Super-resolution in Music Score Images by Instance Normalization
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
The performance of an OMR (Optical Music Recognition) system is usually determined by the characterizing features of the input music score images. Low resolution is one of the main factors leading to degraded image quality. In this paper, we handle the low-resolution problem using the super-resolution technique. We propose the use of a deep neural network with instance normalization to improve the quality of music score images. We apply instance normalization which has proven to be beneficial in single image enhancement. It works better than batch normalization, which shows the effectiveness of shifting the mean and variance of deep features at the instance level. The proposed method provides an end-to-end mapping technique between the high and low-resolution images respectively. New images are then created, in which the resolution is four times higher than the resolution of the original images. Our model has been evaluated with the dataset “DeepScores” and shows that it outperforms other existing methods.
Abstract
The performance of an OMR (Optical Music Recognition) system is usually determined by the characterizing features of the input music score images. Low resolution is one of the main factors leading to degraded image quality. In this paper, we handle the low-resolution problem using the super-resolution technique. We propose the use of a deep neural network with instance normalization to improve the quality of music score images. We apply instance normalization which has proven to be beneficial in single image enhancement. It works better than batch normalization, which shows the effectiveness of shifting the mean and variance of deep features at the instance level. The proposed method provides an end-to-end mapping technique between the high and low-resolution images respectively. New images are then created, in which the resolution is four times higher than the resolution of the original images. Our model has been evaluated with the dataset “DeepScores” and shows that it outperforms other existing methods.
참고문헌 (31)
- Nasrollahi, "Super-resolution:A comprehensive survey", Machine Vision and Applications, 25, pp.1423~1468 (2014)
- Yang, "Single-image super-resolution: A benchmark", European Conference on Computer Vision (ECCV), 4, pp.372~386 (2014)
- Borman, "Super-Resolution from Image Sequences - A Review", Midwest Symposium on Circuits and Systems, pp.374~378 (1998)
- Farsiu, "Fast and robust multiframe super-resolution", IEEE Transactions on Image Processing, 13, pp.1327~1344 (2004)
- Ankit Lat, "Enhancing OCR Accuracy With Super Resolution", International Conference on Pattern Recognition (ICPR), pp.3162~3167 (2018)
- S. Baker, "Limits on super-resolution and how to break them", IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, pp.1167~1183 (2002)
- Lim, "Enhanced Deep Residual Networks for Single Image Super-Resolution", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp.1132~1140 (2017)
- Lukas Tuggener, "DeepScores - a dataset for segmentation, detection and classification of tiny objects", International Conference on Pattern Recognition, pp.3704~3709 (2018)
- Y.-W. Tai, "Super-resolution using Edge Prior and Single Image Detail Synthesis", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2400~2407 (2010)
- J. Sun, "Image super-resolution using gradient profile prior", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2008)
- K. Zhang, "Multi-scale dictionary for single image super-resolution", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1114~1121 (2012)
- H. Yue, "Landmark image super-resolution by retrieving web images", IEEE Transactions on Image Processing, 22, pp.4865~4878 (2013)
- K. Gregor, "Learning fast approximations of sparse coding", Proceedings of the 27th International Conference on Machine Learning, pp.399~406 (2010)
- C. Dong, "Learning a deep convolutional network for image super-resolution", European Conference on Computer Vision, 8692, pp.184~199 (2014)
- C. Dong, "Image super-resolution using deep convolutional networks", IEEE Transactions on Pattern Analysis and Machine Intelligence, 38, pp.295~307 (2016)
- C. E. Duchon, "Filtering in One and Two Dimensions", Journal of Applied Meteorology, 18, pp.1016~1022 (1979)
- Christian Ledig, "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network", Conference on Computer Vision and Pattern Recognition (CVPR), pp.105~114 (2017)
- Zheng Xu, "Strong Baseline for Single Image Dehazing with Deep Features and Instance Normalization", 29th British Machine Vision Conference (2018)
- Zhou Wang, "Image Quality Assessment: From Error Visibility To Structural Similarity", IEEE Transactions on Image Processing, 13, pp.600~612 (2004)
- D. Kingma, "Adam: A method for stochastic optimization", International Conference on Learning Representations (ICLR) (2014)
- J. Kim, "Accurate image superresolution using very deep convolutional networks", Conference on Computer Vision and Pattern Recognition (CVPR), pp.1646~1654 (2016)
- J. Kim, "Deeply-recursive convolutional network for image super-resolution", Conference on Computer Vision and Pattern Recognition (CVPR), pp.1637~1645 (2016)
- Dmitry Ulyanov, "Instance Normalization: The Missing Ingredient for Fast Stylization", ~ (2017)
- Sergey Ioffe, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift", Proc. of the 32nd International Conference on Machine Learning, 37, pp.448~456 (2015)
- Yuxin Wu, "Group Normalization", International Journal of Computer Vision, pp.1~14 (2018)
- Wenzhe Shi, "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network", Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
- QuangNhat Vo, "Recognition of Music Scores with Non-Linear Distortions in Mobile Devices", Multimedia Tools and Applications, 77, pp.15951~15969 (2018)
- Jorge Calvo-Zaragoza, "End-to-End Optical Music Recognition Using Neural Networks", Proc, of the 18th International Society for Music Information Retrieval Conference (ISMIR), pp.472~477 (2017)
- Luu Ngoc Do, "A Covariance-matching-based Model for Musical Symbol Recognition", 스마트미디어저널, 7(2), pp.23~33 (2018), (사)한국스마트미디어학회[DOI]
- Son Tung Trieu, "Machine Printed and Handwritten Text Discrimination in Korean Document Images", 스마트미디어저널, 5(3), pp.30~34 (2016), (사)한국스마트미디어학회
- Van Khien Pham, "Text Detection based on Edge Enhanced Contrast Extremal Region and Tensor Voting in Natural Scene Images", 스마트미디어저널, 6(4), pp.32~40 (2017), (사)한국스마트미디어학회