Abstract
Textline segmentation in ancient handwritten documents is still considered as a challenging task in document analysis and recognition field even though various rule-based methods exist. These methods succeed under constraint such as a roughly uniform background. They do not contribute well in case of variable inter-line spacing and overlapping characters. This article proposes faster region-convolution neural network (R-CNN) based robust method to segment the textlines in the ancient handwritten document in Devanagari script for the first time in literature. The feature matrix has been generated by residual network and proposals have been predicted through the region proposal network (RPN). A pooling layer has been used to extract regions of interest, known as region of interest pooling layer, to locate the textlines. The performance of the proposed textline segmentation system has been evaluated on self generated dataset of ancient handwritten documents in Devanagari script and it has achieved the f-measure of 99.98%. Experimental results demonstrate that the proposed system outperforms the existing state-of-the-art methods of textline segmentation.
Similar content being viewed by others
References
Chammas E, Mokbel C, Likforman-Sulem L (2018) Handwriting recognition of historical documents with few labeled data. In: 13th IAPR International workshop on document analysis systems. IEEE, Vienna, pp 43–48
Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Hawaii, pp 1251–1258
Garz A, Fischer A, Sablatnig R, Bunke H (2012) Binarization-free text line segmentation for historical documents based on interest point clustering. In: 10th IAPR International workshop on document analysis systems, Gold Coast, pp 95–99
Ghosh R (2021) A recurrent neural network based deep learning model for offline signature verification and recognition system. Exp Syst Applic 168 (1):114249
Ghosh R, Vamshi C, Kumar P (2019) Rnn based online handwritten word recognition in devanagari and bengali scripts using horizontal zoning. Pattern Recogn 92(1):203–218
Grüning T, Leifert G, Strauß T, Michael J, Labahn R (2019) A two-stage method for text line detection in historical documents. Int J Doc Anal Recognit 22(3):285–302
Gupta MR, Jacobson NP, Garcia EK (2007) Ocr binarization and image pre-processing for searching historical documents. Pattern Recogn 40 (2):389–397
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, Venice, pp 2961–2969
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE Conference on computer vision and pattern recognition, Las Vegas, pp 770–778
Kavitha A, Shivakumara P, Kumar G, Lu T (2016) Text segmentation in degraded historical document images. Egypt Inform J 17(2):189–197
Keshri P, Kumar P, Ghosh R (2018) Rnn based online handwritten word recognition in devanagari script. In: 16th International conference on frontiers in handwriting recognition, Niagara falls, pp 517–522
Kim S, Park S, Na B, Yoon S (2020) Spiking-yolo: spiking neural network for energy-efficient object detection. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, New York, pp 11270–11277
Kleber F, Sablatnig R, Gau M, Miklas H (2008) Ancient document analysis based on text line extraction. In: 19th International conference on pattern recognition, Tampa, pp 1–4
Lenc L, Martínek J, Král P, Nicolao A, Christlein V (2021) Hdpa: historical document processing and analysis framework. Evolv Syst 12 (1):177–190
Likforman-Sulem L, Faure C (1994) Extracting text lines in handwritten documents by perceptual grouping. Advances in handwriting and drawing: a multidisciplinary approach, 117–135
Liu S, Deng W (2015) Very deep convolutional neural network based image classification using small training sample size. In: 3rd IAPR Asian conference on pattern recognition, Kuala Lumpur, pp 730–734
Louloudis G, Gatos B, Pratikakis I, Halatsis C (2009) Text line and word segmentation of handwritten documents. Pattern Recogn 42(12):3169–3183
Martínek J, Lenc L, Král P (2020) Building an efficient ocr system for historical documents with little training data. Neural Comput Applic 32 (23):1–19
Messaoud IB, Amiri H, Abed HE, Märgner V (2012) A multilevel text-line segmentation framework for handwritten historical documents. In: 13th International conference on frontiers in handwriting recognition, Bari, pp 515–520
Moysset B, Kermorvant C, Wolf C, Louradour J (2015) Paragraph text segmentation into lines with recurrent neural networks. In: 13th International conference on document analysis and recognition, Tunis, pp 456–460
Narang SR, Jindal M, Kumar M (2019) Devanagari ancient documents recognition using statistical feature extraction techniques. Sādhanā 44 (6):141–148
Narang SR, Jindal M, Kumar M (2019) Line segmentation of devanagari ancient manuscripts. Proceedings of the National Academy of Sciences India Section A: Physical Sciences 90(4):1–8
Pelikan M, Goldberg DE, Cantú-Paz E et al (1999) Boa: The bayesian optimization algorithm. In: Proceedings of the genetic and evolutionary computation conference, vol 1, Orlando, pp 525–532
Rabaev I, Biller O, El-Sana J, Kedem K, Dinstein I (2013) Text line detection in corrupted and damaged historical manuscripts. In: 12th International conference on document analysis and recognition, Washington, pp 812–816
Redmon J, Farhadi A Yolov3: an incremental improvement, arXiv:1804.02767
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Procedings of the neural information processing systems, Motreal, pp 91–99
Renton G, Soullard Y, Chatelain C, Adam S, Kermorvant C, Paquet T (2018) Fully convolutional network with dilated convolutions for handwritten text line segmentation. Int J Doc Anal Recognit 21(3):177–186
Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) Generalized intersection over union: a metric and a loss for bounding box regression. In: IEEE Conference on computer vision and pattern recognition, Long Beach, pp 658–666
Saabni R, Asi A, El-Sana J (2014) Text line extraction for historical document images. Pattern Recogn Lett 35(1):23–33
Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vis 104(2):154–171
Vo QN, Lee G (2016) Dense prediction for text line segmentation in handwritten document images. In: IEEE International conference on image processing, Phoenix, pp 3264–3268
Yang S, Gao T, Wang J, Deng B, Lansdell B, Linares-Barranco B (2021) Efficient spike-driven learning with dendritic event-based processing. Front Neurosci 15:97–111
Zeiler M, Fergus R (2014) Visualizing and understanding convolutional networks. In: 13th European conference on computer vision, Zurich, pp 818–833
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors have no conflict of interest/competing interest to declare that are relevant to the content of this article.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jindal, A., Ghosh, R. Text line segmentation in indian ancient handwritten documents using faster R-CNN. Multimed Tools Appl 82, 10703–10722 (2023). https://doi.org/10.1007/s11042-022-13709-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13709-y