Abstract
With the rapid increase of consumer photos, annotating and retrieving such images with text are becoming more significant, which requires optical character recognition (OCR) techniques. However, to predict OCR accuracy, text-related image quality assessment (TIQA) is necessary and of great value, especially in online business processes. With more interests in text, TIQA aims to compute the quality score of an image through predicting the degree of degradation at textual regions.
To assess text-related quality on detected textlines, this paper proposes a deep neural network, TextNet, which mainly includes three layers: encoder, decoder, and prediction. The decoder layer combines the encoded feature map with the decoded map through deconvolution and concatenation. The prediction layer is designed for textline detection and quality assessment with a new loss function. Under the TIQA framework, the overall text-related image quality is computed through pooling the quality of all detected textlines by way of weighted averaging. Experimental results show that the proposed framework can work well in jointly assessing text related image quality and detecting textlines, even for unknown scene images.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
BRISQUE software release. http://live.ece.utexas.edu/research/quality/BRISQUE_release.zip
Buta, M., Neumann, L., Matas, J.: FASText: efficient unconstrained scene text detector. In: IEEE International Conference on Computer Vision, pp. 1206–1214 (2015)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.F.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248–255 (2009)
Kang, L., Ye, P., Li, Y., Doermann, D.: A deep learning approach to document image quality assessment. In: IEEE International Conference on Image Processing, pp. 2570–2574 (2014)
Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: International Conference on Document Analysis and Recognition, pp. 1156–1160 (2015)
Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: International Conference on Document Analysis and Recognition, pp. 1484–1493 (2013)
Kim, K.H., Hong, S., Roh, B., Cheon, Y., Park, M.: PVANET: deep but lightweight neural networks for real-time object detection (2016)
Kumar, J., Chen, F., Doermann, D.: Sharpness estimation for document and scene images. In: International Conference on Pattern Recognition, pp. 3292–3295 (2013)
Li, H., Zhu, F., Qiu, J.: CG-DIQA: no-reference document image quality assessment based on character gradient (2018). https://arxiv.org/abs/1807.04047
Nayef, N.: Metric-based no-reference quality assessment of heterogeneous document images. In: SPIE Electronic Imaging, p. 94020L-12 (2015)
Nayef, N., Luqman, M.M., Prum, S., Eskenazi, S., Chazalon, J., Ogier, J.M.: SmartDoc-QA: a dataset for quality assessment of smartphone captured document images - single and multiple distortions. In: International Conference on Document Analysis and Recognition, pp. 1231–1235 (2015)
Peng, X., Cao, H., Natarajan, P.: Document image quality assessment using discriminative sparse representation. In: Document Analysis Systems, pp. 227–232 (2016)
Rusinol, M., Chazalon, J., Ogier, J.M.: Combining focus measure operators to predict OCR accuracy in mobile-captured document images. In: IAPR International Workshop on Document Analysis Systems, pp. 181–185 (2014)
Shi, B., Yao, C., Liao, M., Yang, M., Xu, P., Cui, L., Belongie, S., Lu, S., Bai, X.: ICDAR 2017 competition on reading Chinese text in the wild (RCTW-17). In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 1429–1434 (2017)
Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Cardoso, M.J.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations (2017)
Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: European Conference on Computer Vision, pp. 56–72 (2016)
Xu, J., Ye, P., Li, Q., Liu, Y., Doermann, D.: No-reference document image quality assessment based on high order image statistics. In: IEEE International Conference on Image Processing, pp. 3289–3293 (2016)
Ye, P., Doermann, D.: Document image quality assessment: a brief survey. In: International Conference on Document Analysis and Recognition, pp. 723–727 (2013)
Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480–1500 (2015)
Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks, pp. 4159–4167 (2016)
Zhou, X., et al.: EAST: an efficient and accurate scene text detector. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 2642–2651 (2017)
Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comput. Sci. 10(1), 19–36 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, H., Qiu, J., Zhu, F. (2018). TextNet for Text-Related Image Quality Assessment. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11140. Springer, Cham. https://doi.org/10.1007/978-3-030-01421-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-01421-6_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01420-9
Online ISBN: 978-3-030-01421-6
eBook Packages: Computer ScienceComputer Science (R0)