Abstract
Detecting and correcting skew angles is critical to success in document layout analysis and optical character recognition tasks, as they are more susceptible to failure when on uneven skews. In automation such as postal systems, library management, office business, and banking data entry, skew angle estimation is crucial to improve procedures response. Although different works have addressed this subject, due to the variability in the input data, many solutions are restricted to a specific language, texts whose contents are within a controlled scope, and entries that differentiate printed from handwritten texts. This paper introduces a new method based on RGB gradient capable of detecting and correcting skew angles in different types of documents. We evaluate the proposed method using two public databases and compare our results with other techniques cited in the literature. In general, our proposal achieved results superior to the approaches compared in all groups of documents in the database. Furthermore, we show that our method can work accurately in various text orientations, and it can work efficiently against documents containing short and sparse text lines, non-textual objects, and image noises caused by imperfect scanning.
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
Al-Khatatneh, A., Pitchay, S.A., Al-Qudah, M.: A review of skew detection techniques for document. In: 17th UKSim-AMSS International Conference on Modelling and Simulation, pp. 316–321. IEEE, Cambridge (2015)
Antonacopoulos, A., Clausner, C., Papadopoulos, C., Pletschacher, S.: Historical document layout analysis competition. In: 2011 International Conference on Document Analysis and Recognition, pp. 1516–1520 (2011). https://doi.org/10.1109/ICDAR.2011.301
Avila, B., Lins, R.: A fast orientation and skew detection algorithm for monochromatic document images. In: ACM Symposium on Document Engineering, pp. 118–126 (2005)
Bafjaish, S.S., Sanusi, M., Nasser, M., Ramzani, A., Mahdin, H.: Skew detection and correction of Mushaf Al-Quran script using Hough transform. Int. J. Adv. Comput. Sci. Appl. 9(8), 402–409 (2018)
Bezmaternykh, P., Nikolaev, D.P.: A document skew detection method using fast Hough transform. In: Twelfth International Conference on Machine Vision (ICMV 2019), vol. 11433, p. 114330J. International Society for Optics and Photonics (2020)
Boiangiu, C.A., Dinu, O.A., Popescu, C., Constantin, N., Petrescu, C.: Voting-based document image skew detection. Appl. Sci. 10(7), 2236 (2020)
Boudraa, O., Hidouci, W.K., Michelucci, D.: Using skeleton and Hough transform variant to correct skew in historical documents. Math. Comput. Simulat. 167, 389–403 (2020)
Cai, C., Meng, H., Qiao, R.: Adaptive cropping and deskewing of scanned documents based on high accuracy estimation of skew angle and cropping value. Visual Comput. 37(7), 1917–1930 (2020). https://doi.org/10.1007/s00371-020-01952-z
Clausner, C., Antonacopoulos, A.: Efficient and effective OCR engine training. Int. J. Doc. Anal. Recogn. 23(1), 73–88 (2020)
Delibasis, K.: Efficient implementation of Gaussian and Laplacian Kernels for feature extraction from IP fisheye cameras. J. Imaging 4(6), 1–21 (2018)
Dengel, A., Ahmad, R.: A novel skew detection and correction approach for scanned documents. In: International IAPR Workshop on Document Analysis Systems (2016)
Epshtein, B.: Determining document skew using inter-line spaces. In: 2011 International Conference on Document Analysis and Recognition, pp. 27–31 (2011). https://doi.org/10.1109/ICDAR.2011.15
Huang, K., Chen, Z., Yu, M., Yan, X., Yin, A.: An efficient document skew detection method using probability model and Q test. Electronics 9(1), 55 (2020)
Kar, R., Saha, S., Bera, S.K., Kavallieratou, E., Bhateja, V., Sarkar, R.: Novel approaches towards slope and slant correction for tri-script handwritten word images. Imag. Sci. J. 67(3), 159–170 (2019)
Khidhir, D.A.M.: Use of Radon transform in orientation estimation of printed text. In: 5th International Conference on Information Technology, pp. 1–5 (2011)
Khuman, Y.L.K., Devi, H.M., Singh, N.A.: Entropy-based skew detection and correction for printed meitei/meetei script ocr system. Mater. Today Proc. 37, 2666–2669 (2021)
Lewis, D., Agam, G., Argamon, S., Frieder, O., Grossman, D., Heard, J.: Building a test collection for complex document information processing. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 665–666 (2006)
Liu, Y., Zheng, C., Zheng, Q., Yuan, H.: Removing Monte Carlo noise using a Sobel operator and a guided image filter. Visual Comput. 34(4), 589–601 (2018)
Obaidullah, S.M., Halder, C., Santosh, K., Das, N., Roy, K.: Phdindic_11: page-level handwritten document image dataset of 11 official indic scripts for script identification. Multim. Tools Appl. 77(2), 1643–1678 (2018)
Papandreou, A., Gatos, B., Louloudis, G., Stamatopoulos, N.: ICDAR 2013 document image skew estimation contest (DISEC 2013). In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1444–1448. IEEE (2013)
Pramanik, R., Bag, S.: A novel skew correction methodology for handwritten words in multilingual multi-oriented documents. Multim. Tools Appl. 80(18), 27323–27342 (2021). https://doi.org/10.1007/s11042-021-10822-2
Ptak, R., Żygadło, B., Unold, O.: Projection-based text line segmentation with a variable threshold. Int. J. Appl. Math. Comput. Sci. 27(1), 195–206 (2017)
Ramegowda, D.: A novel method for document skew detection and correction: application to handwritten document and bank documents. Int. J. Appl. Eng. Res. 10 (2015)
Salagar, Rajashekhar, Patil, Pushpa: Analysis of PCA usage to detect and correct skew in document images. In: Joshi, Amit, Mahmud, Mufti, Ragel, Roshan G.., Thakur, Nileshsingh V.. (eds.) Information and Communication Technology for Competitive Strategies (ICTCS 2020). LNNS, vol. 191, pp. 687–695. Springer, Singapore (2022). https://doi.org/10.1007/978-981-16-0739-4_65
Sauvola, J., Kauniskangas, H.: Mediateam Document Database II, A CD-rom Collection of Document Images. University of Oulu, Finland (1999)
Smith, A.R.: Color gamut transform pairs. ACM Siggraph Comput. Graph. 12(3), 12–19 (1978)
Sobel, I., Feldman, G.: A 3x3 Isotropic Gradient Operator for Image Processing. Stanford Artificial Intelligence Project (SAIL) (1968)
Stamatopoulos, N., Gatos, B., Louloudis, G., Pal, U., Alaei, A.: ICDAR 2013 handwriting segmentation contest. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1402–1406. IEEE (2013)
Sun, C., Si, D.: Skew and slant correction for document images using gradient direction. In: Proceedings of the Fourth International Conference on Document Analysis and Recognition, vol. 1, pp. 142–146 (1997)
Tzogka, C., et al.: OCR workflow: facing printed texts of ancient, medieval and modern greek literature. In: Paschke, A., Rehm, G., Qundus, J.A., Neudecker, C., Pintscher, L. (eds.) Proceedings of the CEUR Workshop, Conference on Digital Curation Technologies (Qurator 2021), Berlin, 8th–12th February 2021, vol. 2836. CEUR-WS.org (2021)
Wang, D., Wang, X., Liu, J.: A skew angle detection algorithm based on maximum gradient difference. In: International Conference on Transportation, Mechanical, and Electrical Engineering, pp. 1747–1750. IEEE, ChangChun (2011)
Zhang, D., Liu, Y., Wang, Z., Wang, D.: OCR with the deep CNN model for ligature script-based languages like Manchu. Sci. Program. 2021, 1–9 (2021)
Acknowledgments
Authors thank to Coordination for the Improvement of Higher Education Personnel (CAPES Finance Code #001) and Instituto Federal Goiano, câmpus Urutaí (Process Number: 23219.000404.2022-67), for their financial support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rocha, B. et al. (2022). Skew Angle Detection and Correction in Text Images Using RGB Gradient. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds) Image Analysis and Processing – ICIAP 2022. ICIAP 2022. Lecture Notes in Computer Science, vol 13232. Springer, Cham. https://doi.org/10.1007/978-3-031-06430-2_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-06430-2_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06429-6
Online ISBN: 978-3-031-06430-2
eBook Packages: Computer ScienceComputer Science (R0)