Super-resolution in Music Score Images by Instance Normalization

• 발행기관: 한국스마트미디어학회
• 저자명: Minh-Trieu Tran Guee-Sang Lee
• 간행물 정보: 『스마트미디어저널』Vol8, No.4, 64~71쪽, 전체 8쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2019.12.30

영문 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.

목차

I. INTRODUCTION

II. INSTANCE NORMALIZATION

III. PROPOSED METHOD

IV. EXPERIMENTAL RESULTS

V. CONCLUSION

키워드

music score images super-resolution residual blocks