CN108416359A - A kind of music score identifying system and recognition methods - Google Patents
A kind of music score identifying system and recognition methods Download PDFInfo
- Publication number
- CN108416359A CN108416359A CN201810193256.7A CN201810193256A CN108416359A CN 108416359 A CN108416359 A CN 108416359A CN 201810193256 A CN201810193256 A CN 201810193256A CN 108416359 A CN108416359 A CN 108416359A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- matrix
- music score
- note
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/273—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion removing elements interfering with the pattern to be recognised
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to music score to identify field, disclose a kind of music score identifying system and recognition methods, image input module, image pre-processing module, low-rank image module, difference image module, spectral line generation module, spectral line removing module, note image module, note comparison identification module, note output module；The music score of input is pre-processed by image pre-processing module；Low-rank image module and difference image module are generated by pretreated music score；The low-rank image module and difference image module of generation enter spectral line generation module；The spectral line of generation enters the deletion that spectral line removing module carries out spectral line；The music score for deleting spectral line generates note image module；The note image module of generation enters note comparison identification module and carries out comparison identification.The present invention, which compares, identifies that the note completed enters note output module and carries out last music score output.Invention increases the efficiency of music score identification, are very suitable for promoting the use of.
Description
Technical field
The invention belongs to music score identification field more particularly to a kind of music score identifying system and recognition methods.
Background technology
It is development trend by the binary data that paper score saves as computer capacity " understanding " in digitized today.
And in face of the music score of substantial amounts, it realizes digitlization only by artificial spectrum of reading, is a time-consuming and laborious job, in order to realize
Paper score digitizes, and Optical Music Recognition technology is come into being.OMR is by after paper score scanning input computer, to pleasure
Spectrogram picture is pocessed, identifies, analyzes, the process of the final computer digit expression for obtaining music score.Most important spy in music score
Sign is one group of parallel horizontal line, i.e. staff.They are necessary for musician, to determine pitch and specification sound
Symbol etc. graphical symbols writing region and size, spectral line there are one distinguishing feature be most music score figures and symbol therewith
There are intersection or overlapping.And when note identifies, it needs to separate note from spectral line, most of optics music score is known
Note separation is an obstacle in other system.
In recent years, have scholar to carry out the carrier frequency estimation of single CF signal under Alpha Stable distritation noise models
Certain research, but its achievement in research is less.Sun Yong plums et al. propose to be based on fractional lower-order statistics, it is proposed that one kind is suitable for
The new spectral analysis method of Alpha Stable distritations.This method is composed using fractional lower-order covariance, to whole value ranges (0 ＜ α
≤ 2) signals with noise carries out frequency-response analysis, and proposes weighting and overlap method of average estimated score low order covariance spectrum.It should
Method is all suitable for any one α value, and the variance of Power estimation is smaller.But there is no provided to carrier frequency estimation in the document
Specific algorithm step, carrier frequency (Sun Yongmei, Qiu Tianshuan, Li Hui, Wei can just be estimated by still needing to further investigate its covariance spectrum
Spectral analysis method [J] the Dalian University Of Communications journal of plum α Stable distritation processes, 2010,31 (4):9-12).Zhao Chunhui et al.
The problem of seriously degenerating in Alpha Stable distritation noises for the method for parameter estimation based on cyclic-statistic proposes
A kind of mpsk signal carrier frequency estimation method based on fractional lower-order Cyclic Spectrum analyzes the psk signal under different M values
The relationship of its carrier frequency and corresponding scores low order Cyclic Spectrum parameter, gives the load of suitable all psk signals on this basis
Wave frequency rate method of estimation.This method is when mixing signal-to-noise ratio is -10dB and α is 1.5, the normalization of the carrier frequency estimation of bpsk signal
Mean square error is that the normalized mean squared error of 0.043, QPSK signal carrier frequency estimation is 0.041, therefore the carrier frequency under low signal-to-noise ratio
Estimation performance is still to be improved, and (mpsk signal parameter is estimated under Zhao Chunhui, Yang Weichao, Cheng Baozhi .Alpha Stable distritation noise backgrounds
Count [J] Shenyang University of Technology journal, 2013,35 (2):194-199).
However, since the noise circumstance of music notation space communication is complicated and changeable and interference problem is serious, signal easily by
It influences and faint state is presented.Therefore, the detection of small-signal under Low SNR in music notation deep space communication is improved
It is current urgent problem to be solved with parameter Estimation.
In conclusion problem of the existing technology is：Existing system is a technology barrier, nothing for the separation of spectral line
Method meets the needs of user.It is poor to obtain data accuracy.
Invention content
In view of the problems of the existing technology, the present invention provides a kind of music score identifying system and recognition methods.
The invention is realized in this way a kind of music score identifying system is provided with：
Image input module, image pre-processing module, low-rank image module, difference image module, spectral line generation module, spectrum
Line removing module, note image module, note comparison identification module, note output module.
Another object of the present invention is to provide a kind of music score recognition method, including：
Step 1, music score to be identified are inputted by image input module；
The music score of step 2, input is pre-processed by image pre-processing module；
Step 3 generates low-rank image module and difference image module by pretreated music score；
Step 4, the low-rank image module and difference image module generated enter spectral line generation module；
Step 5, the spectral line generated enter the deletion that spectral line removing module carries out spectral line；
The music score of step 6, deleted spectral line generates note image module；
Step 7, the note image module generated enter note comparison identification module and carry out comparison identification；
Step 8 compares and identifies that the note completed enters note output module and carries out last music score output.
Further, staff spectral line detection is carried out with delet method, and the musical score image of input is converted into musical score image
Matrix D is decomposed into the sum of two matrixes of low-rank matrix A and sparse matrix E, i.e. D=A+E, the mesh of solving-optimizing problem by matrix D
Scalar functions：
The formula indicates：When the order that constraints is A is less than r and D=A+E so that the F- Norm minimums of E；
The object function of this optimization problem is carried out to be relaxed to following convex optimization problem：
It is D=A+E that the formula meaning, which is in constraints, so that the nuclear norm of A is minimum, and 1 norm of E is penalty term, wherein
Nuclear norm be singular values of a matrix and, 1 norm is the sum of absolute value, and D ∈ Rm × n, A ∈ Rm × n, E ∈ Rm × n, Rmxn indicate m
The real number matrix of row n row, λ indicate Lagrange multiplier vector, | | | | F indicates F- norms, | | | | * indicates nuclear norm, |
| | | 1 indicates 1- norms, | | | | 2 indicate 2- norms, | | | | ∞ indicates Infinite Norm；
Above-mentioned optimization problem is solved using augmented vector approach, constructs Augmented Lagrangian Functions：
Iterative formula is：
A indicate low-rank matrix, E indicate sparse matrix, Y indicate Lagrange multiplier initial value be Y0=D/max (| | Y | |
2, λ -1 | | Y | | ∞), μ indicates that penalty factor initial value is that k indicates that iterations initial value is 0；
The low-rank matrix A of input matrix D is obtained to get to spectral line information；
Spectral line is solved to be expert at and thereon or the difference image modular matrix C that has differences of next line：
C=H.*D
Wherein, C ∈ Rm × n, H ∈ Rn × n are
C indicates that difference image modular matrix belongs to the real number matrix of m rows n row, and H indicates that high-pass filtering matrix belongs to n rows n row
Real number matrix,
Obtained difference image modular matrix, then by with after the progress AND operation of low-rank image module matrix, obtaining
Image array again with original image matrix carry out nonequivalence operation, obtain as a result, formula is as follows：
S=C | | A
B=S xor D
B is required sign matrix.
Further, the image detecting method of the low-rank image module includes：Extract the figure of image pre-processing module processing
The color characteristic and adaptive LBP operator feature of picture；
Multiple features low-rank matrix indicates model；
s.t.Xi=XiAi+Ei, i=1 ..., K
Wherein α is greater than 0 coefficient,For measuring the error that noise and wild point are brought；
It is equivalent to drag：
Extraction adaptive LBP operator characteristics algorithm is as follows：
(1) image of input system is converted into gray level image, summed to image { grayv (i, j) } grey scale pixel value, then
Obtain average value：
(2) background is removed using total textural characteristics, calculates the difference of the grey scale pixel value and mean pixel gray value of image
The sum of absolute value of value is averaged：
Background is removed using Local textural feature, with the sliding window of 3 × 3 sizes, traverses image, seeks center pixel ash
The difference of angle value and neighboring pixel gray value, the averaged in each video in window：
(3) according to experimental data, the method for the Fitting Calculation adaptive threshold：
Further, estimation of the note comparison identification module to progress exact value after note comparison identification；It specifically includes：To sound
The psk signal containing Alpha Stable distritation noises of symbol image module transmission seeks cycle covariant function；
Fourier transformation is carried out to the cycle covariant function, it is asked to recycle co-variation spectrum；
Pass through the section of the cycle co-variation spectrum extraction cycle frequency ε=0Hz；
The peak value for searching for the positive and negative semiaxis in the section finds the corresponding positive negative frequency value of the peak value, and takes absolute value
The estimated value averaged afterwards as carrier frequency；
It is described receive signal cycle covariant function include：
The signal contains the mpsk signal for obeying S α S partition noises, can be expressed as：
Wherein E is the mean power of signal,M=2k, m=1,
2 ... M, q (t) indicate that rectangular pulse waveform, T indicate symbol period, fcIndicate carrier frequency, φ0Initial phase is indicated, if w
(t) it is the non-Gaussian noise for obeying S α S distributions, then its autocovariance function is defined as：
Wherein (x (t- τ))<p-1>=| x (t- τ)p-2X* (t- τ), γx(t-τ)The coefficient of dispersion of x (t), then the cycle of x (t)
Co-variation is defined as：
Wherein ε is known as cycle frequency, and T is a code-element period；
The cycle co-variation spectrum for receiving signal is carried out as follows：
Cycle co-variation spectrum is to recycle the Fourier transformation of covariant function, is expressed as：
It recycles co-variation spectrum and is derived as：
As M >=4,Place,
As M=2,
Wherein Q (f) is the Fourier transformation of q (t), and
Carrier frequency estimation is realized in the section that cycle frequency ε=0Hz in co-variation spectrum is recycled by extraction, is carried out as follows：
The envelope of the cycle co-variation spectrum on n=0, that is, ε=sections 0Hz be：
As f=± fcWhen, envelope obtains maximum value.
The present invention is realized separates note from spectral line, most effective to overcome existing most of optics music score knowledges
Existing technology barrier is detached for middle note in other system, considerably increases the efficiency of music score identification, being very suitable for promoting makes
With.
The present invention can carry out the carrier frequency of psk signal under Alpha Stable distritation noises estimation and obtain accurate note number
According to；
The present invention has preferable estimation performance under low signal-to-noise ratio environment；
In identical emulation experiment environment and identical chip rate, carrier frequency, sample frequency, sampling number and noise
Than etc. signal parameters setting under the conditions of, the present invention than existing method have preferably estimation performance.
The present invention can effectively improve the robustness and accuracy of music data detection according to LBP feature operators, reduce and miss
Inspection.
Description of the drawings
Fig. 1 is music score identifying system structural schematic diagram provided in an embodiment of the present invention；
In figure：1, image input module；2, image pre-processing module；3, low-rank image module；4, difference image module；5、
Spectral line generation module；6, spectral line removing module；7, note image module；8, note compares identification module；9, note output module.
Specific implementation mode
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and coordinate attached drawing
Detailed description are as follows.
The structure of the present invention is explained in detail below in conjunction with the accompanying drawings.
As shown in Figure 1, the music score identifying system described in the embodiment of the present invention includes：Image input module 1, image preprocessing
Module 2, low-rank image module 3, difference image module 4, spectral line generation module 5, spectral line removing module 6, note image module 7,
Note comparison identification module 8, note output module 9 are simultaneously sequentially connected.
The image detecting method of the low-rank image module includes：Extract the color of the image of image pre-processing module processing
Feature and adaptive LBP operator feature；
Multiple features low-rank matrix indicates model；
s.t.Xi=XiAi+Ei, i=1 ..., K
Wherein α is greater than 0 coefficient,For measuring the error that noise and wild point are brought；
It is equivalent to drag：
Extraction adaptive LBP operator characteristics algorithm is as follows：
(1) image of input system is converted into gray level image, summed to image { grayv (i, j) } grey scale pixel value, then
Obtain average value：
(2) background is removed using total textural characteristics, calculates the difference of the grey scale pixel value and mean pixel gray value of image
The sum of absolute value of value is averaged：
Background is removed using Local textural feature, with the sliding window of 3 × 3 sizes, traverses image, seeks center pixel ash
The difference of angle value and neighboring pixel gray value, the averaged in each video in window：
(3) according to experimental data, the method for the Fitting Calculation adaptive threshold：
Further, estimation of the note comparison identification module to progress exact value after note comparison identification；It specifically includes：To sound
The psk signal containing Alpha Stable distritation noises of symbol image module transmission seeks cycle covariant function；
Fourier transformation is carried out to the cycle covariant function, it is asked to recycle co-variation spectrum；
Pass through the section of the cycle co-variation spectrum extraction cycle frequency ε=0Hz；
The peak value for searching for the positive and negative semiaxis in the section finds the corresponding positive negative frequency value of the peak value, and takes absolute value
The estimated value averaged afterwards as carrier frequency；
It is described receive signal cycle covariant function include：
The signal contains the mpsk signal for obeying S α S partition noises, can be expressed as：
Wherein E is the mean power of signal,M=2k, m=1,
2 ... M, q (t) indicate that rectangular pulse waveform, T indicate symbol period, fcIndicate carrier frequency, φ0Initial phase is indicated, if w
(t) it is the non-Gaussian noise for obeying S α S distributions, then its autocovariance function is defined as：
Wherein (x (t- τ))<p-1>=| x (t- τ) |p-2X* (t- τ), γx(t-τ)It is the coefficient of dispersion of x (t), then x (t) is followed
Ring co-variation is defined as：
Wherein ε is known as cycle frequency, and T is a code-element period；
The cycle co-variation spectrum for receiving signal is carried out as follows：
Cycle co-variation spectrum is to recycle the Fourier transformation of covariant function, is expressed as：
It recycles co-variation spectrum and is derived as：
As M >=4,Place,
As M=2,
Wherein Q (f) is the Fourier transformation of q (t), and
Carrier frequency estimation is realized in the section that cycle frequency ε=0Hz in co-variation spectrum is recycled by extraction, is carried out as follows：
The envelope of the cycle co-variation spectrum on n=0, that is, ε=sections 0Hz be：
As f=± fcWhen, envelope obtains maximum value.
Music score recognition method described in the embodiment of the present invention includes：
Step 1, music score to be identified are inputted by image input module 1；
The music score of step 2, input is pre-processed by image pre-processing module 2；
Step 3 generates low-rank image module 3 and difference image module 4 by pretreated music score；
Step 4, the low-rank image module 3 and difference image module 4 of generation enter spectral line generation module 5；
The spectral line of step 5, generation enters the deletion that spectral line removing module 6 carries out spectral line；
Step 6, the music score for deleting spectral line generate note image module 7；
Step 7, the note image module 7 of generation enter note comparison identification module 8 and carry out comparison identification；
Step 8, the note that comparison identification is completed enter note output module 9 and carry out last music score output.
The present invention is realized separates note from spectral line, most effective to overcome existing most of optics music score knowledges
Existing technology barrier is detached for middle note in other system, considerably increases the efficiency of music score identification, being very suitable for promoting makes
With.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Every any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (5)
1. a kind of music score recognition method, which is characterized in that the music score recognition method includes：
Music score to be identified is inputted by image input module；The music score of input is located in advance by image pre-processing module
Reason；
Low-rank image module and difference image module are generated by pretreated music score；The low-rank image module and difference generated
Image module enters spectral line generation module；
The spectral line generated enters the deletion that spectral line removing module carries out spectral line；The music score of deleted spectral line generates note image
Module；The note image module generated enters note comparison identification module and carries out comparison identification；
It compares and identifies that the note completed enters note output module and carries out last music score output.
2. music score recognition method as described in claim 1, which is characterized in that using staff spectral line detection and delet method come
It carries out, the musical score image of input is converted into musical score image matrix D, matrix D is decomposed into low-rank matrix A and sparse matrix E two
The sum of a matrix, i.e. D=A+E, the object function of solving-optimizing problem：
It indicates：When the order that constraints is A is less than r and D=A+E so that the F- Norm minimums of E；
The object function of this optimization problem is carried out to be relaxed to following convex optimization problem：
Meaning be in constraints be D=A+E so that the nuclear norm of A is minimum, and 1 norm of E is penalty term, wherein nuclear norm is
The sum of singular values of a matrix, 1 norm are the sum of absolute values, and D ∈ Rm × n, A ∈ Rm × n, E ∈ Rm × n, Rmxn indicate m rows n row
Real number matrix, λ indicate Lagrange multiplier vector, | | | | F indicates F- norms, | | | | * indicates nuclear norm, | | | | 1 table
Show 1- norms, | | | | 2 indicate 2- norms, | | | | ∞ indicates Infinite Norm；
Above-mentioned optimization problem is solved using augmented vector approach, constructs Augmented Lagrangian Functions：
Iterative formula is：
A indicate low-rank matrix, E indicate sparse matrix, Y indicate Lagrange multiplier initial value be Y0=D/max (| | Y | | 2, λ -1
| | Y | | ∞), μ indicates that penalty factor initial value is that k indicates that iterations initial value is 0；
The low-rank matrix A of input matrix D is obtained, spectral line information is obtained；
Spectral line is solved to be expert at and thereon or the difference image modular matrix C that has differences of next line：
C=H*D；
Wherein, C ∈ Rm × n, H ∈ Rn × n are：
C indicates that difference image modular matrix belongs to the real number matrix of m rows n row, and H indicates that high-pass filtering matrix belongs to the reality of n rows n row
Matrix number；
Obtained difference image modular matrix, then by carrying out AND operation with low-rank image module matrix after, obtained figure
Picture matrix carries out nonequivalence operation with original image matrix again, obtains as a result, formula is as follows：
S=C | | A；
B=S xor D；
B is required sign matrix.
3. a kind of music score identifying system of music score recognition method as described in claim 1, which is characterized in that music score identification system
System includes：Image input module, image pre-processing module, low-rank image module, difference image module, spectral line generation module, spectrum
Line removing module, note image module, note comparison identification module, note output module are simultaneously sequentially connected.
4. music score identifying system as claimed in claim 3, which is characterized in that the image detecting method of the low-rank image module
Including：Extract the color characteristic and adaptive LBP operator feature of the image of image pre-processing module processing；
Multiple features low-rank matrix indicates model；
s.t.xi=XiAi+Ei, i=L ..., K
Wherein α is greater than 0 coefficient,For measuring the error that noise and wild point are brought；
It is equivalent to drag：
Extraction adaptive LBP operator characteristics algorithm is as follows：
(1) image of input system is converted into gray level image, summed to image { grayv (i, j) } grey scale pixel value, then obtain
Average value：
(2) background is removed using total textural characteristics, calculates the grey scale pixel value of image and the difference of mean pixel gray value
The sum of absolute value is averaged：
Background is removed using Local textural feature, with the sliding window of 3 × 3 sizes, image is traversed, seeks center pixel gray value
And the difference of neighboring pixel gray value, the averaged in each video in window：
(3) according to experimental data, the method for the Fitting Calculation adaptive threshold：
5. music score identifying system as claimed in claim 3, which is characterized in that note compares identification module and compares identification to note
The estimation of exact value is carried out afterwards；It specifically includes：To the PSK letters containing Alpha Stable distritation noises of note image module transfer
Number seek cycle covariant function；
Fourier transformation is carried out to the cycle covariant function, it is asked to recycle co-variation spectrum；
Pass through the section of the cycle co-variation spectrum extraction cycle frequency ε=0Hz；
The peak value for searching for the positive and negative semiaxis in the section finds the corresponding positive negative frequency value of the peak value, and is asked after taking absolute value
Estimated value of the mean value as carrier frequency；
It is described receive signal cycle covariant function include：
The signal contains the mpsk signal for obeying S α S partition noises, can be expressed as：
Wherein E is the mean power of signal,M=2k, m=1,2,
... M, q (t) indicate that rectangular pulse waveform, T indicate symbol period, fcIndicate carrier frequency, φ0Initial phase is indicated, if w (t)
It is the non-Gaussian noise for obeying S α S distributions, then its autocovariance function is defined as：
Wherein (x (t- τ))＜ p-1>=| x (t- τ)p-2X* (t- τ), γx(t-τ)The coefficient of dispersion of x (t), then the cycle co-variation of x (t)
It is defined as：
Wherein ε is known as cycle frequency, and T is a code-element period；
The cycle co-variation spectrum for receiving signal is carried out as follows：
Cycle co-variation spectrum is to recycle the Fourier transformation of covariant function, is expressed as：
It recycles co-variation spectrum and is derived as：
As M >=4,Place,
As M=2,
Wherein Q (f) is the Fourier transformation of q (t), and
Carrier frequency estimation is realized in the section that cycle frequency ε=0Hz in co-variation spectrum is recycled by extraction, is carried out as follows：
The envelope of the cycle co-variation spectrum on n=0, that is, ε=sections 0Hz be：
As f=± fcWhen, envelope obtains maximum value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810193256.7A CN108416359A (en) | 2018-03-09 | 2018-03-09 | A kind of music score identifying system and recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810193256.7A CN108416359A (en) | 2018-03-09 | 2018-03-09 | A kind of music score identifying system and recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108416359A true CN108416359A (en) | 2018-08-17 |
Family
ID=63130748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810193256.7A Pending CN108416359A (en) | 2018-03-09 | 2018-03-09 | A kind of music score identifying system and recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108416359A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737589A (en) * | 2020-08-25 | 2020-10-02 | 北京圈清文化传媒有限公司 | Artificial intelligence based recommendation method, device and system |
| CN112926603A (en) * | 2021-03-26 | 2021-06-08 | 平安科技（深圳）有限公司 | Music score recognition method, device, equipment and storage medium |
| CN113076967A (en) * | 2020-12-08 | 2021-07-06 | 无锡乐骐科技有限公司 | Image and audio-based music score dual-recognition system |
| CN114419634A (en) * | 2022-03-28 | 2022-04-29 | 之江实验室 | Feature rule-based music score analysis method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012167616A1 (en) * | 2011-06-09 | 2012-12-13 | The Hong Kong University Of Science And Technology | Image based tracking |
| CN103810474A (en) * | 2014-02-14 | 2014-05-21 | 西安电子科技大学 | Car plate detection method based on multiple feature and low rank matrix representation |
| CN104038454A (en) * | 2014-06-20 | 2014-09-10 | 西安电子科技大学 | Method for estimating carrier frequency of PSK (phase shift keying) signal in Alpha-stable distribution noise |
| CN106203465A (en) * | 2016-06-24 | 2016-12-07 | 百度在线网络技术（北京）有限公司 | A kind of method and device generating the music score of Chinese operas based on image recognition |
| CN106548168A (en) * | 2016-10-25 | 2017-03-29 | 天津大学 | A kind of detection of staff spectral line and delet method based on low-rank structure |
-
2018
- 2018-03-09 CN CN201810193256.7A patent/CN108416359A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012167616A1 (en) * | 2011-06-09 | 2012-12-13 | The Hong Kong University Of Science And Technology | Image based tracking |
| CN103810474A (en) * | 2014-02-14 | 2014-05-21 | 西安电子科技大学 | Car plate detection method based on multiple feature and low rank matrix representation |
| CN104038454A (en) * | 2014-06-20 | 2014-09-10 | 西安电子科技大学 | Method for estimating carrier frequency of PSK (phase shift keying) signal in Alpha-stable distribution noise |
| CN106203465A (en) * | 2016-06-24 | 2016-12-07 | 百度在线网络技术（北京）有限公司 | A kind of method and device generating the music score of Chinese operas based on image recognition |
| CN106548168A (en) * | 2016-10-25 | 2017-03-29 | 天津大学 | A kind of detection of staff spectral line and delet method based on low-rank structure |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737589A (en) * | 2020-08-25 | 2020-10-02 | 北京圈清文化传媒有限公司 | Artificial intelligence based recommendation method, device and system |
| CN113076967A (en) * | 2020-12-08 | 2021-07-06 | 无锡乐骐科技有限公司 | Image and audio-based music score dual-recognition system |
| CN112926603A (en) * | 2021-03-26 | 2021-06-08 | 平安科技（深圳）有限公司 | Music score recognition method, device, equipment and storage medium |
| CN112926603B (en) * | 2021-03-26 | 2024-01-23 | 平安科技（深圳）有限公司 | Music score recognition method, device, equipment and storage medium |
| CN114419634A (en) * | 2022-03-28 | 2022-04-29 | 之江实验室 | Feature rule-based music score analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tong et al. | Channel-attention-based DenseNet network for remote sensing image scene classification | |
| CN108416359A (en) | A kind of music score identifying system and recognition methods | |
| Li et al. | Adversarial examples for CNN-based SAR image classification: An experience study | |
| CN114564982B (en) | Automatic identification method for radar signal modulation type | |
| CN108304357A (en) | A kind of Chinese word library automatic generation method based on font manifold | |
| CN105760821A (en) | Classification and aggregation sparse representation face identification method based on nuclear space | |
| CN109635726B (en) | Landslide identification method based on combination of symmetric deep network and multi-scale pooling | |
| CN103440505A (en) | Spatial neighborhood information weighted hyper-spectral remote sensing image classification method | |
| CN103886342A (en) | Hyperspectral image classification method based on spectrums and neighbourhood information dictionary learning | |
| Zhou et al. | Breast cancer classification from histopathological images using resolution adaptive network | |
| CN109902662A (en) | A kind of pedestrian recognition methods, system, device and storage medium again | |
| CN115659254A (en) | Power quality disturbance analysis method for power distribution network with bimodal feature fusion | |
| Li et al. | An object-oriented CNN model based on improved superpixel segmentation for high-resolution remote sensing image classification | |
| Yuan et al. | Few-shot scene classification with multi-attention deepemd network in remote sensing | |
| CN111639697A (en) | Hyperspectral image classification method based on non-repeated sampling and prototype network | |
| CN114897023A (en) | Underwater sound target identification method based on underwater sound target sensitivity difference feature extraction | |
| Lijun et al. | Geo‐information mapping improves Canny edge detection method | |
| CN117115675A (en) | Cross-time-phase light-weight spatial spectrum feature fusion hyperspectral change detection method, system, equipment and medium | |
| Zhou et al. | Ship target detection in optical remote sensing images based on multiscale feature enhancement | |
| Zhang et al. | Remote sensing image retrieval based on DenseNet model and CBAM | |
| CN115329821A (en) | Ship noise identification method based on pairing coding network and comparison learning | |
| CN116087880A (en) | Radar radiation source signal sorting system based on deep learning | |
| CN113343924B (en) | Modulation signal identification method based on cyclic spectrum characteristics and generation countermeasure network | |
| Chen et al. | Edge Detection and Deep Learning Based SETI Signal Classification Method | |
| Mei et al. | De-crossdet: Divisible and extensible crossline representation for object detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180817 |
|
| RJ01 | Rejection of invention patent application after publication |