JPH1195743A - Music recognition method and computer-readable recording medium having music recognition program recorded - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable the recognition of drum notes in drum music and the conversion into a playable and/or displayable data type by executing the recognition of a drum not head symbol by matching the sepn. label existing in the periphery of a detected stem candidate and a dictionary, then executing the processing to couple the note head and the stem candidate. SOLUTION: The label of the note head is separated and the stem candidate is scanned by using stem information and erasing the bit of the stem. The recognition of the drum note head symbol is executed by matching the sepn. label existing on the periphery of the stem candidate detected by the same and the dictionary and thereafter, the processing to couple the note head and the stem candidate is executed. The music recognition apparatus is constituted by adding a scanner and MIDI interface circuit to the constitution of an electronic computer, such as personal computer. A CPU 1 of this device executes the control over the entire part of the music recognition apparatus in accordance with the program stored in a ROM 2 or RAM 3.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for recognizing a musical score, and more particularly to a computer readable recording medium for storing a program for recognizing a musical score.

[0002]

2. Description of the Related Art Normally, when a musical score is to be recognized mechanically,
After the staff recognition and the paragraph recognition as shown in FIG. 26, the staff is erased and various methods are used to remove the black staff b shown in FIG. 27 (a) or the black ball b shown in FIG. 27 (b). Note head of a note such as white ball w, a stem t continuous to the note head shown in FIG.
Further, the flag f and the like that follow the suffix shown in FIG.

[0003]

Among the note heads displayed on the drum score, the notes other than the black and white balls, which are the same as the normal score, are written in thin lines such as (×) and (◇). There are various other types. For this reason, bold and fine separation (Japanese Unexamined Patent Application Publication No.
Reference, the method that separates the parts that make up the thin line from the image data, detects the symbols that make up the thin line, detects the thick symbols from the rest of the image, and recognizes the symbols that appear on the score), It cannot be detected by ellipse detection (a method of recognizing a black ball or a white ball used for a note head of a normal note using an elliptic formula).

In addition, there are other problems that cannot be solved by the conventional method, such as tie-joining to noteheads and chords in which two or more noteheads touch in the vertical direction. Also, note that the position where noteheads are combined with stems differs depending on the score, and that noteheads are in the middle of stems and there are notes that break the stems. There is no problem.

The present invention has been made in view of the above-mentioned problems of the prior art, and solves these problems, enables recognition of drum notes in a drum score different from a normal score, and provides data that can be played and / or displayed. It does not provide a configuration that can be converted to a format.

[0006]

SUMMARY OF THE INVENTION Therefore, a configuration of the invention according to claim 1 of the present application is directed to a music score recognition method for reading an image of a music score, recognizing the music symbol, and converting the music symbol into a music format that can be played and / or displayed. , The suffix bit is erased using the suffix information (hereafter, erasure refers to erasing the bit plane of the image, which is distinguished from erasure in which the data on the recognition result storage data is erased). , Scan the stem candidates, match the separated labels around the detected stem candidates with the dictionary to recognize the drum head symbols, and then recognize the recognized note heads and stems. It is characterized in that a combining process with a candidate is performed. As mentioned above, note heads of drum staves are written with thin lines such as (x) and (◇) for notes other than black and white balls, and there are various other types as well, It cannot be detected by the thick and thin separation method and the ellipse detection method which are usually used for musical note recognition. Therefore, similar to normal symbol recognition, recognition is performed by matching the separated and extracted labels with the dictionary. However, since there is a stem, it is not possible to separate only the note head as one label. In addition, since there are consecutive hooks and chords, it is impossible to create a dictionary including stems because the pattern becomes enormous. Therefore, in the present configuration, the label of the note head is once separated by using the information of the stem, and the separated label is matched with the dictionary so that the label can be recognized in the same manner as the normal symbol recognition. At that time, the scanhead candidates separated from the noteheads are scanned, and the drum noteheads are recognized with the labels around the notehead candidates as matching targets. Is performed.

[0007] The above configuration is also the same for a computer-readable recording medium storing the musical score recognition program according to claim 11, and has a label separation function for separating note head labels using stem information. A scanning function for scanning a stem candidate, a recognition function for matching a separation label around the stem candidate detected in the scanning with a dictionary, recognizing a note head and recognizing a drum head, and a recognition function. And a program for executing a combining function of combining the obtained note heads and stem candidates.

In the above configuration, when matching between the separation label and the dictionary fails, scanning of the stem candidates is continued, and the next detected notehead label is combined with the separation label. May be performed again. This is because in the case shown in FIG. 1, there is no problem in recognizing the note head even if the stem is deleted, but in the case shown in FIG. It is because it separates into. In such a case, the matching that is performed first fails, and the notehead can be recognized by performing label combining and performing matching again.

The above configuration is the same for a computer-readable recording medium storing the musical score recognition program according to the twelfth aspect. The configuration includes a matching determination function for determining the success or failure of matching between the separation label and the dictionary. If the matching fails, a program for executing a label combining function of performing a combining process of causing the scanning function to continue scanning for stem candidates and performing a combining process of the next detected note head label and the separation label is further provided. Have, after label binding,
This will cause the recognition function to perform the matching between the combined label and the dictionary again.

[0010] Even in the case of performing the label combination and the re-matching processing performed after the dictionary matching failure, the notehead label itself that is detected next and used in the combining processing is also matched with the dictionary, and the matching result has priority. If the degree is high, the recognition result should be given priority.

The above configuration is the same for a computer-readable recording medium on which the musical score recognition program according to claim 13 is recorded. The configuration also includes the note head label itself detected and used for the combining process next. When the matching function is performed with the dictionary, and the matching result has a higher priority, the recognition result is given priority.

In the score recognizing method according to the second aspect, label combining is repeatedly performed, and priorities are given to respective recognition results recognized by matching during the combining, and the recognition results are determined in descending order of priority. Good. During label merging, before it becomes a recognition rectangle containing all the noteheads that should be recognized,
In some cases, the matching result may have the same shape as another notehead, and when performing matching, it is preferable to give a priority to the recognition result. If the recognition result has a low priority, the ID and the rectangle are stored, and the next label scan is performed. If no higher priority ID is found, this is given priority. The recognition target label formed in the middle of label combination is different from the intended
If D is recognized, it is entered in the dictionary as reject travel, and if it is recognized, recognition may be failed.

The above configuration is the same for a computer-readable recording medium storing the musical score recognition program of claim 14, and the configuration is such that the note head recognition and label combination are repeatedly performed. The program further includes a program for executing a priority addition function for assigning a priority to each recognition result recognized by matching during the notehead recognition, and the recognition function corrects the recognition results in descending order of priority. Will do.

In the above configuration, if the tie is in contact with the note head, label separation cannot be performed. Therefore, it is preferable to first erase the ties and then perform label separation, thereby recognizing the drum notes including the note heads in contact with the ties.

The above configuration is the same for a computer-readable recording medium that stores the score recognition program according to claim 15, wherein the configuration includes a program for executing a tie erasing function for erasing a tie contacting a notehead. After the erasure, label separation is performed by a label separation function, and the recognition function recognizes the notehead with which the tie is in contact.

As shown in FIG. 3, when musical instruments other than a normal drum set are represented on the same staff, there are cases where chords in which (x) contacts each other are present. In such a case, it is difficult to set the recognition rectangle by separating each note head before matching with the dictionary. Therefore, claim 6
In the configuration (1), the combined noteheads in which the noteheads are in contact with each other up and down are registered in the dictionary, and the dictionary is matched with the combined noteheads to recognize the combined noteheads.

The above configuration is the same for a computer-readable recording medium storing the musical score recognition program according to claim 16, and the configuration is such that a combined note head in which note heads vertically contact each other is registered in a dictionary. In this case, the recognition function matches the dictionary and the combined notehead, and recognizes the combined notehead.

As described above, the tremolo symbol as shown in FIG. 4 can be recognized by matching the dictionary around while combining the labels around the stem candidates.
Especially in the case of drum music, there are relatively many tremolo symbols. Since the tremolo symbol is almost the same thickness and interval as the hook, if no countermeasures are taken, the flag will be counted in the same way as the hook, and it will be mistaken for a short note such as a 32nd note. I will. Therefore, in the configuration of the present application, the tremolo symbol is registered in the dictionary as shown in FIG. 5, the tremolo symbol is recognized, the symbol bit is deleted, and then the tremolo symbol is displayed including the tremolo symbol. It was decided to recognize other drum notes.

The above configuration is the same for a computer-readable recording medium storing the musical score recognition program according to claim 17, wherein the tremolo symbol is registered in a dictionary, and the tremolo symbol is registered by the recognition function. In addition to recognizing the symbols, the program further has a program for executing a symbol erasing function for erasing the bits of the tremolo symbol, and after the erasure, another drum note displayed including the tremolo symbol is recognized.

In the configuration of the present application, the process of combining noteheads and stems is performed after the recognition of noteheads as in the case of normal music score recognition. Special processing is required. One of them is due to the positional relationship between note heads and stems. That is, in the case of a notehead other than a black ball, as shown in FIG. 2, a stem may be attached to the center of the notehead. In addition, note heads are rarely attached to both sides of the stem.

Note recognition is performed by combining note heads and stem candidates. In this connection, first, the head note heads are combined, and then intermediate note heads are combined. In the case of a normal notehead (black ball, white ball), the ball may be attached to the left and right of the stem.
The position of the head ball is determined in the X direction (horizontal direction) (for example, if the head is upward, the head of the head is attached only to the left of the stem). Therefore, when combining the first ball, the X of the stem and the notehead
The positional relationship in the direction is limited to left and right. At this time,
As shown in FIG. 6, which end of the stem is at the end of the stem (upward or downward), as shown in FIG. Determined by the positional relationship of the Y coordinate. Whether or not the ball is the head ball is determined based on the distance between the end ST of the note stem candidate and the note head center CY or the relationship between the upper and lower ends of the note head ellipse as shown in FIG.

However, in the case of a drum head, when viewed in the X direction, the stem may be at the center of the head, so that the head ball is also shown in FIGS. 7A and 7B. Thus, the right and left are not limited (both can be combined). Thereafter, in order to prevent overlapping of stems, the flag on the side with the stem is checked after combining the stems. In the case of a drum stem, as shown in FIG. Regardless of the positional relationship between the stem and the center of the note head in the X direction, a fixed direction is checked (if the stem is upward, the right side is checked). It should be noted that this check flag is stored as indicating the attribute of the data in the stored data on the notehead side in order to prevent overlapping of the noteheads when combining the notehead and the stem candidate. In this case, as a configuration of the present application, each notehead is provided with a flag that specifies the position of the notehead candidate to be combined with the notehead candidate depending on whether the candidate is upward or downward. In the process of combining the stems with the stem candidates, it is prohibited to combine stems specified by the flag at positions other than the combining position.

Another reason why a special combining process must be performed in the case of a drum score is that note heads for dividing stems as shown in FIGS. 9A and 9B exist.
In the example shown in the figure, the black ball at the head of the stem should be recognized as an eighth note, not a quarter note. As shown in the figure, most of the noteheads that divide stems are patterns in which the head ball is a black ball and there is one notehead that divides the stem. Therefore, in the present configuration, first, as shown in FIG. 10, the black ball is not targeted, and the note head for dividing the stem and the candidate for the stems above and below it are combined, as shown in FIG. After recognizing drum notes with opposite stems that share noteheads, the stems on the right side of the figure delete the downward notes (instead of deleting the bit plane of the image as in the case of erasing, The process of deleting the data itself), and FIG.
Are combined as upper and lower stems as shown in the figure (right side in the figure) and finally combined with the remaining noteheads (black balls).

The above configuration is the same for a computer-readable recording medium storing the musical score recognition program according to claim 18, and includes a note head for dividing a stem by the combining function, and a note above and below the note head. A downward note deletion function for deleting notes with downward stems, which is executed after performing recognition with the tail candidates and performing recognition after recognizing drum notes of opposite stems that share the notehead by the recognition function, It has an execution program with a stem combining function for combining stems, and uses the combined as a stem candidate to combine the remaining noteheads with the combining function.

In the case of drum staves, another reason why a special combining process must be performed is that when a hi-hat open (°) exists near a stem to recognize a note head, It can be mistaken for a head. To prevent this, if you do not want to connect downward stems to the noteheads, check the flag on the left and no stems will be combined on this check side. The checked side is not allowed to combine stem candidates.)

The hi-hat closed (+) symbol and tuplet numeral shown in FIG. 11 are mistaken for a notehead, and when these are combined as a notehead at the head of the stem, the stem directions are completely opposite. It will be recognized as a note. As a countermeasure, these symbols and tuplet numbers may be registered in the dictionary as reject travel. However, the stem direction of drum staves is different from that of normal scores, and it can be limited to some extent. Is above the staff and the lower stem is not below the staff, that is, if the upper stem is above the fifth line and the lower stem is above the first line, the stem is Is upward [it is also effective as a countermeasure for false recognition of hi-hat open (°)], and when the lower stem is below the staff and the upper stem is not above the staff, that is, when the lower stem is When the stem is below the first line and the upper end of the stem is below the fifth line, the stem is determined to be downward, and the leading note head and the candidate stem are combined.

The above configuration is the same for a computer-readable recording medium storing the score recognition program according to claim 19, wherein the upper end of the stem is above the staff and the lower end of the stem. If the stem is not below the staff, the stem is upward, the stem bottom is below the staff, and the stem end is not above the staff,
The program further has a program for executing a stem direction determination function of determining that the stem is downward, and after performing the determination, the leading note head and the stem candidate are combined by the combining function.

However, when the above-described recognition process of the noteheads for dividing the stems and the combining process of these stemheads are performed, if the above-described configuration for determining the stem direction is implemented, FIG.
It becomes impossible to recognize the configuration in which the downward stem is connected to the common stem shown in FIG. 2 (if the upper stem is above the staff and the lower stem is not below the staff, Because it is determined to be an upward stem). For this reason, in the configuration of the present application, normalization in the stem direction is performed after the above-described processing for the note head that divides the stem is performed. That is, at the time of recognizing a drum note including a note having a note head that divides a stem, the leading note head of these drum notes and a stem candidate are combined, and a drum note having a note head that divides a stem is performed. After recognizing a drum note with a reverse stem that shares the note head, deletes a note with a lower stem, and combines the upper and lower stems as candidate stems to form a remaining head prefix. And
For other drum notes, if the upper stem is above the staff and the lower stem is not below the staff,
If the stem is upward, the lower end of the stem is below the staff, and the upper end of the stem is not above the staff, it is determined that the stem is downward and the candidate stem and the remaining stems are determined. After combining them with the head and returning to the original stem candidates if they do not meet these conditions (normalization processing for stem direction), the stem candidates are combined with the remaining note heads.

The above configuration is also applicable to a computer-readable recording medium storing the musical score recognition program according to the twentieth aspect, and includes a configuration for recognizing a drum note including a note having a note head for dividing a stem. At this time, the leading notehead of these drum notes and stem candidates are combined by the combining function, and for a drum note having a notehead that divides a stem, a note that shares the notehead by the recognition function. After recognizing a drum note with a tail reversed, the downward note deletion function deletes a note whose stem is downward, and a combination of upper and lower stems by the stem combination function as a stem candidate, Furthermore, while being combined with the remaining leading noteheads by the combining function, for other drum notes,
By the stem direction determination function, when the upper stem is above the staff and the lower stem is not below the staff, the stem is upward, and the lower stem is below the staff. If the stem has come out and the upper end of the stem does not come out above the staff, it is determined that the stem is downward, and the combining function is used to combine the candidate stem with the remaining noteheads. Those that do not match, further have a program for executing a note candidate return function of returning to the original stem candidate, and after returning to the original stem candidate, the combining function and the remaining note heads are combined by the combining function. And are to be combined.

[0030]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS One embodiment of the present invention will be described below with reference to the accompanying drawings. FIG. 13 shows an embodiment of a musical score recognizing apparatus that operates by reading a computer-readable recording medium storing a musical score recognizing program according to the present invention into an external storage device (or a CD-ROM drive or the like) such as a flexible disk drive FDD5 described later. It is a block diagram showing a form composition. This device is obtained by adding a scanner and a MIDI interface circuit to the configuration of an electronic computer such as a personal computer. The CPU 1 is a central processing unit that controls the entire score recognition apparatus based on a program stored in the ROM 2 or the RAM 3. Further, a timer circuit that interrupts the CPU 1 at a predetermined cycle set in advance is incorporated. The RAM 3 is used as an image data buffer, a work area, and the like in addition to the program area. The hard disk drive HDD4 and the flexible disk drive FDD5 store programs, image data, performance data, and the like. The CRT 6 displays video information output from the CRT interface circuit 7 based on the control of the CPU 1, and the information input from the keyboard 8 is sent to the CPU via the keyboard interface circuit 9.
It is taken into 1. The printer 10 prints print information output from the printer interface circuit 11 under the control of the CPU 1.

The scanner 12 optically scans a (printed) score, for example, and converts it into binary, grayscale or color image data. The scanner 12 may be any type such as a flatbed type, a handy type, and a feeder type. Types of scanners can be used. The image information read by the scanner 12 is taken into the RAM 3 or the HDD 4 via the scanner interface circuit 13. MIDI
The interface circuit 14 is a circuit that transmits and receives MIDI data to and from an external MIDI device such as a sound source module. The bus 15 connects each circuit in the musical score recognition device and exchanges various data, programs, addresses, and the like. In addition, a pointing device such as a mouse or a serial interface circuit such as RS232C may be provided.

FIG. 14 is a flowchart showing the main processing of the CPU 1. In step S <b> 1, the image of the musical score is taken into the RAM 3 by the scanner 12. The image is captured as binary image data. In step S2, in order to reduce blurring, dot noise, and the like,
Image quality smoothing processing such as graphic fusion is performed. In step S3, an image quality check process, which will be described later, is performed in order to obtain resolution and density information and to obtain reference data for staff detection in a later stage. In the music score recognition process, if the resolution and the density are out of the predetermined range, the recognition rate is reduced. Therefore, in step S3, it is checked whether or not these values are within the predetermined range. . In step S4, it is determined whether or not the result of the check in step S3 is image quality OK. If the result is not OK, the process returns to step S1 to change the resolution and density and re-acquire. In step S5, staff recognition, which will be described later, is performed. In the staff recognition process, a staff scanning start position detection process and a staff shift amount detection process are performed. In step S6, a paragraph recognition process is performed. This processing is roughly divided into paragraph recognition processing and bracket recognition processing. In the paragraph recognition process, staffs are detected in the entire image, a set of staffs whose left ends are located at approximately the same location between the staffs is examined, and it is checked whether the ends of the staffs are connected by black pixels. And recognize paragraphs. In step S7, the recognition result of the paragraph is displayed and the user checks whether or not the paragraph recognition result is correct, and it is determined whether or not it is OK. If the result is not OK, step S8 is performed.
Then, the paragraph recognition result is corrected. If the staff recognition fails, the subsequent processing cannot be performed, so that it is necessary to change the resolution and density and re-acquire the image. Therefore, in step S7, the recognition result of the staff is first displayed, and the user is determined whether or not the staff is correct. If the recognition is not correct, the process returns to step S1 to capture the image again, and the staff is correctly recognized. If so, the paragraph recognition result may be displayed and checked.

In step S9, the user is caused to select a drum part of each paragraph. Then step S1
At 0, the normal part recognizes the normal score and the drum part recognizes the drum score. After the recognition of the symbol is completed on all pages, in steps S11 to S13,
By scanning the drum part in one song twice (two loops), the drum notation is estimated for the entire song and the musical instruments are assigned according to the notation for the entire song. This configuration does not include a correction interface for the drum notation estimation result. This is because, if the recognition result is wrong, the recognized music score is corrected by correcting it.
Finally, in step S14, the assigned musical instrument is converted into a playable musical score data format with the specified pitch and pitch.

Hereinafter, steps S9 to S14 will be described in detail. In step S9, the user performs drum part setting at the same time as checking the paragraph recognition or correcting the paragraph recognition result. This is set by displaying the results of the recognized staff and paragraph, and checking the staff that is a drum score. Here, a flag is set in the part information of the data for storing the paragraph recognition result as to whether or not it is a drum score.

Based on the set flag information, the recognizing unit classifies normal music score recognition and drum score recognition, and in step S10, performs symbol recognition on the drum score. The differences between normal score recognition and drum score recognition are as follows. In drum notation recognition, recognition of a symbol that does not exist in the drum notation is skipped (however, in order to take countermeasures against erroneous settings, erroneous recognition, and typographical errors, the recognition itself is performed, and only the output may be limited). In drum notation recognition, recognition of a unique symbol and a unique character string is added to the drum notation, while recognition of an unnecessary character string in the drum notation is deleted. Also, recognition of drum heads other than black and white balls is added. On the other hand, the threshold value corresponding to the appearance probability and appearance form of the symbol of the drum music is changed (for example, since the appearance probability of the slur is low, the speed can be increased by making the threshold value stricter at the time of recognition, etc.). Similarly, the recognition threshold of the normal note is changed (the number of black ball chords is small, the appearance rate of white ball is small, etc. Therefore, the threshold value of the black ball is made strict, and in some cases, the white ball is not recognized. In this configuration, white balls are not recognized).

The recognition of the drum head is performed as follows. A black ball, which is the same as a normal score, in the note head of a drum score is subjected to a thick / fine separation process performed by erasing a staff line or the like and an ellipse detection process for recognizing a black ball portion, similarly to the normal score. However, in the case of a drum score, the number of chords of a black ball (when there is contact with a black ball) is small, and in some cases, note heads can be detected not by ellipse detection processing but by matching by label separation described later. In this configuration, as described above, recognition is not performed because the probability of occurrence of a white ball in a drum score is low. On the other hand, note heads of drum staves other than these are drawn with thin lines such as (x, 、), and there are various other types as well.
It cannot be detected by the thick and thin separation processing and the ellipse detection processing. Therefore, after removing stems, separate note head labels (rectangles set to recognize the target symbol)
This is performed by scanning the stem candidates (provisioned as stems) and matching detected labels around the stem candidates with the dictionary. However, note heads may be divided into a plurality of labels due to stem erasure, so if matching fails, scanning of stem candidates is further continued, and the next detected note head label and the separated label are added. Is performed, the matching with the dictionary is performed again. In addition to the above, there are unique drum score recognition and combining processes, which will be described later.

The noteheads to be recognized are as shown in FIG. There are other drum note heads, but if they correspond to this degree, general drum scores can be almost supported. It is also effective to change the type of notehead to be recognized depending on the position (pitch) of the staff in the staff (pitch). No such recognition has been made]. For noteheads other than black balls (white balls), the recognized notehead types are left in the symbol storage data. That is, the storage area drumNo in the recognition symbol storage data
Write the notehead type in te.

The details of a method of recognizing a musical score of a drum score in the configuration of the musical score recognizing apparatus will be described below. As a prerequisite for the recognition, a score image read by the scanner 12 is acquired in one dot and one byte, and one bit is set as a plane (bitSrc) of the original image.

(1) Normal note detection method (other than white ball) Normal note detection other than white ball (black ball detection) is performed by thick and thin separation processing. The original image plane (bitSrc) is used for normal note and drum note. Another two bit planes (bitT
ic, bitDrm). A staff erasure process is performed on the two copied bit planes. However, the staff is not erased in the plane (bitSrc) of the original image. The score image is scanned horizontally to eliminate short runs from one of the copied bitplanes (bitTic). Scans in the vertical direction as well, eliminating short runs.
The remaining portion constitutes a thick component on the score (black ball head, hook, etc.). Stem detection Detect fine vertical lines using short run bits erased in horizontal scan. Notehead detection If there is a thick part while scanning around the above vertical thin line (hereinafter referred to as "stem candidate"), the boundary line of this thick part is detected, coordinates are voted at certain intervals, and the elliptic equation is calculated. I do. If the elliptic equation is valid as a notehead, it is added to the ellipse storage data (ep). Stem combination / recognition Determines whether the above stem candidate and the ellipse are in a valid positional relationship as a note, and if appropriate, performs processing to combine with the stem and adds it to the recognition result as a note. I do. It is performed by the procedure described below.

The recognized black ball is erased from another copied bit plane (bitDrm) so as not to be subjected to the next drum note recognition. Since small notes have a high risk of misrecognition, it is better to take measures such as not recognizing them or deleting them.

(2) Drum Note Recognition Basic Processing Note Head Label Separation The left and right label bits of the stem candidates of the drum note bit plane (bitDrm) are erased with a certain width as shown in FIG. Then the label of the drum note head can be separated from the stem. However, in some cases, as shown in FIG. 2, the notehead label may be separated into a plurality of labels. Therefore, recognition is performed while performing label combination as described later. While scanning around matching candidate stems, bit planes (bi
tDrm) is detected. The detected label rectangle is slightly widened to the left and right, and the plane (bit)
Src) as a target for matching with the dictionary. The process of slightly expanding the rectangle to the left and right is a process for reducing stem noise. That is, since the distance between the detected label and the stem is short, if the rectangle is left as it is, a part of the stem may or may not enter the recognition target, and the matching with the dictionary will be greatly changed. Is expanded so that stems are included in the recognition target. The reason why the target bit plane is set to bitSrc instead of bitDrm is to prevent the staff erasing state from affecting the matching. Then, bitSrc in the rectangle (label) is matched with the dictionary. Any matching method may be used. The dictionary for matching is a combination of noteheads, stems, and staves.
Prepare a plurality of IDs. After the matching, the ID is integrated. That is, as shown in FIGS. 16 and 17, when the notehead intersects with the staff and when it intersects with the stem, these are further combined to prepare a plurality of IDs for one notehead type. At this time, the recognition target label (the label that matches the dictionary) is as shown in FIG. These are different I
D is matched with the dictionary and finally integrated into one ID called a notehead (x). These patterns may be used as one ID from the beginning. However, if this is done, the number of registration patterns for one ID becomes enormous. Therefore, as described above, if the classification is made based on the intersection with the staff and the intersection with the suffix, the number of patterns per ID becomes smaller, and it becomes easier to organize the dictionary. It is determined whether or not matching should be performed based on the size of the rectangle. For example, a rectangle whose vertical width is clearly smaller than the notehead does not need to be matched, and the process proceeds to label combining processing described later. If the width is wide, a tie may be connected to the note head, and a tie elimination process described later is performed. If this process fails and the rectangle remains large, matching is determined to have failed from the beginning, and the label combining process is reset. Label binding Matching between the notehead dictionary and the label is performed. If the label is not matched (ID_MATCHINGNONE), scanning of the label is continued, and the label is combined with the next detected label and re-recognized (again, matching with the dictionary). However, matching is performed once with the second label itself used for the combination, and if the priority of the ID of the matching result is the highest, this is prioritized. Also, the maximum size (dxt) of label combination and the reset of label combination (to enable label combination) are performed, and the vertical distance (d
yt) is also set. Further, if the priority of the ID of the recognition result is the highest, the rectangle combining is terminated at that time, and a rectangle and a distance are initialized to perform a new rectangle combining (the above two resetting processes are performed. ). In the matching, prior to the recognition rectangle including all the noteheads to be originally recognized during the combining of the labels, the matching result may have the same shape as another notehead. If the recognition result has a low priority, the ID and the rectangle are stored, and the next label scan is performed. If no higher priority ID is found, this is given priority. If the recognition target label formed during label combining is recognized by an ID different from the intended one, it is entered in the dictionary as a reject travel, and if the recognition result becomes this, recognition fails. You can also. There are special cases where the matching result is special, such as a combined notehead or a tremolo symbol that represents a combination of noteheads. If these are recognized, processing is performed accordingly, as described later. When matching with the dictionary is obtained, data is added to the note head data (ep). Stem combination / recognition Similar to black balls, joint processing with stem candidates is performed. However, special processing may be required for drum note heads. This will be described later. For the noteheads other than the black ball (white ball), the type of the recognized notehead is left in the symbol storage data. That is, the storage area drumN in the recognition symbol storage data
Write the notehead type in "note".

The details of the matching process including the label combining process are shown as flowcharts in FIGS. The processing shown in the figure is performed around a vertical line of a stem candidate by a certain width dw.
Searches for bitDrm while scanning with, and if found, applies a painting function to detect a rectangle (rectCur: a rectangle surrounding the detected label). While judging the size of the rectangle, first as shown in FIGS.
Matching is performed only with ur, depending on the result, merging with a previous rectangle, and matching with a merged rectangle (rectMrg: a rectangle in which labels are connected to each other). Step S21
In, the default values are rectMrg, rect
In addition to the initialization of the coordinates of the rectangle in each coordinate of Cur, the initialization of the saved notehead ID is also performed. In step S22, the y value at the highest point of the stem is put in yBef. In step S23, y is looped from the top to the bottom of the stem candidates. Then, in step S24, rectM
It is determined whether each coordinate of rg is a default value, and if it is a default value, the process jumps to step S29 described later. If this value is not the default value, the process proceeds to step S25.
If there is a certain distance where there is no dot at that time, it must be reset for the next scan. Therefore, in step S25, it is determined whether or not the absolute value of the difference between the value of the point y under investigation and the value of the uppermost suffix has exceeded the value of dyt. Fly, but if over, go to step S
At 26, it is determined whether the stored note ID is in the initial state. If it is the initial state, step S28 described later
Proceed to. Conversely, if it is not the initial state, in step S27, notehead data is created using the saved notehead ID and the rectangle. In step S28, a default value is set for each coordinate of the rectMrg, and the stored notehead ID is also initialized. The series of processing from S25 to S28 is rectMr
This is performed only when the coordinates of g are not in the initial state (see S24). After this processing is completed, or when it is determined in S25 that the value is not exceeded, step S2
In step 9, the periphery of the vertical line of the stem candidate is scanned with a certain width dw. In step S30, it is determined whether or not the bit bitDrm exists at the coordinates (x, y). If not, the process jumps to step S48, which will be described later, and ends the x-direction scanning loop. In step S30, if the same bit exists, the second label (rectangle) is detected by applying a painting function to the bit in step S31 (rectCu).
r). In step S32, it is determined whether or not the found second label rectangle is larger than the maximum size (dxt) of the label combination, and if it is determined to be larger, tie erasure processing described later is performed in step S33. In step S34, it is determined whether or not the tie erasure process has succeeded. If the tie erasure process has failed, the process jumps to step S42 and rec
Let yBef be the bottom y coordinate of tCur. If it is determined in S34 that the tie erasure process has been successful, and
32, the second label rectangle found is the dxt
If it is determined to be smaller, it is determined in step S35 whether or not the second label is large enough for matching. If it is smaller, the process jumps to step S48 to be described later, and the x-direction scanning loop is performed. finish. If it is determined in S35 that the size is sufficient, then in step S36, matching is once performed only with the second label (rectCur). In step S37,
It is determined whether or not the priority of the ID is the maximum. If the priority is determined to be the maximum, the process jumps to step S42 and
The lowest y coordinate of r is set to yBef, and step S4
At step 6, notehead data is created. If it is determined in step S37 that the priority is not the highest, it is determined in step S38 whether the coordinates of the label rectMrg to be combined match the default value. If not, the first label is determined in step S39. Is combined with the second label, and if they match, step S40
Is not subjected to the combining process, and the shape as it is is set as a merge rectangle (rectMrg). In step S41, the lowermost y coordinate of the rectMrg is set to the yBef. Next, in step S43, it is determined whether or not rectMrg is large enough for the matching. If it is determined that rectMrg is not sufficient, the process jumps to step S48 to be described later and ends the x-direction scanning loop. If it is determined in S43 that the size is sufficient, in step S44, matching with the dictionary of rectMrg is performed. In step S45, it is determined whether or not the priority of the ID is the maximum. If it is determined that the priority is not satisfied, the process jumps to step S46 to create notehead data using the saved notehead ID and the rectangle. If the priority is not the highest, the process jumps to step S48 to perform x-direction scanning. End the loop. After the above step S46, step S47
In, the process of putting a default value in each coordinate of rectMrg (end of label combination) is performed, and the saved notehead ID is stored.
Is initialized. If it is determined in S45 that the priority is not the maximum, or if label combining end processing has been performed in S47, the loop of the x-direction scanning is ended in step S48. Further, in step S49, the loop of the scanning in the y direction ends. Then, in step S50,
It is determined whether the remaining stored note ID is in the initial state, and if it is in the initial state, the process ends. If it is not the initial state,
In step S51, notehead data is created.

FIG. 23 shows the flow of the rectangle matching process in steps S36 and S44 in FIG. In step S52, matching with the dictionary is performed, and the processing result is entered in the ID. Step S
In 53, it is determined whether or not the matching has succeeded. If it is determined that the matching has failed (ID_MATCHINGNONE), the process ends. If it is determined in S53 that the matching has not failed, it is determined in step S54 whether or not the matching result is a reject travel, and if it is determined that the reject travel, the process ends. If it is determined in S54 that it is not a reject travel, it is determined in step S55 whether or not the matching result is a combined notehead. If it is determined that the combined notehead is present, in step S56, the notehead ID and the rectangle are determined. Is saved. On the other hand, if it is determined in S55 that it is not a combined note head, it is determined in step S57 whether or not the matching result is a tremolo symbol. If it is determined that the matching result is a tremolo symbol, in step S58, the tremolo thick portion is determined. An erasing process is performed. On the other hand, if it is determined in S57 that the character is not a tremolo symbol, then in step S59, the notehead ID
And the rectangle is saved. S56, S58 and S59
After the end of the process, the entire process ends.

(3) Tie erasure processing As described above, if the width of the label is wider than the notehead, it is considered that the tie is connected to the notehead, and the label cannot be separated. Will be performed. As shown in FIG. 24, scanning is performed vertically from the left and right ends of the rectangle in the reverse direction, and only one run is found, and the x width where the run length is equal to or less than a certain threshold value dyt2 is a certain threshold. If it is greater than or equal to the value dxt2, it can be determined that this is a notehead. In this case, the run length is longer than a certain length dvt2 (the tie portion in contact with the notehead has a run length longer than dyt2) or the second or subsequent run (vertical while scanning the run) Tie up to the position where it comes into contact with the run that is found separately in the direction) and erase up to that point.

(4) Combined notehead processing There are few chords where the noteheads touch the drum score, and there is no problem with the contact between black balls or between black balls and other noteheads. When the symbols are written on the same staff, there are cases where chords in which (x) touch each other exist as shown in FIG. In such a case, it is difficult to set the recognition rectangle by separating each note head before matching with the dictionary. Therefore, the combined note heads whose note heads are in contact with each other up and down are registered in the dictionary, and when this dictionary matches the combined note head (step S5 in FIG. 23).
5), data is added by the number of noteheads connected to the notehead data (see step S56 in the figure). Since such a label has a long shape in the vertical direction, the target ID of the dictionary can be changed according to the vertical width of the label, and the rate of erroneous recognition can be reduced. It is also effective to add a feature amount by size to the matching itself.

(5) Tremolo symbol processing According to the procedure described above, matching is performed with the dictionary while combining the labels around the stem candidates.
A tremolo symbol as shown in FIG. 4 can also be recognized. Especially in the case of drum music, there are relatively many tremolo symbols. Since the tremolo symbol is approximately the same thickness and spacing as the hooks,
If no countermeasures are taken, the flag will be counted in the same manner as in the case of a continuous hook, and it will be erroneously recognized as a note having a short duration such as a 32nd note. Therefore, the tremolo symbol is registered in the dictionary as shown in FIG. However, in this configuration, the symbol pasting interface does not correspond to the tremolo symbol, so that the symbol matching interface matches this (see step S57 in FIG. 23).
, A thick portion is erased (see step S58 in the figure) to take a countermeasure against flag count failure at the time of detecting consecutive hooks.

(6) Notehead-stem combination processing In this configuration, the noteheads and stems are combined after recognition of the notehead in the same manner as in normal music score recognition. In the case of a staff, a special process is also required for this combining process. Positional relationship between noteheads and stems One of the reasons is that noteheads other than black balls may have a stem at the center of the notehead, as shown in FIG. In addition, note heads are rarely attached to both sides of the stem. In such a case, the first notehead of the upward stem or the downward stem is combined, and then the middle notehead is combined. In the case of this configuration, in the case other than the black ball and the white ball, depending on the positional relationship between the center of the ellipse and the x-coordinate of the stem, one of the left and right stem combining flags is checked, and the leading of the stem is checked. Regarding the noteheads, it is determined that the combination is impossible based on the positional relationship in the x direction. However, in the case of a drum notehead (other than a black ball), when the first notehead is combined, it is above the vertical center of the stem. Decide whether to check left or right depending on whether it is below or below. That is, if it is below the middle point, the right side of the note head is checked regardless of the positional relationship in the x direction. The check heads in the middle of the stem depend on whether the stem is upward or downward. The reason why the notehead combination flag is used in this way is to avoid combining stems by disabling combining stem candidates to the side where the flag is checked. Noteheads that separate stems In the case of drum staves, another reason why special combining processing must be performed is that noteheads that separate stems as shown in FIGS. 9A and 9B exist. That is. As shown in the figure, most of the noteheads that divide stems are patterns in which the head ball is a black ball and there is one notehead that divides the stem. Therefore, in the present configuration, as shown in FIG. 10A, a note head for dividing a stem and candidates for stems above and below it are performed as shown in FIG. As a result, a drum note having the opposite stem direction and sharing the note head, as shown in FIG. Thereafter, a stem linking process is performed. However, in this case,
Since the stem length before the connection is shortened, it is necessary to reduce the shortest threshold value of the length of the stem connected to the note head. Prior to the stem linking process, the note whose right stem in FIG. 10B is downward is deleted, and the stem candidate is changed to a combination of upper and lower stems as shown in FIG. (Right side of the figure). Then, when notehead-stem concatenation for black balls is also performed, the stem candidates combined in the above process and black balls are connected. ○ Note Head and Hi-Hat Open In the case of drum staves, there is yet another reason that a special combining process must be performed. ○ In order to recognize note heads, the hi-hat open (°) existed near the stem. In that case, there is a possibility of being mistaken for a note head. As a countermeasure, in this configuration, the left side of the left and right stem combination flags is checked in advance in this configuration. By doing so, the downward stem is not attached to the note head. However, FIG.
As shown in the figure, a recognition rectangle is set for each part in one image (shown by a wavy line in the figure). However, if a paragraph is approaching, the symbol of the next paragraph may enter the recognition rectangle. is there. In consideration of the danger that the hi-hat open in the next paragraph may enter the recognition rectangle and the possibility that the hi-hat open (°) may be used for the pedal hi-hat below the first line, the circle below the first line may be used. The note head may check the right flag instead of the left flag. Countermeasures for mis-recognition of hi-hat closed and tuplet numbers In addition, the (+) sign and tuplet number of hi-hat closed shown in FIG. It will be recognized as a completely different note in the opposite direction. As a countermeasure, these symbols and tuplet numbers may be registered in the dictionary as reject travel, but the stem direction of drum staves is different from that of normal music and can be limited to some extent. Is above the fifth line and the lower end of the stem is above the first line, the stem is directed upward [hi-hat open (
°) is also effective as a countermeasure against misidentification]
When the stem is below the line and the upper end of the stem is below the fifth line, the stem is determined to be downward, and the leading note head and the candidate stem are combined. However, when the above-described recognition process of the noteheads that divide the stems and the combining process of these stemheads are performed, if the above-described configuration for determining the direction of the stems is implemented, the shared symbols shown in FIG. Recognition of a configuration in which a downward stem is connected to the head becomes impossible (when the upper end of the stem is above the fifth line and the lower end of the stem is above the first line, it is determined to be an upward stem). Therefore, in the present configuration, normalization in the direction of stems is performed after performing the above-described processing for noteheads that divide stems. That is, at the time of recognizing a drum note including a note having a note head that divides a stem, the leading note head of these drum notes and a stem candidate are combined, and a drum note having a note head that divides a stem is performed. After recognizing a drum note with a reverse stem that shares the note head, deletes a note with a lower stem, and combines the upper and lower stems as candidate stems to form a remaining head prefix. And for other drum notes, the upper end of the stem is above the fifth line and the lower end of the stem is the first.
If it is above the line, the stem is upward, and if the lower end of the stem is below the first line and the upper end of the stem is below the fifth line, it is determined that the stem is downward, and the candidate for stems and the remaining And the ones that do not meet these conditions are restored to the original stem candidates (stem direction normalization process), and then the candidate stems are combined with the remaining note heads. I have. Reduction of misrecognition by the proportion of thick parts on stems Even in normal music, if the proportion of thick parts on stem candidates is high,
It was excluded from notehead merging as a misidentification of stems. In the case of a drum score, since the number of chords of a black ball is small, the threshold value can be reduced, and the probability of erroneous recognition can be reduced. In particular, in the case of drum staves, notehead labels are divided and matched, so while labeling around a vertical line detected on a symbol that is not actually a note is divided and combined while matching, May be mistaken as Therefore, the above processing becomes effective. However, care must be taken when processing noteheads for dividing stems, since short note candidates exist. In order to solve this, once, FIG.
(b) Deletes notes whose stems on the right side are downward, and changes the stem candidates to the combination of upper and lower stems as shown in (c) of the same figure (right side of the figure). After performing the above note head-stem concatenation, the ratio of the thick portion on the stem is detected, and if the ratio is higher than the threshold value, the note may be deleted. Furthermore, in the case of misidentification of a note, considering that the possibility of misinterpretation of a chain hook is low and that the ratio of the thick part of a note with a chain hook is relatively high, It is also effective to perform a ratio-based check, or to make the threshold value of the ratio check of a thick portion without a continuous hook stricter than that with a continuous hook.

In the configuration of the present embodiment described above, in the drum score, as in the case of the normal score, the normal / small separation process performed by deleting the staff lines and the like and the ellipse detection process for recognizing the black ball portion are performed. The same black ball is detected as in the score. In addition, note heads of drum staves other than the black ball and the white ball whose appearance probability is low (no recognition is performed) are drawn with thin lines such as (x, ◇), and there are various types other than these. However, these cannot be detected by the thick / fine separation processing and the ellipse detection processing as in the case of black ball detection. This is performed by matching the detected label around the candidate with the dictionary.
However, note heads may be divided into a plurality of labels due to stem erasure, so if matching fails, scanning of stem candidates is further continued, and the next detected note head label and the separated label are added. Is performed, the matching with the dictionary is performed again. In addition, since there is a unique processing in the recognition and combination processing of the drum music, each processing is performed as described above.

[0049]

According to the configuration of the present invention described in detail above, it is possible to recognize a drum note in a drum score different from a normal score, and to convert it into a data format that can be played and / or displayed. Become. In particular, the recognition of noteheads in drum staves is performed by erasing stems, separating notehead labels, scanning candidate stems, and matching detected labels around candidate stems with the dictionary. Yes,
In addition, since noteheads may be divided into a plurality of labels due to stem erasure, if matching fails, further scanning of stem candidates is continued, and the next detected notehead label and the separated label are added. After performing the combining process, the matching with the dictionary is performed again, so that the drum notes can be accurately recognized.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram showing a state of a note head label separation process of a drum note.

FIG. 2 is an explanatory diagram showing a state in which a note head is divided into a plurality by a stem erasing process.

FIG. 3 is an explanatory diagram showing an example of a musical score including a note in a state where note heads are in contact with each other up and down.

FIG. 4 is an explanatory diagram showing an example of a musical score including a tremolo symbol.

FIG. 5 is an explanatory diagram showing an example of a tremolo symbol dictionary image.

FIG. 6 is an explanatory diagram showing a positional relationship determination method in the case of combining note heads and stems.

FIG. 7 is an explanatory diagram showing a combined state of note heads and stems of a drum staff.

FIG. 8 is an explanatory diagram showing a check state of a flag when a note head and a stem are combined.

FIG. 9 is an explanatory diagram showing an example in which stems are separated by note heads.

FIG. 10 is an explanatory diagram showing an example of a note recognition process for note heads dividing a stem;

FIG. 11 is an explanatory diagram showing an example of a musical score including hi-hat closed and tuplet numeral symbols.

FIG. 12 is an explanatory diagram showing an example of a configuration in which a downward stem is connected to a common note head.

FIG. 13 is a block diagram showing an embodiment configuration of a music score recognition apparatus which operates by reading a computer-readable recording medium storing a music score recognition program according to the present invention into an external storage device.

FIG. 14 is a flowchart illustrating main processing of a CPU.

FIG. 15 is an explanatory diagram showing a note head to be recognized.

FIG. 16 is an explanatory diagram showing an example in which a notehead to be integrated into one notehead type crosses a staff.

FIG. 17 is an explanatory diagram showing an example in which a notehead to be integrated into one notehead type intersects a stem;

FIG. 18 is an explanatory diagram showing a form of a label to be recognized in the case of the intersection.

FIG. 19 is a flowchart illustrating details of a matching process including a label combining process.

FIG. 20 is a flowchart showing details of a matching process including a label combining process.

FIG. 21 is a flowchart showing details of a matching process including a label combining process.

FIG. 22 is an explanatory diagram illustrating an actual example of a matching process including a label combining process.

FIG. 23 is a flowchart illustrating the flow of a rectangle matching process.

FIG. 24 is an explanatory diagram showing a tie recognition process for a note head label that has come into contact with a tie.

FIG. 25 is an explanatory diagram showing a state where the hi-hat open of the next paragraph has entered the recognition rectangle.

FIG. 26 is an explanatory diagram of a paragraph on a musical score.

FIG. 27 is an explanatory diagram showing noteheads, stems, and flags of black and white balls of notes to be recognized.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 CPU 2 ROM 3 RAM 4 Hard disk drive 5 Flexible disk drive 6 CRT 7 CRT interface circuit 8 Keyboard 9 Keyboard interface circuit 10 Printer 11 Printer interface circuit 12 Scanner 13 Scanner interface circuit 14 MIDI interface circuit 15 Bus

Claims (20)

[Claims] 1. A music score recognition method for reading an image of a music score, recognizing a music symbol thereof, and converting the music symbol into a music format that can be played and / or displayed. Music score recognition characterized by matching a separation label around a stem candidate detected by scanning a tail candidate with a dictionary, recognizing a drum head symbol, and performing a stem-note head combining process. Method. 2. The music score recognition method according to claim 1, wherein
When the matching between the separation label and the dictionary fails, the scan of the stem candidate is continued, and the matching processing between the next detected note head label and the separation label is performed, and then the matching with the dictionary is performed again. The music score recognition method according to claim 1, wherein: 3. The music score recognition method according to claim 2,
3. The score according to claim 2, wherein the notehead label itself detected and used for the combining process is also matched with the dictionary, and if the matching result has a higher priority, the recognition result is given priority. Recognition method. 4. The score recognizing method according to claim 2,
2. The musical score recognition according to claim 1, wherein label combining is performed repeatedly, priorities are given to respective recognition results recognized by matching during the combining, and the recognition results are determined in descending order of priority. Method. 5. The music score recognition method according to claim 1, wherein a tie contacting the notehead is deleted to perform label separation, and a drum note including the notehead contacting the tie is recognized. 5. The score recognition method according to claim 1, wherein: 6. A musical score recognition method according to claim 1, wherein the combined note heads whose note heads are vertically contacted are registered in a dictionary, and the dictionary is matched with the combined note heads. 6. The music score recognition method according to claim 1, further comprising the step of recognizing a combined notehead. 7. The musical score recognition method according to claim 1, wherein the tremolo symbol is registered in a dictionary, the tremolo symbol is recognized and deleted, and then the tremolo symbol is displayed including the tremolo symbol. 7. The score recognizing method according to claim 1, wherein another drum note is recognized. 8. The music score recognition method according to claim 1, wherein, when recognizing a drum note having a note head that divides a stem, the combination of the note head that divides a stem and candidate stems above and below it is recognized. After going to recognize the note with the opposite stem that shares the note head, the note with the lower stem is deleted, and the combination of the upper and lower stems is used as the stem candidate, and the remaining note heads are combined. The music score recognition method according to claim 1, wherein the score is combined. 9. The music score recognition method according to claim 1, wherein the stem is upward when the upper end of the stem is above the staff and the lower end of the stem is not below the staff. If the lower stem is below the staff and the upper stem is not above the staff, it is determined that the stem is downward and the first note head is combined with the candidate stem. Claim 1 characterized by the following:
8. The music score recognition method according to any one of claims 1 to 7. 10. The music score recognition method according to claim 8, wherein at the time of recognizing a drum note including a note having a note head that divides a stem, a process of combining a head note head of these drum notes and a stem candidate is performed. For a drum note having a note head that separates a stem, after recognizing a drum note that is opposite to the stem that shares the note head, delete the note whose stem is downward,
The combination of the upper and lower stems is combined with the remaining leading noteheads as stem candidates, and for other drum notes,
If the upper stem is above the staff and the lower stem is not below the staff, the stem is upward, the lower stem is below the staff and the upper stem is If it does not appear above the staff, it is determined that the stem is downward, and the candidate is combined with the remaining noteheads.
9. The musical score recognition method according to claim 8, wherein after returning to the original stem candidates, the stem candidates are combined with the remaining note heads. 11. A computer-readable recording medium storing a score recognition program for reading an image of a score, recognizing a music symbol of the score, and converting the score into a playable and / or displayable score format. A label separating function for separating the note head labels, a scanning function for scanning the stem candidates, and a drum that performs note head recognition by matching the separated labels around the stem candidates detected by the scanning with the dictionary. A computer-readable recording medium recording a score recognition program for executing a recognition function for recognizing a notehead and a combining function for combining the recognized notehead and the stem candidate. 12. A computer-readable recording medium storing the musical score recognition program according to claim 11, wherein a matching determination function for determining whether or not matching between the separation label and the dictionary is successful, and when the matching fails,
Continued scanning of note candidates by the scanning function, further comprising a program to perform a label combining function of performing a combining process of the next detected note head label and the separation label, after label combining, the 12. The computer-readable recording medium according to claim 11, wherein the recognition function causes the combined label and the dictionary to be matched again. 13. A computer-readable recording medium on which a musical score recognition program according to claim 12 is recorded, wherein the note head label itself detected next and used in the combining process is matched with the dictionary by the recognition function. 13. The computer-readable recording medium storing a musical score recognition program according to claim 12, wherein when the matching result has a higher priority, the recognition result is prioritized. 14. A computer-readable recording medium on which a musical score recognition program according to claim 12 is recorded, wherein said note head recognition and label combination are repeatedly performed during said note head recognition while being recognized. 13. The program according to claim 12, further comprising a program for executing a priority adding function of assigning a priority to each of the recognition results, wherein the recognition function corrects the recognition results in descending order of priority. A computer-readable recording medium storing a musical score recognition program. 15. A computer-readable recording medium on which the musical score recognition program according to claim 11 is recorded, further comprising a program for executing a tie erasing function for erasing a tie touching a notehead, and after the erasure. 15. The computer-readable recording according to claim 11, wherein the label separation function performs label separation, and the recognition function recognizes a notehead with which the tie is in contact. Medium. 16. A computer-readable recording medium on which a musical score recognition program according to claim 11 is recorded, wherein a combined note head in which note heads vertically contact each other is registered in a dictionary, and said note function is registered in said dictionary. 16. A computer-readable recording medium storing a musical score recognition program according to claim 11, wherein matching between the dictionary and the combined notehead is performed to recognize the combined notehead. 17. A computer-readable recording medium in which a score recognition program according to claim 11 is recorded, wherein tremolo symbols are registered in a dictionary, and said tremolo symbols are recognized by said recognition function. 17. The musical score recognition according to claim 11, further comprising a program for executing a symbol erasing function for erasing a tremolo symbol, and performing recognition of another drum note displayed including the tremolo symbol after erasure. A computer-readable recording medium on which a program is recorded. 18. A computer-readable recording medium in which a musical score recognition program according to claim 11 is recorded, wherein the combining function divides stems when recognizing a drum note having a note head that divides stems. Performs after combining the note head and the candidate for upper and lower stems and recognizing the drum note of the opposite stem sharing the note head by the recognition function. It has an execution program of a note deletion function and a stem combining function of combining upper and lower stems, and the combined one is used as a stem candidate and combined with the remaining noteheads by the combining function. A computer-readable recording medium storing the musical score recognition program according to claim 11. 19. A computer-readable recording medium on which the musical score recognition program according to claim 11 is recorded, wherein the upper end of the stem is above the staff and the lower end of the stem is below the staff. If not, the stem is pointing up,
When the lower stem is below the staff and the upper stem is not above the staff, the program further has a program for executing a stem direction determination function to determine that the stem is downward. ,
18. The computer-readable recording medium storing a musical score recognition program according to claim 11, wherein after performing the determination, the leading notehead and the stem candidate are combined by the combining function. 20. A computer-readable recording medium on which a musical score recognition program according to claim 18 is recorded, wherein said drum notes including notes having noteheads for dividing stems are recognized by said combining function. For a drum note having a notehead that divides a stem by performing a combining process of the first notehead and the stem candidate, the above-described recognition function recognizes a note note in the opposite direction to the notehead sharing the notehead. Then, the downward note deletion function deletes notes with lower stems, and the upper and lower stems combined by the stem combining function are used as stem candidates, and the remaining leading initials are combined by the combining function. With regard to other drum notes, the stem direction determination function determines that when the stem upper end is above the staff and the stem lower end is not below the staff, If the tail is upward and the lower end of the stem is below the staff and the upper end of the stem is not above the staff, it is determined that the stem is downward and the combining function determines that the stem is a candidate. In addition to combining with the remaining noteheads, those which do not meet these conditions further have a program for performing a note candidate return function to return to the original note candidates, and after returning to the original note candidates, 19. The computer-readable recording medium storing a score recognition program according to claim 18, wherein the note-stem candidates are combined with the remaining noteheads by a combining function.