An MRF model for binarization of music scores with complex background

Vo, Quang Nhat; Kim, Sung Hyun; Yang, Hyung Jeong; Lee, Guee-Sang

doi:10.1016/j.patrec.2015.10.017

Cited by 23 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, BLIST method [16] consists of an adaptive local thresholding algorithm based on the estimation of features of staff lines in the score. In the work of Vo et al [17], a Markov Random Field is used to binarize the documents from a foreground modeling based on the color of the staff lines. However, the main problem found in these options is the varying performance depending on the characteristics of the document [18,19].…”

Section: Introductionmentioning

confidence: 99%

“…Although this favors a global view of the document, it is more complex to perform a fine-grained segmentation such as that necessary to detect the elements of musical documents. Energy-based algorithms such as Markov Random Fields or Graph Cuts have also been widely considered for image segmentation tasks [17,37]. However, they require greater prior knowledge of the application context, given that an appropriate energy function has to be established.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Neural Networks for Document Processing of Music Score Images

et al. 2018

View full text Add to dashboard Cite

There is an increasing interest in the automatic digitization of medieval music documents. Despite efforts in this field, the detection of the different layers of information on these documents still poses difficulties. The use of Deep Neural Networks techniques has reported outstanding results in many areas related to computer vision. Consequently, in this paper, we study the so-called Convolutional Neural Networks (CNN) for performing the automatic document processing of music score images. This process is focused on layering the image into its constituent parts (namely, background, staff lines, music notes, and text) by training a classifier with examples of these parts. A comprehensive experimentation in terms of the configuration of the networks was carried out, which illustrates interesting results as regards to both the efficiency and effectiveness of these models. In addition, a cross-manuscript adaptation experiment was presented in which the networks are evaluated on a different manuscript from the one they were trained. The results suggest that the CNN is capable of adapting its knowledge, and so starting from a pre-trained CNN reduces (or eliminates) the need for new labeled data.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Neural Networks for Document Processing of Music Score Images

et al. 2018

View full text Add to dashboard Cite

show abstract

“…It depends on a stability heuristic criterion to choose suitable parameter values for individual images. Another binarization method [17] for music score images that combines the Gaussian Mixture Model (GMM) and MRF model is proposed. This method tries to extract the foreground information by modeling the color distribution of detected the staff lines.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, a pre-trained residual network was chosen for the backbone structure because it helps model having generalization capability. Different from our previous work [17], we do not need some post and pre-processing steps such as the staff line detection, and our proposed network structure can work on grayscale images while delivers better results. On the other hand, the proposed model can distinguish the foreground and background pixels with similar color values which is the weak point of previous work.…”

Section: Introductionmentioning

confidence: 96%

“…Howe [6] employs a parameter-turning strategy for the selection of suitable parameter values for each image sample. A Gaussian Mixture Markov Random Field (GMMRF) model [17] was proposed for the binarization of music score images that uses the detected staff lines and background seeds to construct the color distribution of foreground and background. However, this method is difficult in binary images with background similar to the staff line or music symbol.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Binarization of music score with complex background by deep convolutional neural networks

Tran

Lee

2021

Multimed Tools Appl

View full text Add to dashboard Cite

Binarization is an important step for most of document analysis systems. Regarding music score images with a complex background, the existence of background clutters with a variety of shapes and colors creates many challenges for the binarization. This paper presents a model for binarization of the complex background music score images by fusion of deep convolutional neural networks. Our model is directly trained from image regions using pixel values as inputs and the binary ground truth as labels. By utilizing the generalization capability of the residual network backbone and useful feature learning ability of dense layer, the proposed network structures can differentiate foreground pixels from background clutters, minimize the possibility of overfitting phenomenon and thus can deal with complex background noises appearing in the music score images. Comparing to traditional algorithms, binary images generated by our method have a cleaner background and better-preserved strokes. The experiments with captured and synthetic music score images show promising results compared to existing methods.

show abstract

Research on image segmentation methods based on optimization theory

Lihua

2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

An MRF model for binarization of music scores with complex background

Cited by 23 publications

References 9 publications

Deep Neural Networks for Document Processing of Music Score Images

Deep Neural Networks for Document Processing of Music Score Images

Binarization of music score with complex background by deep convolutional neural networks

Research on image segmentation methods based on optimization theory

Contact Info

Product

Resources

About