Abstract
Handwritten documents are often characterized by dense and uneven layout. Despite advances, standard deep network based approaches for semantic layout segmentation are not robust to complex deformations seen across semantic regions. This phenomenon is especially pronounced for the low-resource Indic palm-leaf manuscript domain. To address the issue, we first introduce Indiscapes2, a new large-scale diverse dataset of Indic manuscripts with semantic layout annotations. Indiscapes2 contains documents from four different historical collections and is \(150\%\) larger than its predecessor, Indiscapes. We also propose a novel deep network Palmira for robust, deformation-aware instance segmentation of regions in handwritten manuscripts. We also report Hausdorff distance and its variants as a boundary-aware performance measure. Our experiments demonstrate that Palmira provides robust layouts, outperforms strong baseline approaches and ablative variants. We also include qualitative results on Arabic, South-East Asian and Hebrew historical manuscripts to showcase the generalization capability of Palmira.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agarwal, M., Mondal, A., Jawahar, C.: Cdec-net: Composite deformable cascade network for table detection in document images. In: ICPR (2020)
Alaasam, R., Kurar, B., El-Sana, J.: Layout analysis on challenging historical arabic manuscripts using siamese network. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 738–742. IEEE (2019)
Alberti, M., Vögtlin, L., Pondenkandath, V., Seuret, M., Ingold, R., Liwicki, M.: Labeling, cutting, grouping: an efficient text line segmentation method for medieval manuscripts. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1200–1206. IEEE (2019)
Barman, R., Ehrmann, M., Clematide, S., Oliveira, S.A., Kaplan, F.: Combining visual and textual features for semantic segmentation of historical newspapers. arXiv preprint arXiv:2002.06144 (2020)
Cheng, T., Wang, X., Huang, L., Liu, W.: Boundary-preserving mask R-CNN. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 660–676. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_39
Clausner, C., Antonacopoulos, A., Pletschacher, S.: Icdar 2019 competition on recognition of documents with complex layouts-rdcl2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1521–1526. IEEE (2019)
Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764–773 (2017)
Gao, J., Wang, Z., Xuan, J., Fidler, S.: Beyond fixed grid: learning geometric image representation with a deformable grid. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 108–125. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_7
Gupta, A., Dollár, P., Girshick, R.B.: LVIS: A dataset for large vocabulary instance segmentation. CoRR abs/1908.03195 (2019). http://arxiv.org/abs/1908.03195
He, K., Gkioxari, G., Dollár, P., Girshick, R.B.: Mask R-CNN. In: ICCV, pp. 2980–2988 (2017)
Kesiman, M.W.A., Pradnyana, G.A., Maysanjaya, I.M.D.: Balinese glyph recognition with gabor filters. J. Phys. Conf. Ser. 1516, 012029 (2020). https://doi.org/10.1088/1742-6596/1516/1/012029
Kirillov, A., Wu, Y., He, K., Girshick, R.: Pointrend: image segmentation as rendering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9799–9808 (2020)
Klette, R., Rosenfeld, A. (eds.) Digital Geometry. The Morgan Kaufmann Series in Computer Graphics, Morgan Kaufmann, San Francisco (2004)
Lee, J., Hayashi, H., Ohyama, W., Uchida, S.: Page segmentation using a convolutional neural network with trainable co-occurrence features. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1023–1028. IEEE (2019)
Li, M., et al.: Docbank: a benchmark dataset for document layout analysis. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 949–960 (2020)
Liang, J., Hu, Q., Zhu, P., Wang, W.: Efficient multi-modal geometric mean metric learning. Pattern Recogn. 75, 188–198 (2018)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV, pp. 2980–2988 (2017)
Ma, W., Zhang, H., Jin, L., Wu, S., Wang, J., Wang, Y.: Joint layout analysis, character detection and recognition for historical document digitization. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 31–36. IEEE (2020)
Made Sri Arsa, D., Agung Ayu Putri, G., Zen, R., Bressan, S.: Isolated handwritten balinese character recognition from palm leaf manuscripts with residual convolutional neural networks. In: 2020 12th International Conference on Knowledge and Systems Engineering (KSE), pp. 224–229 (2020). https://doi.org/10.1109/KSE50997.2020.9287584
Monnier, T., Aubry, M.: docExtractor: An off-the-shelf historical document element extraction. In: ICFHR (2020)
Oliveira, S.A., Seguin, B., Kaplan, F.: dhsegment: a generic deep-learning approach for document segmentation. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 7–12. IEEE (2018)
Paulus, E., Suryani, M., Hadi, S.: Improved line segmentation framework for sundanese old manuscripts. J. Phys. Conf. Ser. 978, 012001. IOP Publishing (2018)
Prusty, A., Aitha, S., Trivedi, A., Sarvadevabhatla, R.K.: Indiscapes: instance segmentation networks for layout parsing of historical indic manuscripts. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 999–1006. IEEE (2019)
Puarungroj, W., Boonsirisumpun, N., Kulna, P., Soontarawirat, T., Puarungroj, N.: Using deep learning to recognize handwritten thai noi characters in ancient palm leaf manuscripts. In: Ishita, E., Pang, N.L.S., Zhou, L. (eds.) ICADL 2020. LNCS, vol. 12504, pp. 232–239. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64452-9_20
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
Siddiqui, S., Malik, M., Agne, S., Dengel, A., Ahmed, S.: DECNT: deep deformable CNN for table detection. IEEE Access 6, 74151–74161 (2018)
Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 282–298. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_17
Trivedi, A., Sarvadevabhatla, R.K.: Hindola: a unified cloud-based platform for annotation, visualization and machine learning-based layout analysis of historical manuscripts. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 2, pp. 31–35. IEEE (2019)
Valy, D., Verleysen, M., Chhun, S., Burie, J.C.: Character and text recognition of khmer historical palm leaf manuscripts. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 13–18. IEEE (2018)
Zhong, X., Tang, J., Yepes, A.J.: Publaynet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015–1022. IEEE (2019). https://doi.org/10.1109/ICDAR.2019.00166
Acknowledgment
We wish to acknowledge the efforts of all annotators who contributed to the creation of Indiscapes2.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Sharan, S.P., Aitha, S., Kumar, A., Trivedi, A., Augustine, A., Sarvadevabhatla, R.K. (2021). Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts. In: Lladós, J., Lopresti, D., Uchida, S. (eds) Document Analysis and Recognition – ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science(), vol 12822. Springer, Cham. https://doi.org/10.1007/978-3-030-86331-9_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-86331-9_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86330-2
Online ISBN: 978-3-030-86331-9
eBook Packages: Computer ScienceComputer Science (R0)