Abstract
Automatic localization of text-lines in handwritten documents is still an open and challenging research problem. Various writing issues such as uneven spacing between the lines, oscillating and touching text, and the presence of skew become much more challenging when the case of complex handwritten document images are considered for segmentation directly in their respective compressed representation. This is because, the conventional way of processing compressed documents is through decompression, but here in this paper, we propose an idea that employs deep feature learning directly from the JPEG compressed coefficients without full decompression to accomplish text-line localization in the JPEG compressed domain. A modified U-Net architecture known as Compressed Text-Line Localization Network (CompTLL-UNet) is designed to accomplish it. The model is trained and tested with JPEG compressed version of benchmark datasets including ICDAR2017 (cBAD) and ICDAR2019 (cBAD), reporting the state-of-the-art performance with reduced storage and computational costs in the JPEG compressed domain.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bisen, T., Javed, M., Kirtania, S., Naghabhushan, P.: DWT-COMPCNN: deep image classification network for high throughput jpeg 2000 compressed documents. In: Pattern Analysis and Applications (2023)
Renton, G., Soullard, Y., Chatelain, C., Adam, S., Kermorvant, C., Paquet, T.: Fully convolutional network with dilated convolutions for handwritten text line segmentation. IJDAR 21(3), 177–186 (2018)
Barakat, B., Droby, A., Kassis, M., El-Sana, J.: Text line segmentation for challenging handwritten document images using fully convolutional network. In: ICFHR, pp. 374–379 (2018)
Rajesh, B., Javed, M., Nagabhushan, P.: Automatic tracing and extraction of text-line and word segments directly in jpeg compressed document images. IET Image Process. (2020)
Mechi, O., Mehri, M., Ingold, R., Ben Amara, N.E.: Text line segmentation in historical document images using an adaptive u-net architecture. In: ICDAR, pp. 369–374 (2019)
Javed, M., Nagabhushan, P., Chaudhuri, B.B.: A review on document image analysis techniques directly in the compressed domain. Artif. Intell. Rev. 50(4), 539–568 (2018)
Mukhopadhyay, J.: Image and Video Processing in the Compressed Domain. Chapman and Hall/CRC (2011)
Bisen, T., Javed, M., Nagabhushan, P., Watanabe, O.: Segmentation-less extraction of text and non-text regions from jpeg 2000 compressed document images through partial and intelligent decompression. IEEE Access 11, 20673–20687 (2023)
Gueguen, L., Sergeev, A., Kadlec, B., Liu, R., Yosinski, J.: Faster neural networks straight from jpeg. In: ANIPS, pp. 3933–3944 (2018)
Ehrlich, M., Davis, L.S.: Deep residual learning in the jpeg transform domain. In: ICCV, pp. 3484–3493 (2019)
Rajesh, B., et al.: DCT-COMPCNN: a novel image classification network using jpeg compressed DCT coefficients. In: 2019 IEEE Conference on Information and Communication Technology, pp. 1–6. IEEE (2019)
Liu, J., Sun, H., Katto, J.: Semantic segmentation in learned compressed domain. In: 2022 Picture Coding Symposium (PCS), pp. 181–185. IEEE (2022)
Chen, L., Sun, H., Zeng, X., Fan, Y.: Learning from the NN-based compressed domain with deep feature reconstruction loss. In: 2022 IEEE International Conference on Visual Communications and Image Processing (VCIP), pp. 1–5 (2022)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Kiumarsi, E., Alaei, A.: A hybrid method for text line extraction in handwritten document images. In: ICFHR, pp. 241–246 (2018)
Ben Aïcha Gader, T., Kacem Echi, A.: Unconstrained handwritten Arabic text-lines segmentation based on ar2u-net. In: ICFHR, pp. 349–354 (2020)
Demır, A.A., ÖzŞeker, İ., Özkaya, U.: Text line segmentation in handwritten documents with generative adversarial networks. In: INISTA, pp. 1–5 (2021)
Amarnath, R., Nagabhushan, P.: Text line segmentation in compressed representation of handwritten document using tunneling algorithm. IJISAE 6(4), 251–261 (2018)
Zaman, B.R.M.: JPEG-Compression-Algorithm (2022). https://drive.google.com/drive/folders/1fv5wU0bFY0_2nUWyp4x_MtbCN4hFiMd2?usp=sharing. Accessed 10 Aug 2022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rajesh, B., Zaman, S.M., Javed, M., Nagabhushan, P. (2023). CompTLL-UNet: Compressed Domain Text-Line Localization in Challenging Handwritten Documents Using Deep Feature Learning from JPEG Coefficients. In: Lu, H., Blumenstein, M., Cho, SB., Liu, CL., Yagi, Y., Kamiya, T. (eds) Pattern Recognition. ACPR 2023. Lecture Notes in Computer Science, vol 14407. Springer, Cham. https://doi.org/10.1007/978-3-031-47637-2_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-47637-2_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47636-5
Online ISBN: 978-3-031-47637-2
eBook Packages: Computer ScienceComputer Science (R0)