CN104778467A - Automatic musicofasong photographing and playing system - Google Patents

Abstract

The embodiment of the invention discloses an automatic musicofasong photographing and playing system. A method of the system mainly comprises the following several key steps: acquiring images and preprocessing the images; determining a five-line staff and positions of bars according to the ratio of pixels; determining music rhythms by using image matching; determining musical notes of each bar; and converting the musical notes into digital signals and playing the musical notes. By virtue of the application of the automatic musicofasong photographing and playing system, a user can enjoy the melody of the musicofasong without understanding of the musicofasong; meanwhile, the musicofasong is conveniently photographed by a camera; the automatic musicofasong photographing and playing system has a high practical value.

Description

A kind of music score of Chinese operas is taken pictures automatic playing system

Technical field

The present invention utilizes image processing techniques, concentrates and solves the identification of staff and playback problem, constructs emphatically a music score of Chinese operas and to take pictures automatic playing system.

Background technology

Music is the instrument that people's body and mind loosens, and musical instrument has a lot, but the music score of Chinese operas only has one, and the music score of Chinese operas is the representative of melody.Naturally can understand for the people being familiar with staff, unfamiliar people can search on the internet, but the not every music score of Chinese operas can be found, and to take pictures automatic playing system so this patent devises a music score of Chinese operas for this problem, as long as accomplish the music score of Chinese operas, just music can be enjoyed.

Just at present, not yet find about technology in this respect in open source information, only have mellotron, or the system play of oneself setting a song to music.Based on this, consider the opening of operating system, the present invention devises a application system, utilizes camera to take pictures to the music score of Chinese operas, and plays the music score of Chinese operas.

Summary of the invention

The object of the invention is design application system, taking pictures by calling camera to the music score of Chinese operas, by image processing techniques identification note, be transformed to the frequency signal of loudspeaker, making it sounding is music.

For achieving the above object, the automatic playing system that the present invention proposes comprises the following steps:

One, the pre-treatment step of image: complete tiling music score of Chinese operas paper will be comprised with in the photo of camera shooting, by the square boundary of rim detection determination music score of Chinese operas paper, carry out rotational transform and become standard music score of Chinese operas picture;

Two, staff, the determining step of brief summary: by the line by line and by column pixel detection to binary image, calculate black picture element percentage, determine the line position of staff and the position, separatrix of trifle;

Three, the determining step of music score of Chinese operas beat: the beat digital picture of Article 1 staff (left-hand part) is extracted and, and to compare with in advance ready standard syllable picture, determine beat;

Four, note step is identified: judge the note classification in each syllable, and determine the pronunciation representated by it;

Five, transfer digital signal to and play step: after all notes are determined, according to the vibration frequency corresponding relation of music and loudspeaker, making it to be converted to digital signal, and pronounced by loudspeaker.

The determining step of music score of Chinese operas beat, the detailed process of this step is as follows:

1) border of beat digital picture, is determined, the position of present staff and trifle is determined, first remember that binary image is A, conveniently determine the scope of note, staff is removed in binaryzation picture, in the scope of the first trifle of first row staff (left-hand part), the presence or absence detecting black picture element is by column determined to be designated as P by the width range of beat digital picture _leftand P _right.And in this width, detect the altitude range determining beat digital picture line by line, be designated as P _highwith P _low.Then the little figure image of beat digital picture is designated as:

A1＝A(P _high：P _low，P _left：P _right)

2) template matching method determination beat, is adopted: existing digital picture and template digital picture are subtracted each other, the template digital picture that error is minimum and this existing picture match.B is existing digital picture, and A1 is template picture to be matched, namely finds B and makes Σ _iΣ _j| B-A1| is minimum, i and j is respectively line index and the column index of image.

Identify note step, the detailed process of this step is as follows:

1) determine the square boundary of note, first remember that binary image is.Because the position of staff is determined, conveniently determine the scope of note, in binaryzation picture, remove staff, in single monosyllabic scope, the presence or absence detecting black picture element by column determines note width range, is designated as Q _leftand Q _right.And in this width line by line detect determine note altitude range, be designated as Q _highwith Q _low.Then the little figure image of note is designated as:

I1＝I(Q _high：Q _low，Q _left：Q _right)

2) to I1 process, using note width as feature, i.e. (Q _right-Q _left), note is divided into monophonic note (whole note, half dieresis, 1/4 note) and multitone symbol (multitone symbol is the connection of multiple monophonic note).

A. for monophonic note, first special note (as tremolo note) is determined whether according to the pixel distribution near note vertical line, if not special note, height shared by note, i.e. (Q _low-Q _high), judge there is several sound, ask pixel barycenter to determine its diaphone to each sound.

The position of longitudinal barycenter is:

$\mathrm{Pi}=\frac{{\mathrm{\Σ}}_i{\mathrm{\Σ}}_{j}I1(i,j)\×i}{{\mathrm{\Σ}}_{i,j}I1(i,j)}$

The position of horizontal barycenter is:

$\mathrm{Pj}=\frac{{\mathrm{\Σ}}_j{\mathrm{\Σ}}_{i}I1(i,j)\×j}{{\mathrm{\Σ}}_{i,j}I1(i,j)}$

Determine which kind of note it is according to the relative position of longitudinal barycenter in staff, judge the duration of note according to the presence or absence of barycenter (Pi, Pj) surrounding white pixel.

B. multitone is accorded with, equally first find note vertical line, several note vertical lines are found just to have several note, judge the pixel distribution near note vertical line one by one, namely the chequered with black and white distribution number of plies is judged, by the multiple that the number of plies determination duration of a sound reduces, afterwards it is divided into multiple monophonic note again, repeats step A.

Utilizing the embodiment of the present invention, the melody of the music score of Chinese operas can be enjoyed when being ignorant of the music score of Chinese operas, utilize camera to take very convenient simultaneously, have great practical value.

Accompanying drawing explanation

Fig. 1 is that a kind of music score of Chinese operas of the present invention is taken pictures the system flowchart of automatic playing system;

Fig. 2 is the flow chart of steps that concrete implementation step S3 determines music score of Chinese operas beat;

Fig. 3 is the flow chart of steps that concrete implementation step S4 identifies note.

Embodiment

Below in conjunction with accompanying drawing, specific embodiments of the present invention is described in detail.

Fig. 1 is process flow diagram of the present invention, comprises the following steps:

Step S1: the pre-service of image;

Step S2: row and the trifle position of determining staff;

Step S3: the beat determining the music score of Chinese operas;

Step S4: identify every monosyllabic note one by one;

Step S5: be converted to digital signal and play.

To be specifically described each step below:

Step S1: confirm that the music score of Chinese operas is on the regular rectangle paper be printed on without other pollutions, and comprise complete paper in the photo of camera shooting.By rim detection determination music score of Chinese operas paper border in the picture, Boundary Extraction is proposed out and becomes rectangle by image rotation, and by image binaryzation.

Step S2: row and the trifle position of determining staff

2.1, the line position of staff is determined, detect line by line, determine that the sum of black picture element in every a line (being 0 in computing machine) accounts for the ratio of this journey total pixel number, if more than a, assert this behavior spectral line (a is parameter, and span is 0 to 1).

2.2, determine trifle to be scanned by the file between two adjacent staffs, determine that the sum of black picture element in each row accounts for the ratio of this journey total pixel number, if more than b, assert this behavior bar line (b is parameter, and span is 0 to 1).

Step S3: the beat determining the music score of Chinese operas, the idiographic flow that Fig. 2 gives the method is as follows

3.1, the border of beat digital picture is determined, the position of present staff and trifle is determined, first remember that binary image is A, conveniently determine the scope of note, staff is removed in binaryzation picture, in the scope of the first trifle of first row staff (left-hand part), the presence or absence detecting black picture element is by column determined to be designated as P by the width range of beat digital picture _leftand P _right.And in this width, detect the altitude range determining beat digital picture line by line, be designated as P _highwith P _low.Then the little figure image of beat digital picture is designated as:

A1＝(P _high：P _low，P _left：P _right)

3.2, template matching method determination beat is adopted: existing digital picture and template digital picture are subtracted each other, the template digital picture that error is minimum and this existing picture match.B is existing digital picture, and A1 is template picture to be matched, namely finds B and makes min (Σ _iΣ _j| B-A1|) minimum, i and j is respectively line index and the column index of image.

Step S4, identify every monosyllabic note one by one, the idiographic flow that Fig. 3 gives the method is as follows

4.1, determine the square boundary of note, first remember that binary image is.Because the position of staff is determined, conveniently determine the scope of note, in binaryzation picture, remove staff, in single monosyllabic scope, the presence or absence detecting black picture element by column determines note width range, is designated as Q _leftand Q _right.And in this width line by line detect determine note altitude range, be designated as Q _highwith Q _low.Then the little figure image of note is designated as:

I1＝I(Q _high：Q _low，Q _left：Q _right)

4.2, to I1 process, using note width as feature, i.e. (Q _right-Q _left), note is divided into monophonic note (whole note, half dieresis, 1/4 note) and multitone symbol (multitone symbol is the connection of multiple monophonic note).

4.2.1, for monophonic note, first special note (as tremolo note) is determined whether according to the pixel distribution near note vertical line, if not special note, height shared by note, i.e. (Q _low-Q _high), judge there is several sound, ask pixel barycenter to determine its diaphone to each sound.

The position of longitudinal barycenter is:

$\mathrm{Pi}=\frac{{\mathrm{\Σ}}_i{\mathrm{\Σ}}_{j}I1(i,j)\×i}{{\mathrm{\Σ}}_{i,j}I1(i,j)}$

The position of horizontal barycenter is:

$\mathrm{Pj}=\frac{{\mathrm{\Σ}}_j{\mathrm{\Σ}}_{i}I1(i,j)\×j}{{\mathrm{\Σ}}_{i,j}I1(i,j)}$

Determine which kind of note it is according to the relative position of longitudinal barycenter in staff, judge it is half dieresis or 1/4 note or whole note according to the presence or absence of barycenter (Pi, Pj) surrounding white pixel.

4.2.2, multitone is accorded with, equally first find note vertical line, several note vertical lines are found just to have several note, judge the pixel distribution near note vertical line one by one, namely the chequered with black and white distribution number of plies is judged, by the multiple that the number of plies determination duration of a sound reduces, afterwards it is divided into multiple monophonic note again, repeats 4.2.1 step.

After step S5, all notes are determined, according to the vibration frequency corresponding relation of music and loudspeaker, make it to be converted to digital signal, and pronounced by loudspeaker.

Below by reference to the accompanying drawings the take pictures embodiment of Play System of proposed qin spectrum is set forth.By the description of above embodiment, one of ordinary skill in the art clearly can recognize that the mode that the present invention can add required general hardware platform by software realizes.Based on such understanding, technical scheme of the present invention can embody the part that prior art contributes in essence in other words in form of a computer software product, this software product is stored in a storage medium, comprises some instructions and performs method described in each embodiment of the present invention in order to make one or more computer equipment.

According to thought of the present invention, all will change in specific embodiments and applications.In sum, this description should not be construed as limitation of the present invention.

Above-described embodiment of the present invention, does not form the restriction to invention protection domain.Any amendment done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.

Claims (3)

1. the music score of Chinese operas is taken pictures an automatic playing system, it is characterized in that, comprises following several committed step:

One, the pre-treatment step of image: complete tiling music score of Chinese operas paper will be comprised with in the photo of camera shooting, by the square boundary of rim detection determination music score of Chinese operas paper, carry out rotational transform and become standard music score of Chinese operas picture;

Two, staff, the determining step of brief summary: by the line by line and by column pixel detection to binary image, calculate black picture element percentage, determine the line position of staff and the position, separatrix of trifle;

Three, the determining step of music score of Chinese operas beat: the beat digital picture of Article 1 staff (left-hand part) is extracted and, and to compare with in advance ready standard syllable picture, determine beat;

Four, note step is identified: judge the note classification in each syllable, and determine the pronunciation representated by it;

Five, transfer digital signal to and play step: after all notes are determined, according to the vibration frequency corresponding relation of music and loudspeaker, making it to be converted to digital signal, and pronounced by loudspeaker.

2. the method for claim 1, is characterized in that, in the determining step of music score of Chinese operas beat, the detailed process of this step is as follows:

1) border of beat digital picture is determined, and the position of staff and trifle is determined, first remember that binary image is A, conveniently determine the scope of note, staff is removed in binaryzation picture, in the scope of the first trifle of first row staff (left-hand part), the presence or absence detecting black picture element is by column determined to be designated as P by the width range of beat digital picture _leftand P _right, and in this width, detect the altitude range determining beat digital picture line by line, be designated as P _highwith P _low, then the little figure image of beat digital picture is designated as:

A1＝A(P _high：P _low，P _left：P _right)

2) adopt template matching method determination beat: existing digital picture and template digital picture are subtracted each other, the template digital picture that error is minimum and this existing picture match, B is existing digital picture, and A1 is template picture to be matched, namely find B and make min (∑ _i∑ _j| B-A1|) minimum, i and j is respectively line index and the column index of image.

3. the method for claim 1, is characterized in that, identifies that in note step, the detailed process of this step is as follows:

1) determine the square boundary of note, first remember that binary image is I; Because the position of staff is determined, conveniently determine the scope of note, in binaryzation picture, remove staff, in single monosyllabic scope, the presence or absence detecting black picture element by column determines note width range, is designated as Q _leftand Q _right, and in this width line by line detect determine note altitude range, be designated as Q _highwith Q _low, then the little figure image of note is designated as:

I1＝I(Q _high：Q _low，Q _left：Q _right)

2) to I1 process, using note width as feature, i.e. (Q _right-Q _left), note is divided into monophonic note (whole note, half dieresis, 1/4 note) and multitone symbol (multitone symbol is the connection of multiple monophonic note);

A, for monophonic note, first determine whether special note (as tremolo note) according to the pixel distribution near note vertical line, if not special note, height shared by note, i.e. (Q _low-Q _high), judge there is several sound, ask pixel barycenter to determine its diaphone to each sound,

The position of longitudinal barycenter is:

$\mathrm{Pi}=\frac{{\mathrm{\Σ}}_i{\mathrm{\Σ}}_{j}I1(i,j)\×i}{{\mathrm{\Σ}}_{i,j}I1(i,j)}$

The position of horizontal barycenter is:

$\mathrm{Pj}=\frac{{\mathrm{\Σ}}_j{\mathrm{\Σ}}_{i}I1(i,j)\×j}{{\mathrm{\Σ}}_{i,j}I1(i,j)}$

Determine which kind of note it is according to the relative position of longitudinal barycenter in staff, judge it is half dieresis or 1/4 note or whole note according to the presence or absence of barycenter (Pi, Pj) surrounding white pixel;

B, multitone to be accorded with, equally first find note vertical line, several note vertical lines are found just to have several note, judge the pixel distribution near note vertical line one by one, namely the chequered with black and white distribution number of plies is judged, by the multiple that the number of plies determination duration of a sound reduces, afterwards it is divided into multiple monophonic note again, repeats step A.