JP2015176491A - Handwritten music symbol recognition device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a handwritten music symbol recognition device that enables handwritten input symbols to be accurately recognized without holding enormous data.SOLUTION: A handwritten music symbol recognition device has: touch information acquisition means for acquiring positional information whenever input means moves until the input means gets away from touching a screen; stroke information storage means for creating vector information showing the movement of the input means from the positional information obtained from the touch information acquisition means, and storing a series of vectors until the input means completely gets away from touching the screen as one stroke information; object information storage means for storing one or multiple stroke information storing a series of one or multiple vector information; and stroke feature value calculation means for calculating a feature value of the stroke from the vector information.

Description

  The present invention relates to a handwritten music symbol recognition device, and more particularly to a technique suitable for use in creating a musical score by recognizing a symbol handwritten (including using a pen) on a terminal device equipped with a touch panel.

  A tablet terminal corresponding to handwriting input detects trajectory information obtained by scanning a touch panel by an input means such as a finger, and recognizes a symbol or a figure based on the detected information.

  For example, Patent Document 1 proposes the following method. A specific symbol or figure for character conversion is registered and set in advance. Characters entered for character recognition when a character is entered in a handwritten character input character frame for inputting character to perform character recognition, and the particular symbol or figure is entered after entering the character. Is converted to the desired character. For example, a handwritten character recognition device and a character input method for handwritten character recognition that can easily realize that an input character is recognized as a lowercase letter have been proposed.

Japanese Patent Laid-Open No. 2000-194796

  The technique proposed in Patent Document 1 requires that a specific symbol or figure for converting characters be registered in advance. For this reason, since it is necessary to retain data for the number of recognizable characters, symbols, or figures, a storage medium having a large storage capacity is required.

In addition, since it is necessary to correlate the input characters with the character candidates stored in a large amount in the storage medium on a one-to-one basis, there is a problem that a complicated and large program is required. In addition, there are problems that characters and symbols that are not registered in the storage medium cannot be recognized, and that accurate symbol recognition cannot be performed unless they are entered cleanly.
The present invention has been made in view of the above-described problems, and an object of the present invention is to make it possible to accurately recognize a handwritten symbol without holding a large amount of data.

  The handwritten music symbol recognition apparatus according to the present invention includes a touch information acquisition unit that acquires position information every time the input unit moves until the input unit touches the screen and leaves, and a position obtained from the touch information acquisition unit. Stroke information storage means for creating vector information indicating movement of the input means from the information, storing a series of vectors from when the input means touches the screen until it completely leaves as one stroke information, and a series of 1 to 1 Comprises object information storage means for storing one or more stroke information in which a plurality of vector information is stored, and stroke feature quantity calculation means for calculating a feature quantity of the stroke from the vector information. To do.

  According to the present invention, since the feature point of the vector constituting the music symbol is evaluated and the symbol is recognized, the symbol inputted by hand can be accurately recognized without holding a huge amount of data. .

It is a block diagram which shows the structural example of the handwritten music symbol recognition apparatus in embodiment of this invention. It is a figure explaining the relationship between a vector, a stroke, and an object, taking a Sayo mark as an example. It is a figure which shows the example which classify | categorizes a vector into nine types. It is a figure which shows the example of the inscribed rectangle of S character vector, and a center coordinate. It is a figure which shows the example of a change of the rotation angle from the said vector to the following vector. It is a flowchart explaining the procedure of a music symbol recognition process. It is a figure which shows the creation example of vector information. It is a flowchart explaining the procedure of the recognition process of an object. It is a flowchart explaining the detail of stroke recognition. It is a figure which shows four symbols comprised by 2 vectors. It is a figure which shows an example of the symbol to recognize. It is a flowchart explaining the process which recognizes a symbol by the change of a rotation direction. It is a figure explaining a mode that judgment of a circle and an ellipse is performed. It is a figure which shows the rotation direction change point of S. It is a figure explaining a mode that the determination of a treble clef is performed. It is a figure which shows an example of the touchscreen on which the recognition execution button which a user can operate is displayed. (A) shows a sharp symbol, (b) is a diagram showing a database for sharpening. (A) shows the gravity center of each stroke which comprises a sharp sign, (b) is a figure which shows the positional relationship of a gravity center. It is a figure which shows the start point, end point coordinate, vector ID, and stroke feature-value of each vector of a Seño mark. It is a figure which shows how to determine a connection type and shows the relationship between the ID of the vector and the ID of the next vector. It is a figure which shows how to determine a rotation direction, and shows the relationship between ID of the said vector, and ID of the next vector. It is a figure which shows how to determine the symbol comprised by 2 vector strokes, and shows the relationship between ID of vector 1 and ID of vector 2. FIG. It is a figure which shows the position ID arrangement | sequence of a seigno mark object.

Hereinafter, an embodiment of a handwritten music symbol recognition apparatus of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram illustrating a schematic configuration of a handwritten music symbol recognition apparatus 10, and the handwritten music symbol recognition apparatus 10 includes a tablet terminal (including a touch-compatible PC).

  In FIG. 1, 11 is a bus, 12 is ROM, 13 is RAM, 14 is CPU, 15 is flash memory, 16 is a network interface, 17 is a touch display, 18 is an audio output device, and 19 is a MIDI output device.

A program for controlling the overall operation of the handwritten music symbol recognition apparatus 10 is stored in the flash memory 15, and is read out, expanded in the RAM 13, and executed by the CPU 14.
The touch information acquisition means, which is a main component of the present embodiment, is configured by the touch display 17, the RAM 13, the CPU 14, the flash memory 15, and the like, and acquires the position information every time the touch position moves.

The stroke information storage means and the object information storage means are constituted by the RAM 13.
The stroke feature amount calculating means, stroke recognizing means, and object recognizing means are composed of a RAM 13, a CPU 14, and a flash memory 15. The stroke information storage means creates vector information indicating the movement of the input means such as a finger and a touch pen from the position information obtained from the touch information acquisition means, and a series of vectors from when the input means touches the screen until it completely leaves Is stored as one stroke information.

The network interface 16 stores the recognized music symbol information as a file in other hardware, or reads a stored music symbol information file.
The audio output device 18 is provided in order to create music performance information from the recognized music symbols and output the sound.
The MIDI output device 19 is provided in order to create MIDI information from the recognized music symbols and output the MIDI information.

<Description of vector, stroke, and object>
The relationship between vectors, strokes, and objects will be described with reference to FIG.
The Seigno mark object is composed of an S-shaped stroke, a linear stroke, and two point strokes. A linear stroke and a point stroke are composed of one vector.

(How to assign a vector ID)
In the present embodiment, the vectors are classified into nine types in order to simplify the processing.
As shown in FIG. 3, the slope a is obtained from the starting point (x1, y1) and the ending point (x2, y2) of the vector using the equation (1).
Then, the vector ID is determined in consideration of the positional relationship of x1, y1, x2, and y2. The lower side of the y-axis is “+”.

| a |> 2
y2 <y1: Lower → Up y2> y1: Lower → Up-2 ≦ a <−0.5
x2 <x1: lower left → upper right x2> x1: upper right → lower left
| a | ≦ 0.5
x2> x1: Left → Right x2 <x1: Right → Left 0.5 <a ≦ 2
x2> x1: upper left → lower right x2 <x1: lower right → upper left x1 = x2
y2 <y1: Bottom → Up y2> y1: Bottom → Up x1 = x2 and y1 = y2
point

In the case of vector 0 of stroke 0 in FIG.
Since a = (352-400) / (421-424) = 16 and the end point Y coordinate is smaller than the start point Y coordinate value (upper), the ID becomes lower → upper (see FIG. 19).

<Description of each feature>
FIG. 19 shows the start point, end point coordinate, vector ID, and stroke feature amount of each vector of the Seigno mark in FIG. 2 as examples of feature amounts.
(Start point end point distance)
When this distance is smaller than the specified value, it is considered as a closed figure like a circle, and when it is larger, it is considered as a figure not closed like an arc line.
If the start point coordinates of the first vector are (x1, y1) and the end point coordinates of the final vector are (x2, y2), the start point / end point distance D _se is obtained by the following equation (2).

(The coordinates of the four points of the inscribed rectangle and the center coordinates)
This value is used to obtain the positional relationship between the strokes.
FIG. 4 shows an example of the inscribed rectangle and center coordinates of the S-shaped vector.
Rectangular coordinate left is the leftmost X coordinate of the start or end points of all vectors.
Rectangular coordinate right is the rightmost X coordinate of the start or end points of all vectors.
On the rectangular coordinates, it is the highest Y coordinate among the start points or end points of all vectors.
Below the rectangular coordinates is the lowest Y coordinate of the start or end points of all vectors.
The center coordinate is represented by an X coordinate intermediate between the rectangular coordinate left and the rectangular coordinate right, and an intermediate Y coordinate above the rectangular coordinate and below the rectangular coordinate.

(Connection type)
This value is used to determine whether the symbol is smooth, has a corner, or the like.
It is determined from the ID of the vector and the ID of the next vector (see FIG. 20). In this embodiment, the obtuse angle is 1 or the right angle is 2 or the acute angle is 3 or 0.
In the stroke 0 of the Seigno mark, the first vector ID is 1 (lower → upper) and the next vector ID 8 (lower right → upper left), so the connection type is 1 (obtuse angle).

(Direction of rotation)
The point where the rotation direction has changed is important as a clue for identifying the symbol.
For example, in the first stroke of “f”, vectors are smoothly continuous like “S”, the start point and the end point are separated, but “S” has one point where the rotation direction changes. So you can distinguish. This is also determined from the ID of the vector and the ID of the next vector (see FIG. 21). In the stroke 0 of the Seigno mark, the ID of the vector 0 is lower → upper (1) and the ID of the vector 1 is lower right → upper left (8), so the counterclockwise rotation (2).

(rotation angle)
FIG. 5 shows a change example of the rotation angle from the vector to the next vector. From this total, it can be determined whether the symbol is a circle or a multiple circle.
If the start point of the vector is (x11, y11), the end point is (x12, y12), the start point of the next vector is (x21, y21), and the end point is (x22, y22), the angle Deg ( °) is obtained by the following formula.

(Left / Right direction and Up / Down direction)
It is determined whether the symbol is simply a line segment drawn from top to bottom and from left to right.
Obtained from the vector ID. If the vector ID is down → up (1), the left / right movement direction is none (0), and the up / down movement direction is up (1). If the vector ID is lower right → upper left (8), the horizontal movement direction is left (1) and the vertical movement direction is up (1).

(Leftmost point, rightmost point, topmost point, lowest point index)
For example, if the leftmost point Index is 0 (start point of the first vector) and the rightmost point Index is N (start point of the final vector), if the highest point Index is near N / 2, the bottom is an open mountain Can be determined. In the case of FIG. 4, the leftmost point Index is 12, the rightmost point Index is 9, the uppermost point Index is 2, and the lowermost point Index is 11.

Next, the operation of the handwritten music symbol recognition apparatus of this embodiment will be described with reference to the flowchart of FIG. FIG. 6 is a flowchart for explaining the procedure of the music symbol recognition process.
In S61, it is determined whether or not the screen is touched. When the screen is not touched, it enters a standby state. If the screen is touched, the process proceeds to S62.

In S62, the coordinate array is emptied and the touched coordinates are stored in the coordinate array. Every time the finger moves from touching the screen until it leaves, a finger movement process is performed. In this process, the coordinates of the moved finger are stored in the coordinate array.
In S63, it is determined whether or not the touched finger has left the screen. If the finger is not released from the screen, the process returns to S62, and the finger moving process of S62 is performed every time the finger moves until the finger is released from the screen. As a result of the determination in S63, when the finger leaves the screen, the process proceeds to S64.

In S64, a stroke is generated. In this process, first, stroke information is newly generated.
Next, vector coordinates having the first coordinate as the start point and the second coordinate as the end point are created. At this time, a vector ID is also set. The vector magnitude is also calculated. The created vector information is stored in a vector array of stroke information.

  Next, vector information having the second coordinate as the start point and the third coordinate as the end point is created and stored in the stroke information. In the example of FIG. 7, that is, the Seigno mark and the stroke 0, 12 pieces of vector information are created. When vector information is created from all coordinates and stored in the stroke information, a stroke feature amount is generated and stored in the stroke information.

  Next, in S65, it is determined whether or not the screen is touched within a certain time. If the input of the next stroke is started within a predetermined time, the process returns to S62, and the processes of S62 to S64 are performed to create a new stroke.

  FIG. 2 shows an example in which, after the S-shaped stroke is input, a linear stroke is input within a certain time, a point stroke is further input within a certain time, and a point stroke is further input within a certain time. Yes. When such an input is performed, each stroke is generated for each input. If there is no next stroke input within the predetermined time, the process proceeds to S66.

In S66, an object generation process for newly generating one object is performed, and the strokes generated so far are stored in the stroke array. Further, the relative positional relationship of each stroke = position ID is obtained. The position ID is an ID indicating the position of the stroke with respect to the reference stroke.
In this embodiment, the same (0), lower → upper (1), lower left → upper right (2), left → right (3), upper left → lower right (4), upper → lower (5), upper right → lower left (6) There are nine types, right → left (7) and lower right → upper left (8), which are similar to the vector ID.

Here, how to obtain the position ID will be described.
Consider a vector whose starting point is the center coordinate of the inscribed rectangle of the reference stroke and whose end point is the center coordinate of the inscribed rectangle of the stroke, and obtain the vector ID of this vector. If the vector ID is lower → upper, the position ID is upper, and if the vector ID is left → right, the position ID is right.

  In the example of FIG. 2, the position ID of the S-shaped stroke is first obtained. Since the S-shaped stroke is the first stroke, the reference stroke is the last point vector. In this case, since the vector inclination a = (426-449) / (375-428) = 0.43 and the X coordinate of the start point is larger than the X coordinate of the end point, the vector ID is changed from right to left, and the position ID Becomes “left”.

Next, a straight line vector ID is obtained. In this case, a vector having the start point as the center coordinate of the inscribed rectangle of the S-shaped stroke and the end point as the center coordinate of the inscribed rectangle of the linear stroke is obtained.
Since the X coordinate of the start point and the end point is the same, and the Y coordinate of the start point is smaller than the Y coordinate of the end point, the vector ID becomes lower → upper and the position ID becomes “upper”.
Hereinafter, when the position ID is similarly obtained, four IDs of “left”, “upper”, “left”, and “right” are obtained. These are stored in the position ID array of the object shown in FIG.
In S67, when the stroke and the position ID are stored in the object, what symbol the object is is recognized.
The procedure of the object recognition process performed in S67 is shown in the flowchart of FIG.

In S81, the stroke is recognized. Details of stroke recognition will be described later.
In S82, it is determined whether there is any other unrecognized stroke. If there is an unrecognized stroke, the process returns to S81, and if there is no unrecognized stroke, the process proceeds to S83.
In S83, object recognition processing is performed. The object recognition process will be described later.
As shown in FIG. 8, after the strokes stored in the object are recognized, the object is recognized.

Details of the stroke recognition performed in S81 of FIG. 8 will be described with reference to the flowchart of FIG.
In S91, the process is branched according to the number of vectors. In the branching process of S91, if the stroke is composed of one vector, the process proceeds to S92. If the stroke is composed of two vectors, the process proceeds to S93. If it is any other stroke, the process proceeds to S94.

  In S92, a process of recognizing a stroke composed of one vector is performed. As a result, any one of a vertical line, a horizontal line, a diagonally rising line, a diagonally rising line, and a point is recognized based on the vector ID. For example, if the vector ID is lower right → upper left or upper left → lower right, the line is a diagonally upward left line.

  In S93, a stroke recognition process composed of two vectors is performed. In the present embodiment, a case where four symbols shown in FIG. 10 are recognized will be described. FIG. 22 shows how to determine a symbol when recognizing which symbol is based on two vector IDs. In the case of combinations other than those shown in FIG. 22, there is no corresponding symbol.

  As shown in FIG. 22, when there is a possibility of two symbols, such as the ID of vector 1 is lower left → upper right and the ID of vector 2 is upper right → lower left, it is determined whether the inscribed rectangle is vertically long or horizontally long. If it is vertically long, it is breath or accent, and if it is horizontally long, it is crescendo or decrescendo.

In S94, recognition processing for other strokes (three or more vectors) is performed.
Processing for recognizing the symbols shown in FIG. 11 will be described with reference to the flowchart of FIG.
In S121, the rotation direction of the feature quantity is referred to, the number of times the rotation direction is changed is counted, and the process branches depending on the number. If the number is 0, the process proceeds to S122. If the number is 1, the process proceeds to S123. If the number is 2, the process proceeds to S124. In this embodiment, if the number of times is other than 0, 1, or 2, there is no corresponding symbol.

(When the number of rotation direction changes is 0)
In S122, determinations other than “S” and “G clef” are performed according to the following procedure.
(1) Check if there is an acute angle point. If there is an acute angle point, there is no corresponding symbol.
(2) The sum of the rotation angles is obtained, and the symbol is determined thereby.

Rotation angle ≤ 180 °
The arc line is determined under the following conditions.
・ There is “right” in the left / right movement direction and there is no “left”.
・ The highest point is other than the start point and end point → upper arc line ・ The highest point is the start point or end point → lower arc line

-There is no "right" in the left / right movement direction and there is "left".
・ The highest point is other than the start point and end point → upper arc line ・ The highest point is the start point or end point → lower arc line

・ There is “Down” in the vertical movement direction, and there is no “Up”.
・ Leftmost point is other than start point and end point → left arc line ・ Leftmost point is start point or end point → right arc line

・ There is no “down” in the vertical movement direction and “up”.
・ Left-most point is other than start point and end point → Left arc line ・ Left-most point is start point or end point → Right arc line ・ Other than above → No applicable symbol.

Rotation angle> 360 ° → multiple circles

Other circles and ellipses are determined according to the following procedure (see FIG. 13).
1. Find the equation of the straight line (the major axis) connecting the leftmost point and the rightmost point.
2. From each point, the perpendicular foot drawn on the straight line is obtained.
3. The point where the length of each point and the leg of the perpendicular is the longest is defined as the half minor axis of the ellipse.
4). The ratio of the major axis of the semi-minor axis × 2 (assuming the minor axis) is obtained.
・ The calculated ratio is almost 1: 1 → circle ・ others → ellipse

(When the number of rotation direction changes is 1)
In S123, “S” is determined.
FIG. 14 shows the rotation direction change point of “S”.
-Check the number of vectors before and after the rotation direction change point, and if the number is less than the number that can draw an arc (3), there is no corresponding symbol. In the present embodiment, there are 7 vectors before the change and 5 vectors after the change, so the condition is satisfied.
“S” if the absolute value of the total rotation angle up to and including the rotation direction change point is 100 ° or more. In the case of this embodiment, it is 257 ° before the rotation direction change and 220 ° after the rotation direction, so it can be determined as “S”.

(When the number of rotation direction changes is 2)
In S124, the “g clef” is determined (see FIG. 15).
The conditions for the determination of “G clef” are as follows.
There are one point where the rotation direction changes from clockwise to counterclockwise (rotation direction change point 1) and one point where the rotation direction changes from counterclockwise to clockwise (rotation direction change point 2).
The rotation direction change point 1 is above the center of the inscribed rectangle.
The rotation direction change point 2 is below the center of the inscribed rectangle.

Next, the object recognition process performed in S83 of the flowchart of FIG. 8 will be described.
In the following, the case of the Seño mark will be described. In order for a written symbol to be determined as a Seño mark, the following conditions must be satisfied.
Condition 1: It is composed of four strokes of “S”, “upward diagonal line”, “point”, and “point”.
Condition 2: Inscribed rectangle centers of “S” and “upward diagonal line” are close to each other.
Condition 3: There are “points” on the left and right of the inscribed rectangle center of “S” or “upward diagonal line”.

  In this embodiment, since the position ID of the stroke 1 with respect to the stroke 0 is “up”, the position is close in the X-axis direction. In addition, since the Y coordinate of the center of the inscribed rectangle is only 20 away, it can be regarded as close (condition 2 is cleared).

The position ID of stroke 2 with respect to stroke 1 is “left”. The Y coordinate of the inscribed rectangle center of stroke 1 and the Y coordinate of the inscribed rectangle center of stroke 3 are 3, and the X coordinate of the inscribed rectangle center of stroke 1 is the X coordinate of the inscribed rectangle center of stroke 3. Since stroke 50 is smaller, stroke 3 is located to the right of stroke 1.
Therefore, in the present embodiment, since the conditions 1 to 3 are satisfied, it can be determined as a Seigno mark.

  In the object recognition process, if another stroke is input within a certain time after the input of one stroke is completed, the process waits until the input is completed. To recognize the object.

  As shown in FIG. 16, a recognition execution button 161 that can be operated by the user is displayed on the touch panel 160 in order to issue a recognition start instruction. When the recognition execution button 161 is operated after the user has written all the strokes (ellipses, vertical lines), recognition starts. The CPU 14 registers an unrecognized stroke in the object and recognizes the object.

  In the handwritten music symbol recognition apparatus of the present embodiment, a staff 162 is displayed in advance on the input screen, and when an object is recognized as a circle or the like, it is recognized as a musical note and its pitch can be specified. In the example of FIG. 16, since the elliptical portion of the object is between the first line and the second line, an example is shown in which a half note 163 having a pitch of “F” is recognized.

The detection of a plurality of strokes will be described using the sharp symbol “#” as an example.
As shown in FIG. 17A, the sharp symbol “#” is composed of Stroke 1, Stroke 2, Stroke 3, and Stroke 4. Such a symbol composed of a plurality of strokes has a database (dictionary data) as shown in FIG. Note that the dictionary data stores what symbol each stroke is, and does not store actual coordinate data or vector information created based on the coordinate data.

In the sharp database (dictionary data), Stroke 1 is “upper right diagonal”, “horizontal”, “upper right diagonal”, and “horizontal”.
Stroke 2 is “horizontal”, “upper right diagonal”, “upper right diagonal”, and “horizontal”.
Stroke 3 and Stroke 4 are “vertical”, “vertical”, “vertical”, and “vertical”.

Further, as shown in FIG. 18B, the center of gravity of each stroke 1 to 4 shown in FIG. 18A is “down”, “down”, “lower right”, “lower right” as shown in FIG. It is.
2 → 3 are “upper left”, “up”, “up”, and “upper left”.
3 → 4 is “right”, “right”, “right”, “right”.

  In the embodiment described above, an example of recognizing a music symbol has been shown, but the handwritten music symbol recognition apparatus of the present invention can also recognize characters such as “Coda”, numbers, and the like.

(Other embodiments)
The present invention can also be realized by executing the following processing. That is, software (computer program) that implements the functions of the above-described embodiments is supplied to a system or apparatus via a network or various computer-readable storage media. Then, the computer (or CPU, MPU, etc.) of the system or apparatus reads out and executes the program.

10 Handwritten Music Symbol Recognition Device 11 Bus 12 ROM
13 RAM
14 CPU
15 Flash memory 16 Network interface 17 Touch display 18 Audio output device 19 MIDI output device

Claims (9)

Touch information acquisition means for acquiring position information each time the input means moves until the input means touches the screen and then leaves,
A stroke that creates vector information indicating the movement of the input means from the position information obtained from the touch information acquisition means, and stores a series of vectors as one stroke information from when the input means touches the screen until it completely leaves. Information storage means;
Object information storage means for storing one or more stroke information in which a series of one or more vector information is stored;
A handwritten music symbol recognition apparatus comprising: a stroke feature amount calculating unit that calculates a feature amount of the stroke from the vector information.   The vector information is based on the slope of the vector: point, bottom → top, bottom left → top right, left → right, top left → bottom right, top → bottom, top right → bottom left, right → left, bottom right → top left, The handwritten music symbol recognition apparatus according to claim 1, wherein the handwritten music symbol recognition apparatus is classified into nine types and includes the ID.   The stroke feature amount calculated by the stroke feature amount calculation means is at least the distance from the start point to the end point, the coordinates and center coordinates of the four points of the rectangle inscribed by the stroke, the connection type indicated by the angle of the vector and the next vector, Index of vector whose connection type is an acute angle, rotation direction from the vector to the next vector, rotation angle from the vector to the next vector, movement direction in the horizontal direction, movement direction in the vertical direction, leftmost point, 2. The handwritten music symbol recognition apparatus according to claim 1, wherein one or all of the rightmost point, the uppermost point, and the index corresponding to the lowermost point are included and stored in stroke information.   4. The handwriting according to claim 3, wherein the rotation direction from the vector to the next vector among the stroke feature amounts indicates whether the rotation direction is clockwise or counterclockwise. Music symbol recognition device.   4. The handwritten music symbol recognition apparatus according to claim 3, further comprising stroke recognition means for comparing the stroke feature quantity with the feature of the symbol and recognizing what symbol the stroke is.   6. The handwritten music symbol recognition apparatus according to claim 5, further comprising object recognition means for recognizing a symbol drawn by a plurality of strokes based on a positional relationship of the plurality of strokes recognized by the stroke recognition means.   The object recognizing unit waits until the input is completed if another stroke is input within a predetermined time after the input of one stroke is completed. The handwritten music symbol recognition apparatus according to claim 6, wherein the object is recognized and the object is recognized.   A recognition start instruction means operable by a user, and when the recognition start instruction means is operated, the object recognition means registers an unrecognized stroke in the object and recognizes the object; The handwritten music symbol recognition device according to claim 6.   9. The staff according to claim 7 or 8, wherein a staff is displayed in advance on the input screen, and the object recognizing means recognizes the object as a circle and recognizes it as a note and can also specify its pitch. The handwritten music symbol recognition apparatus of description.

Images