture recognition, the sensing unit 12 will detect the initial position where the user’s finger touches the touch screen 11 and define it Is the starting coordinate. In order to further obtain other characteristic data of the character, the calculation unit 13 will continue to execute the coordinate recording step.

Please refer to FIG. 3, which shows a flowchart of an embodiment of the coordinate recording step, which includes: obtaining a previous coordinate, a relay coordinate, and a current coordinate (step b1); according to the previous coordinate and the relay coordinate Calculate a first angle (step b2); calculate a second angle based on the relay coordinates and the current coordinates (step b3); determine whether a difference between the first angle and the second angle is greater than one Threshold (step b4); the calculation unit records the relay coordinates into the turning point coordinate group (step b5); and determines whether the current coordinates are equal to the end coordinates (step b6).

Specifically, the calculation unit 13 obtains the coordinates of the finger on the touch screen at the current time point through the sensing unit 12, and defines them as the current coordinates; in addition, the calculation unit 13 uses the sensing unit 12 Obtain the coordinates of the finger on the touch screen before the current coordinate one time interval (for example, one frame), and define them as relay coordinates; then, the calculation unit 13 obtains the relay coordinates through the sensing unit 12 The coordinates of the finger on the touch screen before the time interval (for example, one frame) are defined as the previous coordinates.

After obtaining the previous coordinates and the relay coordinates, a first vector from the previous coordinates to the relay coordinates can be calculated, and a first angle θ1 is defined by the angle between the first vector and the horizontal axis; On the other hand, after obtaining the relay coordinates and the current coordinates, a second vector from the relay coordinates to the current coordinates can be calculated, and a second vector is defined by the angle between the second vector and the horizontal axis. Two angle θ2. After obtaining the first angle θ1 and the second angle θ2, the calculation unit 13 can determine whether the relay coordinate is in the process of writing the character by using the difference between the first angle θ1 and the second angle θ2 Turning point.

In detail, the touch module 1 can obtain a threshold value according to the test data. When the difference between the first angle θ1 and the second angle θ2 is the absolute value of the angle change between the two angles Δθ = |θ2 − When θ1| is greater than the threshold, the calculation unit 13 will regard the relay coordinates as a turning point in the process of writing the character, and record the relay coordinates in the turning point coordinate group. After the determination of the magnitude between the absolute value of the angle change and the threshold value and the record of the turning point coordinate group are performed, the calculation unit 13 detects through the sensing unit 12 whether the user's finger leaves the touch screen 11, That is, whether the current coordinates are equal to the end coordinates. If yes, it means that the coordinate recording step of the current stage is temporarily finished; if not, it means that the user is still in the writing process, and the calculation unit 13 will update the previous coordinates and the middle after the time interval (for example, one frame). Following the coordinates, the current coordinates, the first angle θ1, and the second angle θ2, that is, the previous coordinates, the relay coordinates, and the current coordinates are obtained again after the time interval, through the new previous coordinates, the relay coordinates, and the current The coordinates calculate a new first angle θ1 and a new second angle θ2, and use the new first angle θ1 and the new second angle θ2 to detect possible turning point coordinates, and record them in the turning point coordinate group .

When the user's finger leaves the touch screen 11, the sensing unit 12 detects the final position where the finger leaves the touch screen 11 and defines it as the end point coordinates. After that, the calculation unit 13 will perform character recognition based on the start coordinate, the turning point coordinate group, and the end coordinate.

In detail, when the turning point coordinate group has n sets of turning point coordinates, the first set of turning point coordinates to the nth set of turning point coordinates can be defined as (x ₁ , y ₁ ), (x ₂ , y ₂ ),… …, (x _n , y _n ), according to the i-th set of turning point coordinates (x _i , y _i ) and the i-1th set of turning point coordinates (x _i-1 , y _i-1 ) in this array of turning point coordinates , Can calculate the i-th Euclidean distance between the two adjacent sets of turning point coordinates ρ _i = [(x _i -x _i-1 ) ² + (y _i -y _i-1 ) ² ] ^1/2 . When the Euclidean distance ρ _{i is} less than the given threshold of a stroke, it means that the stroke may be the habit of starting and ending the stroke, or the deflection in the writing process and does not need to be included in the characteristics of character recognition, and the calculation is The unit 13 will determine the stroke corresponding to the Euclidean distance ρ _i as a redundant stroke and discard it.

In addition to the misjudgment of the stroke length being too short, the turning point formed between two turning angles that are too close can sometimes become a source of misjudgment in character recognition. To this end, the i-1th set of turning point coordinates (x _i-1 , y _i-1 ), the i-th set of turning point coordinates (x _i , y _i ) and the i-1th set of turning point coordinates ( x _i-1 , y _i-1 ), the first set of turning point coordinates (x _i-1 , y _i-1 ) to the i-th set of turning point coordinates (x _i , y _i ) can be obtained Turning vector and a second turning vector from the i-th set of turning point coordinates (x _i , y _i ) to the i+1-th set of turning point coordinates (x _i+1 , y _i+1 ), and the first turning point can be obtained The angle between the vector and the second turning vector. If the included angle is less than a given included angle threshold, it means that the i-th set of turning point coordinates (x _i , y _i ) may not be the turning point of the actual character. At this time, the calculation unit will determine the turning point corresponding to the included angle as redundant Turning point and discard.

After determining and discarding redundant strokes and redundant turning points in the writing process, the calculation unit 13 will perform character recognition based on the effective character features such as the start coordinate, the turning coordinate group, and the end coordinate, thereby avoiding complexity The comparison mechanism can also reduce the misjudgment caused by redundant strokes and redundant turning points, and greatly improve the success rate and efficiency of character recognition.

The disclosure in this case is a preferred embodiment, and any partial changes or modifications that are derived from the technical ideas of the case and can be easily inferred by those who are familiar with the art do not deviate from the scope of the patent right of the case.

In summary, regardless of the purpose, means and effect of this case, it is shown that it is very different from the conventional technology, and its first invention is suitable for practicality, and it does meet the patent requirements of the invention. I implore the examiner to investigate and grant the patent as soon as possible. Society is for the best prayer.

Step a: The sensing unit detects an initial coordinate of a user's finger touching the touch screen Step b: The calculation unit executes a mark recording step to obtain a turning point coordinate set Step b1: Obtain a previous coordinate, a relay coordinate and a current coordinate Step b2: Calculate a first angle based on the previous coordinates and the relay coordinates Step b3: Calculate a second angle according to the relay coordinates and the current coordinates Step b4: Determine whether a difference between the first angle and the second angle is greater than a threshold? Step b5: The calculation unit records the relay coordinates into the turning point coordinate group Step b6: Determine whether the current coordinates are equal to the end coordinates? Step c: The sensing unit detects an end point where the finger leaves the touch screen Step d: The calculation unit performs character recognition according to the start coordinate, the turning point coordinate group, and the end coordinate 1: Touch module 11: Touch screen 12: Sensing unit 13: Computing unit

FIG. 1 shows a block diagram of an embodiment of the touch module of the present invention. FIG. 2 shows a flowchart of an embodiment of the character recognition method of the present invention. FIG. 3 is a flowchart of an embodiment of the coordinate recording step in FIG. 2.

Step a: The sensing unit detects an initial coordinate of a user's finger touching the touch screen

Step b: The calculation unit executes a mark recording step to obtain a turning point coordinate set

Step c: The sensing unit detects an end point where the finger leaves the touch screen

Step d: The calculation unit performs character recognition according to the start coordinate, the turning point coordinate group, and the end coordinate

Claims (10)

A character recognition method is suitable for a touch module, wherein the touch module includes a touch screen, a sensing unit, and a calculation unit. The sensing unit is electrically connected to the touch screen, and the calculation unit Electrically connected to the sensing unit, the character recognition method includes: The sensing unit detects an initial coordinate of a user's finger touching the touch screen; The calculation unit executes a mark recording step to obtain a turning point coordinate group; The sensing unit detects an end point where the finger leaves the touch screen; and The calculation unit performs character recognition according to the start coordinate, the turning point coordinate group, and the end coordinate; Among them, the coordinate recording steps include: Obtain a previous coordinate, a relay coordinate, and a current coordinate, where the relay coordinate is the coordinate of the finger on the touch screen before the current coordinate one time interval, and the previous coordinate is the relay coordinate before the time interval The coordinates of the finger on the touch screen; Calculate a first angle according to the previous coordinates and the relay coordinates; Calculate a second angle based on the relay coordinates and the current coordinates; and Judging whether a difference between the first angle and the second angle is greater than a threshold; Wherein, when the difference is greater than the threshold, the calculation unit records the relay coordinates in the turning point coordinate group; when the current coordinates are not equal to the end point coordinates, the calculation unit updates the previous coordinates after the time interval , The relay coordinates, the current coordinates, the first angle, and the second angle. For the character recognition method described in item 1 of the scope of patent application, the turning point coordinate group includes a complex array of turning point coordinates, and the character recognition method further includes: Calculate the Euclidean distance between every two adjacent sets of turning point coordinates in the complex array of turning point coordinates; and Determine whether each Euclidean distance is less than a stroke threshold. For the character recognition method described in item 1 of the scope of patent application, the turning point coordinate group includes a complex array of turning point coordinates, and the character recognition method further includes: Calculate an included angle between every three adjacent sets of turning point coordinates in the complex array of turning point coordinates; and It is determined whether each included angle is less than an included angle threshold. For the character recognition method described in item 1 of the scope of patent application, the calculation of the first angle based on the previous coordinates and the relay coordinates includes: Calculate a first vector from the previous coordinate to the relay coordinate, where the first angle is the angle between the first vector and the horizontal axis. For the character recognition method described in item 1 of the scope of patent application, the calculation of the second angle based on the relay coordinates and the current coordinates includes: Calculate a second vector from the relay coordinate to the current coordinate, where the second angle is the angle between the second vector and the horizontal axis. A touch module includes a touch screen, a sensing unit, and a calculation unit to perform a character recognition method, wherein the sensing unit is electrically connected to the touch screen, and the calculation unit is electrically connected to the sensing Unit, the character recognition method includes: The sensing unit detects an initial coordinate of a user's finger touching the touch screen; The calculation unit executes a mark recording step to obtain a turning point coordinate group; The sensing unit detects an end point where the finger leaves the touch screen; and The calculation unit performs character recognition according to the start coordinate, the turning point coordinate group, and the end coordinate; Among them, the coordinate recording steps include: Obtain a previous coordinate, a relay coordinate, and a current coordinate, where the relay coordinate is the coordinate of the finger on the touch screen before the current coordinate one time interval, and the previous coordinate is the relay coordinate before the time interval The coordinates of the finger on the touch screen; Calculate a first angle according to the previous coordinates and the relay coordinates; Calculate a second angle based on the relay coordinates and the current coordinates; and Judging whether a difference between the first angle and the second angle is greater than a threshold; Wherein, when the difference is greater than the threshold, the calculation unit records the relay coordinate in the turning point coordinate group; when the current coordinate is not equal to the end point coordinate, the calculation unit updates the previous coordinate after the time interval , The relay coordinates, the current coordinates, the first angle, and the second angle. For the touch module described in item 6 of the scope of patent application, the turning point coordinate group includes a complex array of turning point coordinates, and the character recognition method further includes: Calculate the Euclidean distance between every two adjacent sets of turning point coordinates in the complex array of turning point coordinates; and Determine whether each Euclidean distance is less than a stroke threshold. For the touch module described in item 6 of the scope of patent application, the turning point coordinate group includes a complex array of turning point coordinates, and the character recognition method further includes: Calculate an included angle between every three adjacent sets of turning point coordinates in the complex array of turning point coordinates; and It is determined whether each included angle is less than an included angle threshold. For the touch module described in item 6 of the scope of patent application, the first angle calculated based on the previous coordinates and the relay coordinates includes: Calculate a first vector from the previous coordinate to the relay coordinate, where the first angle is the angle between the first vector and the horizontal axis. For the touch module described in item 6 of the scope of patent application, the second angle calculated based on the relay coordinates and the current coordinates includes: Calculate a second vector from the relay coordinate to the current coordinate, where the second angle is the angle between the second vector and the horizontal axis.

Images