See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/221050952

Staff Line Detection and Removal with Stable Paths.

Conference Paper · January 2008

Source: DBLP

CITATIONS

11READS

851

4 authors:

Some of the authors of this publication are also working on these related projects:

Interactive Dance View project

Cervical cancer screening View project

Artur Capela

Institute for Systems and Computer Engineering, Technology and Science (INESC …

6 PUBLICATIONS   147 CITATIONS   

SEE PROFILE

Ana Rebelo

Institute for Systems and Computer Engineering, Technology and Science (INESC …

40 PUBLICATIONS   733 CITATIONS   

SEE PROFILE

Jaime S. Cardoso

University of Porto

322 PUBLICATIONS   5,096 CITATIONS   

SEE PROFILE

Carlos Guedes

New York University Abu Dhabi

60 PUBLICATIONS   658 CITATIONS   

SEE PROFILE

All content following this page was uploaded by Carlos Guedes on 15 May 2014.

The user has requested enhancement of the downloaded file.

STAFF LINE DETECTION AND REMOVAL WITH STABLE PATHS

Artur Capela, Ana RebeloINESC Porto, Campus da FEUP, Rua Dr. Roberto Frias 378, 4200-465 Porto, Portugal

gcapela@inescporto.pt, arebelo@inescporto.pt

Jaime S. CardosoINESC Porto, Faculdade de Engenharia, Universidade do Porto, Portugal

jaime.cardoso@inescporto.pt

Carlos GuedesINESC Porto, Escola Superior de Musica e Artes do Espectaculo, Portugal

carlosguedes@mac.com

Keywords: Music, optical character recognition, document image processing, image analysis.

Abstract: Many music works produced in the past are currently available only as original manuscripts or as photocopies.Preserving them entails their digitalization and consequent accessibility in a machine-readable format, whichencourages browsing, retrieval, search and analysis while providing a generalized access to the digital material.Carrying this task manually is very time consuming and error prone. While optical music recognition (OMR)systems usually perform well on printed scores, the processing of handwritten music by computers remainsbelow the expectations. One of the fundamental stages to carry out this task is the detection and subsequentremoval of staff lines. In this paper we integrate a general-purpose, knowledge-free method for the automaticdetection of staff lines based on stable paths, into a recently developed staff line removal toolkit. Linesaffected by curvature, discontinuities, and inclination are robustly detected. We have also developed a staffremoval algorithm adapting an existing line removal approach to use the stable path algorithm at the detectionstage. Experimental results show that the proposed technique outperforms well-established algorithms. Thedeveloped algorithm will now be integrated in a web based system providing seamless access to browsing,retrieval, search and analysis of submitted scores.

1 INTRODUCTION

The Universal Declaration on Cultural Diversityadopted by the General Conference of UNESCO on2001 asserts that cultural diversity is as necessary forhumankind as biodiversity is for nature, and that poli-cies to promote and protect cultural diversity thus arean integral part of sustainable development. Beingmusic a pivotal part of our cultural heritage, its preser-vation, in all of its forms, must be pursued. Fre-quently, the preservation of many music works en-tails their digitalization and consequent accessibilityin a format that encourages browsing, analysis and re-trieval.

There is a vast amount of invaluable paper-basedheritage, including printed and handwritten musicscores, which are deteriorating over time due to natu-ral decaying of paper and chemical reaction (i.e., be-tween written ink and paper). Various efforts havebeen focused on this issue in order to preserve the

record of our heritage. Digitisation has been com-monly used as a possible tool for preservation. Al-though a digital copy may not conserve the originaldocument, it can preserve the most important part:its data. It has also the advantages of easy dupli-cations, distribution, and digital processing. Never-theless, the output of the digitalization process is notamenable for further analysis or semantic search op-erations. Thus, an Optical Music Recognition (OMR)process is needed. However, the manual process re-quired to recognize handwritten musical symbols inscores and to put them in relationship with the spinestructure of the score is very time consuming. Thisjustifies the research around reliable automatic OMRalgorithms as current solutions are still below the ex-pectations.

As a concrete example, Portugal has a notoriouslack in music publishing from virtually all eras ofits musical history. However, whereas most of theknown original music manuscripts before the twen-

263

tieth century are kept at the National Library Archivein Lisbon, there is virtually no national repository forthe Portuguese music from the twentieth century. Al-though there are recent efforts in order to catalogueand preserve in digital form the Portuguese musicfrom the late twentieth century—notably the MusicInformation Center (MIC, 2008) and the section onmusical heritage from the Institute of the Arts web-site (IOA, 2008)—most of the music pre-dating com-puter notation software was never published and stillexists as manuscripts or photocopies spread out allover the country in inconspicuous places. The riskof irreversibly losing this rich cultural heritage is thusa reality.

1.1 OMR System

The project “Optical recognition system for handwrit-ten music scores” initiated in 2007 by INESC Portoand ESMAE is the point of departure for creatinga web-based system of music manuscripts of Por-tuguese composers from the twentieth century. Thisdatabase will provide generalized access to a widecorpus of unpublished handwritten music encoded inMusicXML, which can be accessed remotely via theInternet. The database will not only centralize asmuch information as possible but will also serve topreserve this corpus in a way that is easily accessi-ble for browsing, analysis, and ultimately, for per-forming this repertoire, therefore helping to keep thePortuguese music alive (Capela et al., 2008). Al-though the aim of this project is Portuguese music,it is equally valid for all printed and handwritten mu-sic scores that need to be preserved from all aroundthe world.

The ambitious goal of providing generalized ac-cess to handwritten scores that have never been pub-lished has been severely hampered by the actual state-of-the-art of handwritten music recognition. Thereare currently various commercial OMR software so-lutions (Capella software1, SharpEye Music Reader2,OMeR3) and a few open source solutions (AOMR24,OpenOMR5, Audiveris6), but they are all offline stan-dalone applications. The existing online archives ofmusic scores (Lester Levi Collection, 2008; Classical

1http://www.capella-software.com/capscan.htm

2http://www.visiv.co.uk3http://www.myriad-online.com/en/products/

omer.htm4http://www.bzzt.net/˜arnouten/wiki/index.

php/Gamera#AOMR2:_omr_toolkit5http://sourceforge.net/projects/openomr6http://audiveris.dev.java.net

Sheet Music Collection, 2008; Mutopia Collection,2008) usually provide them in inadequate formats—usually only as the scanned score image—for retrievalor automatic analysis. These online archives are merestandard websites, without facilities for optical recog-nition, editing and searching through the scores mu-sical content. The creation of an OMR system, in-tegrating optical recognition, storage, search, brows-ing and downloading capabilities, while keeping thescores in their original format along with their digitalcounterpart, would therefore be extremely beneficial.An integrated score editor would be provided in orderto view and edit the submitted music scores.

In our previous work on this project we havepresented a complete OMR System solution—OMRSYS (Capela et al., 2008)—comprising adatabase driven web application with one or moreOMR applications integrated in the proposed system.The proposed architecture successfully attends thestated objectives. At the end of our project we planon developing a fully functional system according tothe specified architecture and integrating a completeOMR package.

1.2 Detection and Removal of StaffLines

Staff line detection and removal are the first funda-mental stages on the OMR process, with subsequentprocesses relying heavily on their performance. Thereasons for detecting and removing the staff lines lieon the need to isolate the musical symbols for a moreefficient and correct detection of each symbol presenton the score. Although their primary application is asa preprocessing step in the recognition of music no-tation, the line detection problem also occurs in dif-ferent contexts (e.g., the recognition of bank transferforms).

The detection of staves is complicated due to avariety of reasons. The handwritten staff lines arerarely straight and horizontal, and are not parallel toeach other. For example, some staves may be tiltedone way or another on the same page or they may becurved. These scores tend to be rather irregular anddetermined by a person’s own writing style. More-over, if we consider that most of these works are old,the quality of the paper in which it is written mighthave degraded throughout the years, making it a lotharder to correctly identify its contents.

In (Cardoso et al., 2008a; Cardoso et al., 2008b)we presented a new and robust staff line detection al-gorithm based on a stable paths approach. The pro-posed paradigm uses the image as a graph, where thestaff lines result as connected paths between the two

SIGMAP 2008 - International Conference on Signal Processing and Multimedia Applications

264

lateral margins of the image. A staff line can be con-sidered as a connected path from the left side to theright side of the music score. As staff lines are almostthe only extensive black objects on the music score,the path to look for is the shortest path between thetwo margins if paths (almost) entirely through blackpixels are favoured.

In this paper we present our recent work and re-sults focusing on the implementation of the StablePaths algorithm as a C++ plugin for the MusicStavesToolkit (Dalitz et al., 2008; MusicStaves Toolkit,2008) (based on the Gamera Framework (MacMillanet al., 2002; Gamera Framework, 2008)), as well ason the removal stage by using our detection algorithmin the first stage. We have also adapted a removal al-gorithm based on the LineTrack Height approach pro-posed in (Dalitz et al., 2008), which we will present insection 3. In section 2 the Gamera and MusicStavesToolkit are presented, together with our C++ plugin.In section 4, both our proposed detection and removalalgorithms are evaluated experimentally using a well-known dataset of music scores. Finally, conclusionsare drawn and future work is outlined in section 5.

2 STABLE PATHS INTEGRATION

In this section we present the platform in which ourdetection algorithm was integrated for testing and val-idation. The platform is comprised by its core—theGamera Framework (MacMillan et al., 2002; GameraFramework, 2008)—and by a toolkit for the evalua-tion of detection and removal algorithms—the Mu-sicStaves Toolkit (Dalitz et al., 2008; MusicStavesToolkit, 2008). This toolkit is a set of Gamera plu-gins aiming to support the development and test ofstaff line detection and removal algorithms for musicscores, by extending the Gamera functionality.

After we describe each part constituting this plat-form, we present the implementation of our staff linedetection algorithm as a C++ plugin on the Music-Staves Toolkit. Finally, we present the integration ofour detection algorithm on some removal algorithmsin the MusicStaves toolkit. We have integrated ouralgorithm in those removal algorithms where the de-tection is processed separately from the removal op-eration, replacing the Dalitz algorithm (Dalitz et al.,2008) as the detection stage.

2.1 Gamera Framework

Gamera (MacMillan et al., 2002; Gamera Framework,2008) is a portable and open source framework to cre-ate structured documents analysis applications by do-

main experts. The name Gamera is an acronym to“Generalized Algorithms and Methods for Enhance-ment and Restoration of Archives”. It combines a pro-gramming library with graphical tools for an interac-tive training and development of recognition systems.This framework tries to be a tool to create custom ap-plications through the domain experts knowledge in-stead of responding to various requirements with amonolithic application. It aims at providing an ef-ficient test and refinement development cycle. Theprogramming language in its basis is the high-levellanguage Python, although it has many extensionswritten in C++ to carry out low-level image process-ing. Nevertheless, due to its nature, Python turns thecode writing process more agile and facilitates the useof scripting, which makes Gamera an interactive andbatchable framework. Besides the large number of ex-tensions deployed with this framework, it is also pos-sible to customize and extend with plugins or toolkits,written in Python and C++.

The Gamera framework is modular and organizedin a series of horizontal layers, which can be seen atFigure 1.

Figure 1: Gamera Architecture.

Gamera follows a modular plugin architecture. Itis made of modules (plugins), both written in Pythonand C++, integrated in a high-level scripting environ-ment. Each module executes a task on the recognitionprocess. The framework maintains a toolbox designapproach, i.e., a user has access to a large set of toolsfor the optical recognition stages.

2.2 MusicStaves Toolkit

MusicStaves (Dalitz et al., 2008; MusicStavesToolkit, 2008) is a Gamera toolkit specific for the de-velopment and test of staff line detection and removal

STAFF LINE DETECTION AND REMOVAL WITH STABLE PATHS

265

algorithms. This Phyton toolkit also integrates facili-ties to create a test set of music scores and to evaluateresults with established metrics. As with Gamera, thistoolkit is portable and its source code is freely avail-able. In order to use MusicStaves, it must be importedto Gamera, either in the GUI or in a programmaticmanner.

MusicStaves is structured as seen in Figure 2. Thetoolkit is composed by a set of main classes where thestaff line detection and removal algorithms are imple-mented, and by a set of plugins in Python and C++.Some plugins are used by the implemented algorithmswhile others are tools to aid the algorithms testing. Itis an extendable toolkit in which one can integrate anew staff line detection and/or removal algorithm. Itsplugin system follows the Gamera framework ratio-nale and as such the plugins may be written in Pythonand C++. In order to write new staff line detectionor removal algorithms the toolkit provides two inter-faces: StaffFinder (detection) and MusicStaves (re-moval).

Figure 2: MusicStaves Architecture.

A test set of 32 synthetic music scores is also pro-vided by the authors of this toolkit. Moreover, thetoolkit allows applying a set of deformations (e.g., ro-tation, curvature, typeset emulation, white speckles)commonly found in the real world to these perfectscores—see Figure 3. The purpose is to be able tomeasure the performance of the removal algorithmscontained in MusicStaves by using three defined er-ror metrics (Dalitz et al., 2008): Pixel Level, Seg-mentation Region Level and Staffline Interruptions.However, the same set may be used to evaluate staffline detection algorithms alone by defining adequateerror metrics (Cardoso et al., 2008a; Cardoso et al.,2008b). We have restricted the range of the param-eters controlling the intensity of the deformations tovalues considered realistic.

Figure 3: Some examples of applied deformations: a) Cur-vature; b) Rotation; c) White Speckles; d) Staffline Inter-ruptions; e) Staffline y-variation; f) Typeset Emulation. See(Dalitz et al., 2008) for details.

2.3 Integration

We have integrated our recently proposed algorithmfor staff line detection (Cardoso et al., 2008a; Car-doso et al., 2008b) in MusicStaves as a C++ plugin.The plugin encompasses the main StaffFinder class inthe toolkit root, the respective Python plugin in thePython plugins folder and the algorithm implementa-tion in C++ in the C++ plugins folder. In Figure 4we present a diagram of the algorithm as integrated inMusicStaves.

The algorithm processing starts with the call to themethod find staves, which receives a binarized imageas input. That image is then passed to the functionin C++ by the plugin Python code. In the C++ im-plementation, after the respective staff line detectionfunction is called, the image is converted to the formatused internally by our algorithm. After the whole de-tection task is complete it returns the staff lines skele-ton in the MusicStaves format. After receiving theskeleton list on its Python class, it fills the structureself.linelist with the obtained values.

Figure 4: Overall view.

Besides integrating our Stable Paths Approach al-gorithm into the MusicStaves toolkit as a C++ plu-gin, we have also integrated the algorithm with staff

SIGMAP 2008 - International Conference on Signal Processing and Multimedia Applications

266

removal algorithms in order to evaluate the improve-ments over the original results. However, this is nota standard integration as the toolkit does not providethe means for this kind of integration. This integra-tion was coded in the staff removal algorithms byadding the possibility to choose the staff line detec-tion algorithm through a parameter value. A diagramillustrating this integration can be seen in Figure 5.Some removal algorithms present in MusicStaves de-tect the staff lines along with the removal process.From those, we have used the one with best resultsin general (Dalitz et al., 2008)—Skeleton—for com-parison purposes.

Figure 5: Stable Paths integration with staff removal algo-rithms.

3 STAFF REMOVALALGORITHMS

In the process of recognizing music scores the staff re-moval algorithm is processed after the staff line detec-tion stage takes place. In our current work the removalalgorithm is based on the LineTrack Height algorithmpresented on (Randriamahefa et al., 1993). The goalon this method is to track the staff lines positions ob-tained by a detection algorithm and remove verticalrun sequences of black pixels that have a value lowerthan a specified threshold, which was experimentallyset at 2*staffHeight.

As music scores may suffer from deformations,the staff lines may have descontinuities, be curved orinclined. These problems will influence the successto achieve a correct detection of lines contained onthe score to recognize. However, due to the above-mentioned problems, the positions of the staff linesobtained by a staff line detection algorithm may passslightly above or under the real staff lines positions.That way, if we are in presence of a white pixelwhen the staff lines are tracked, we search verticallyfor the closest black pixel. If that distance is lowerthan a specified tolerance—experimentally chosen as1+ceil(staffHeight/3.0)—we move the reference posi-

tion of the staff line to the position of the black pixelfound.

Algorithm 1 : Staff Removal Algorithm.procedure STAFFLINEREMOVAL(IMAGE,STAV ES)threshold = 2∗staffHeight;

tolerance = 1+ ceil(staffHeight/3.0);IMAGE REMOV E = copy(IMAGE);for nvalid = 0 to STAVES size do

Point2D staff = validStaves[nvalid];for i = 0 to staff size do

col =staff[i].x;re f Row =staff[i].y;row = re f Row;pel = valuePixel(IMAGE, IMAGE REMOV E)decrement/increase the reference row until one

pixel different from white pixel (dist1/dist2) is found;if dist1≤ max(1,min(dist2, tolerance)) then

re f Row−= dist1;else

if dist2 ≤ max(1,min(dist1, tolerance))then

re f Row+ = dist2;else

continue;end if

end ifCount the number of decrements/increase on

the reference row until the black pixel changes to whitepixel (run);

if run≥ threshold thencontinue;

end ifremove the vertical black sequences on the IM-

AGE;end for

end forend procedure

On (Dalitz et al., 2008) a new method ispresented—Skeleton—which uses the skeleton infor-mation, but performs the staff removal on the originalimage instead of the skeleton. The method relies onthe fact that symbols on the stafflines lead to junctionpoints or corner points in the skeleton.

4 RESULTS

Although the evaluation of new staff detection algo-rithms may be done by visually inspecting the out-put on a set of scores—as adopted on (Rebelo et al.,2007)—, our current comparison is supported onquantitative measures. The test set adopted for thequalitative evaluation of the proposed method is theone presented in (Dalitz et al., 2008) and already de-scribed. It consists of ideal synthetic scores to whicha set of known deformations have been applied—see

STAFF LINE DETECTION AND REMOVAL WITH STABLE PATHS

267

(Dalitz et al., 2008) for more details. In total we havegenerated 2688 deformed images originated from 32perfect scores. In order to conveniently measure theperformance of staff line removal algorithms we haveadopted two error metrics from (Dalitz et al., 2008):Pixel Level and Segmentation Region Level.

Staff line detection algorithms can be used as afirst step in many staff removal algorithms. To un-derstand the potential of our algorithm to leveragethe performance of existing staff removal algorithms,we conducted a series of experiments, comparing theoriginal version of a staff removal algorithm with themodified version of it, making use of the Stable Pathsalgorithm at the staff line detection step. The quanti-tative comparison of the different algorithms is totallyin line with the comparison presented in (Dalitz et al.,2008).

With respect to the considered distortions, regard-ing the detection stage, the Stable Paths based ap-proach outperforms the Dalitz algorithm. In Figure 6we present our results for the removal algorithms:LineTrack Height (with Dalitz and Stable Paths),Skeleton and LineTrack Height Modified (with StablePaths). We chose the methods that present the best re-sults in (Dalitz et al., 2008), implementing our ownremoval algorithm with LineTrack Height as a basis.In general we verify that the replacement of the Dalitzmethod by our Stable Paths Approach algorithm asthe staff detection step has improved the final staffline removal results7. Additionally, the LineTrackingHeight Modified algorithm presents an overall betterperformance than the original LineTrack Height algo-rithm from (Dalitz et al., 2008). Our staff line de-tection and removal approaches also outperform theSkeleton method, although it continues to present acompetitive performance. We have not integrated theStable Paths algorithm with the Skeleton algorithmas the second performs the lines detection along withtheir removal instead of using two separate stages. Allthe parameters, both on the Stable Paths detection al-gorithm and LineTrack Height Modified, were pre-liminary tuned over an independent set of images.

This performance gain is even more noteworthy asthe MusicStaves algorithms are receiving as input thecorrect number of lines per staff. Had not this been thecase, the differential between both would have beenmuch larger. In summary, these experiments show thestrength of the algorithms presented here. Despite be-ing based on simple and intuitive underlying princi-ples, the performance of the proposed algorithms isquite competitive.

The analysed results have covered the detection

7For the deformations not shown, the stable path is notsignificantly better than Dalitz.

and removal accuracy but a brief word on speed is alsoin order. Comparing different algorithms for speedis notoriously difficult; we are simultaneously judg-ing mathematical properties and specific implementa-tions. In the experimental study, the current imple-mentation of the Stable Paths algorithm run almostas fast as the Dalitz algorithm (20% slower). In re-spect to the removal algorithms our LineTrack Heightversion with Stable Paths is significantly faster thanthe Skeleton algorithm (two times faster). Compar-ing to the original LineTrack Height algorithm withthe Dalitz detection algorithm the runtime differenceis not significant. The algorithms were evaluated asavailable at the Staff Removal Toolkit (Dalitz et al.,2008).

5 CONCLUSIONS

This paper presented the integration of our robust Sta-ble Paths Approach algorithm (Cardoso et al., 2008a;Cardoso et al., 2008b) in the MusicStaves Toolkit(Dalitz et al., 2008) as a C++ plugin, an improvedversion of an existing staff line removal algorithm—LineTrack Height (Dalitz et al., 2008), and the re-sults we have obtained in our staff line removal tests.We have integrated our detection algorithm with ex-isting staff line removal algorithms. Our approachsuccessfully deals with the difficulties posed by thesymbols superimposed on the staff lines as well as awide range of image conditions (e.g., discontinuities,curved lines), frequently found on handwritten scores.

The encouraging results lead us now to considerinvestigating the detection of music symbols bene-fiting from the improved staff line detection and re-moval, creating a complete OMR application in or-der to integrate it on our proposed complete OMRsolution—OMRSYS (Capela et al., 2008). Thus, ourproposed system offers a complete solution for thepreservation of our musical heritage. It includes anoptical recognition engine integrated with an archiv-ing system and a user-friendly interface for search-ing, browsing and edition. The digitized scores arestored in MusicXML, a recent and expanding musicinterchange format designed for notation, analysis, re-trieval, and performance applications.

Our proposed algorithms and complete OMR sys-tem promote the creation of a full corpus of mu-sic documents, promoting its preservation and study.This project will culminate in the creation of a repos-itory of handwritten scores, accessible online. Thedatabase will be available for enjoyment, educationaland musicological purposes, thus preserving this cor-pus of music in an unprecedented way.

SIGMAP 2008 - International Conference on Signal Processing and Multimedia Applications

268

(a) Curvature. (b) Curvature. (c) White Speckles.

(d) Rotation. (e) Staffline Y-Variation. (f) Staffline Y-Variation.

(g) Staffline Interruptions. (h) Typeset Emulation Part 1. (i) Typeset Emulation Part 2.

Figure 6: Effect of different deformations on the overall staff removal error rates. See (Dalitz et al., 2008) for parameterdetails.

ACKNOWLEDGEMENTS

This work was partially funded by Fundacao paraa Ciencia e a Tecnologia (FCT) - Portugal throughproject PTDC/EIA/71225/2006.

REFERENCES

Capela, A., Cardoso, J. S., Rebelo, A., and Guedes, C.(2008). Integrated recognition system for musicscores. In International Computer Music Conference(ICMC) (Accepted).

Cardoso, J. S., Capela, A., Rebelo, A., and Guedes, C.(2008a). A connected path approach for staff detec-tion on a music score. In International Conference onImage Processing (ICIP 2008) (Accepted).

Cardoso, J. S., Capela, A., Rebelo, A., and Guedes, C.(2008b). Staff detection with stable paths. Trans-actions on Pattern Analysis and Machine Intelligence(TPAMI) (Submitted).

Classical Sheet Music Collection (2008). Classical SheetMusic and MIDI Files, http://www.music-scores.com.

Dalitz, C., Droettboom, M., Pranzas, B., and Fujinaga, I.(2008). A comparative study of staff removal algo-rithms. IEEE Transactions on Pattern Analysis andMachine Intelligence, 30(5):753–766.

Gamera Framework (2008). Gamera Framework,http://ldp.library.jhu.edu/projects/gamera/.

IOA (2008). Institute of the Arts,http://patrimonio.dgartes.pt/?lang=pt.

Lester Levi Collection (2008). The LesterS. Levi Collection of Sheet Music,http://levysheetmusic.mse.jhu.edu/.

STAFF LINE DETECTION AND REMOVAL WITH STABLE PATHS

269

MacMillan, K., Droettboom, M., and Fujinaga, I. (2002).Gamera: Optical music recognition in a new shell. InInternational Computer Music Conference (ICMC),pages 482–485.

MIC (2008). Music Information Center, http://www.mic.pt.

MusicStaves Toolkit (2008). MusicStaves Toolkit,http://lionel.kr.hsnr.de/ dalitz/data/projekte/stafflines/.

Mutopia Collection (2008). The Mutopia Project,http://sca.uwaterloo.ca/Mutopia.

Randriamahefa, R., Cocquerez, J. P., Fluhr, C., Ppin, F., andPhilipp, S. (1993). Printed music recognition. In Pro-ceedings of the 2nd International Conference on Doc-ument Analysis and Recognition (ICDAR’93), pages898–901.

Rebelo, A., Capela, A., da Costa, J. F. P., Guedes, C., Carra-patoso, E., and Cardoso, J. S. (2007). A shortest pathapproach for staff line detection. In AXMEDIS ’07:Proceedings of the Third International Conference onAutomated Production of Cross Media Content forMulti-Channel Distribution, pages 79–85, Washing-ton, DC, USA. IEEE Computer Society.

SIGMAP 2008 - International Conference on Signal Processing and Multimedia Applications

270

View publication statsView publication stats