Abstract
Digital libraries include huge amount of information that are continuously increasing with the need of storing various kinds of handwritten documents such as administrative forms, and cultural heritage manuscripts. Therefore, new emerging techniques such as writer retrieval are used to facilitate information extraction from archived documents. Basically, a writer retrieval system is composed of two main steps that are feature generation and dissimilarity measure. To achieve a robust retrieval, we propose the use of an SVM classifier trained to automatically separate intra-writer features from inter-writer features. For feature generation, we investigate the effectiveness of the Histogram of Oriented Gradients, Gradient Local Binary Patterns, and Local Difference Features. Experiments are conducted on three benchmark datasets. The results obtained evince a satisfactory performance of SVM, which can give better results than the state of the art.
Similar content being viewed by others
Data Availability
The used datasets are a benchmarking datasets that are available online. The CVL dataset is available on http://hwww.caa.tuwien.ac.at. The ICDAR-2011 dataset is available on: http://www.cvc.uab.es/icdar2011competition. The KHATT dataset is available on: http://khatt.ideas2serve.net/. This study uses a custom code which is only available via contacting authors.
References
Arab N, Nemmour H, Chibani Y (2020) Improved multi-scale local difference features for off-line handwritten signature verification. In: 020 1st international conference on communications, control systems and signal processing (CCSSP), (El-Oued, 16–17 March), pp 266–270
Atanasiu V, Likforman-sulem L, Vincent N (2011) Writer retrieval — exploration of a novel biometric scenario using perceptual features derived from script orientation. In: 11th international conference on document analysis and recognition, (Beijing, 18–21 September), pp 628–632
Bouadjenek N, Nemmour H, Chibani Y (2015) Age, gender and handedness prediction from handwriting using gradient features. In: 13th international conference on document analysis and recognition, pp 1116–1120
Bouadjenek N, Nemmour H, Chibani Y (2016) Robust soft-biometrics prediction from off-line handwriting analysis. Appl Soft Comput 46:980–990
Bouibed ML, Nemmour H, Chibani Y (2017) New gradient descriptor for keyword spotting in handwritten documents. In: International conference on advanced technologies for signal and image processing, pp 1–5
Bouibed ML, Nemmour H, Chibani Y (2017) Writer retrieval using histogram of templates features and SVM. In: 3rd international conference on electrical engineering and control applications, (Constantine, 21–23 November), pp 537–544
Bouibed ML, Nemmour H, Chibani Y (2018) Evaluation of gradient descriptors and dissimilarity learning for writer retrieval. In: 8th international conference on information science and technology, (Cordoba, 2–5 July), pp 252–256
Bouibed ML, Nemmour H, Chibani Y (2020) Multiple writer retrieval systems based on language independent dissimilarity learning. Expert Syst Appl 143:113023
Bouibed ML, Nemmour H, Derdouche S, Leslous A, Chibani Y (2020) Score level fusion for improving writer retrieval in handwritten document databases. In: 020 1st international conference on communications, control systems and signal processing (CCSSP), (El-Oued, 16–17 March), pp 248–253
Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2:121–167
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE Computer society conference on computer vision and pattern recognition (CVPR), (San Diego, 20–25 June), pp 886–893
Dey S, Nicolaou A, Llados J, Pal U (2016) Local binary pattern for word spotting in handwritten historical document. In: Robles-Kelly A, Loog M, Biggio B, Escolano F, Wilson R (eds) Structural, syntactic, and statistical pattern recognition. Springer International Publishing, Cham, pp 574–583
Djeddi C, Siddiqi I, Souici-Meslati L, Ennaji A (2013) Text-independent writer recognition using multi-script handwritten texts. Pattern Recogn Lett 34:1196–1202
Fiel S, Sablatnig R (2012) Writer retrieval and writer identification using local features. In: 10th IAPR international workshop on document analysis systems, (Queensland, 27–29 March), pp 145–149
Fiel S, Sablatnig R (2013) Writer identification and writer retrieval using the fisher vector on visual vocabularies. In: 12th international conference on document analysis and recognition, (Washington, 23–25 August), pp 545–549
Fiel S, Sablatnig R (2015) Writer identification and retrieval using a convolutional neural network. In: International conference on computer analysis of images and patterns, (Valetta, 2–4 September), pp 26–37
Hmood AK, Suen CY, Lam L (2018) An enhanced histogram of oriented gradient descriptor for numismatic applications. Pattern Recognit Image Anal 28:569–587
Jebril NA, Al-Zoubi HR, Abu Al-Haija Q (2018) Recognition of handwritten arabic characters using histograms of oriented gradient (hog). Pattern Recognit Image Anal 28:321–345
Jiang N, Xu J, Yu W, Goto S (2013) Gradient local binary patterns for human detection. In: International symposium on circuits and systems, Beijing, pp 978–981
Kleber F, Fiel S, Diem M, Sablatnig R (2013) CVL-database: an off-line database for writer retrieval, writer identification and word spotting. In: 12th international conference on document analysis and recognition, (Washington, 23–25 August), pp 560–564
Louloudis G, Stamatopoulos N, Gatos B (2011) ICDAR 2011 Writer identification contest. In: 11th international conference on document analysis and recognition, (Peking, 18–21 September), pp 1475–1479
Mahmoud SA, Ahmad I, Alshayeb M, Al-Khatib WG, Parvez MT, Fink GA, Märgner V, El Abed H (2012) KHATT: arabic offline handwritten text database. In: 12th international conference on frontiers in handwriting recognition, (Bari, 18–20 September), pp 449–454
Marti U-V, Bunke H (2002) The iam-database: an english sentence database for offline handwriting recognition. Int J Doc Anal Recognit 5:39–46
Ojala T, Pietikainen M, Harwood D (1996) A comparative study of texture measures with classification based on feature distributions. Pattern Recogn 29:51–59
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66
Ouamane A, Benakcha A, Belahcene M, Taleb-Ahmed A (2015) Multimodal depth and intensity face verification approach using lbp, slf, bsif, and lpq local features fusion. Pattern Recognit Image Anal 25:603–620
Platt JC (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in large margin classifiers, MIT Press, pp 61–74
Serdouk Y, Nemmour H, Chibani Y (2015) New gradient features for off-line handwritten signature verification. In: International symposium on innovations in intelligent systems and applications, (Madrid, 2–4 September), pp 1–4
Shirdhonkar MS, Kokare MB (2011) Writer based handwritten document image retrieval using contourlet transform. In: Nagamalai D, Renault E, Dhanuskodi M (eds) Advances in digital image processing and information technology. Communications in computer and information science, vol 205, pp 108–117
Vapnik V (1995) The nature of statistical learning theory. Springer, Berlin
Yilmaz MB, Yanikoglu B, Tirkaz C, Kholmatov A (2011) Offline signature verification using classifier combination of HOG and LBP features. In: International joint conference on biometrics (IJCB), (Washington, 11–13 October), pp 1–7
Zhang J, Deng Y, Guo Z, Chen Y (2016) Face recognition using part-based dense sampling local features. Neurocomputing 184:176–187
Funding
The present work has not received any financial assistance.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declare that they have no conflicts of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Bouibed, M.L., Nemmour, H. & Chibani, Y. SVM-based writer retrieval system in handwritten document images. Multimed Tools Appl 81, 22629–22651 (2022). https://doi.org/10.1007/s11042-020-10162-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10162-7