Abstract
This paper is presenting a handwriting strokes and grapheme-based offline writer identification framework. This framework works by firstly measuring the hand pressures during script writing using identical grapheme and writing strokes and then generates the pressure descriptors which are rotation as well as scale invariant. The descriptors are used to present different hand pressure distribution accuracies which are defined according to approximation-coefficients of the grapheme zone, perpendicular lines average over the handwritten script skeleton, stroke-width, and handwritten script skeleton grapheme. Discrete-Cosine Transform and Principal-Component-Analysis methods are used to evaluate the descriptors execution accuracy. The performance of the proposed method is assessed with the help of one-versus-all strategy and the k-fold validation is done with the help of Structural Support Vector Machine (S-SVM). Whereas heuristic enhancement calculation based simulated annealing is used to identify the S-SVM hyper parameters. The performance assessment of the handwriting strokes and grapheme based offline writer identification framework with single character gives the encouraging results. Also the combination of the characters enhances the accuracy as well as overall performance of personality identification up to 99.99%.
Similar content being viewed by others
Change history
04 November 2020
This article has been retracted. Please see the Retraction Notice for more detail: https://doi.org/10.1007/s12046-020-01516-w.
References
Galbally J, Sébastien M and Fierrez J 2014 Biometric Antispoofing methods: a survey in face recognition. IEEE Access 2:1530–1552
Manusov Y, Dotan Y, Freylafert O and Khitrenovich A 2015 User Authentication Based on Biometric Handwriting Aspects of a Handwritten Code. US Patent 9,202,035
Parziale A, Santoro A, Marcelli A, Rizzo A P, Molinari C, Cappuzzo A G and Fontana F 2014 An interactive tool for forensic handwriting examination. In: 14 th International Conference on Frontiers in Handwriting Recognition, pp. 440–445
Papaodysseus C, Rousopoulos P, Giannopoulos F, Zannos S, Arabadjis D, Panagopoulos M, Kalfa E, Blackwell C and Tracy S 2014 Identifying the writer of ancient inscriptions and byzantine codices: a novel approach. Compt. Vis. Image Underst. 12(1):57–73
Fecker D, Asit A, Märgner V, El-Sana J and Fingscheidt T 2014 Writer identification for historical arabic documents. In: 22nd International Conference on Pattern Recognition (ICPR), pp. 3050–3055
Hafemann L G, Sabourin R and Oliveira L S 2015 Off-line handwritten signature verification-literature review. arXiv:1507.07909
Smekal Z, Mekyska J, Rektorova I and Faundez Z M 2013 Analysis of neurological disorders based on digital processing of speech and handwritten text. In: Signals, Circuits and Systems (ISSCS), International Symposium on IEEE, pp. 1–6
Kotsavasiloglou C, Kostikis N, Hristu V D and Arnaoutoglou M 2017 Machine learning-based classification of simple drawing movements in parkinson’s disease. Biomed. Signal Proc. Control. 31:174–180
Siddiqi I, Djeddi C, Raza A and Souici M L 2015 Automatic analysis of handwriting for gender classification. Patt. Anal. Appl. 18(4):887–899
Bouadjenek N, Nemmour H and Chibani Y 2015 Robust soft-biometrics prediction from off-line handwriting analysis. Appl. Soft Comput. 46:980–990
Carlà L, Fantacci R, Gei F, Marabissi D and Micciullo L 2016 LTE enhancements for public safety and security communications to support group multimedia communications. IEEE Netw. 30(1):80–85
Porwik P, Doroz R and Orczyk T 2015 The k-nn classifier and self-adaptive hotelling data reduction technique in handwritten signatures recognition. Patt. Anal. Appl. 18(4):983–1001
Vapnik V N 1999 An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5):988–999
Hannad Y, Siddiqi I and El Kettani M E Y 2016 Writer identification using texture descriptors of handwritten fragments. Expert Syst. Appl. 47:14–22
Miller J J, Patterson R B, Gantz D T, Saunders C P, Walch M A and Buscaglia J 2017 A set of handwriting features for use in automated writer identification. J. Forensic Sci. 62(3):722–734
Bensefia A and Paquet T 2016 Writer verification based on a single handwriting word samples. EURASIP J. Image Video Process. 1(34):1–9
Halder C and Roy K 2014 Individuality of isolated bangla characters. In: Devices, Circuits and Communications (ICDCCom), International Conference on IEEE, pp. 1–6
Halder C, Obaidullah S M, Paul J and Roy K 2016 Writer Verification on Bangla Handwritten Characters. Advanced Computing and Systems for Security. Springer, Berlin, pp. 53–68
He S and Schomaker L 2017 Writer identification using curvature-free features. Pattern Recognit. 63:451–464
Brink A, Smit J, Bulacu M and Schomaker L 2012 Writer identification using directional ink-trace width measurements. Pattern Recognit. 45(1):162–171
Khan F A, Tahir M A, Khelifi F, Bouridane A and Almotaeryi R 2017 Robust off-line text independent writer identification using bagged discrete cosine transform features. Expert Syst. Appl. 71:404–415
Christlein V, Bernecker D, Honig F and Maier A and Angelopoulou E 2017 Writer identification using gmm supervectors and exemplar-svms. Pattern Recognit. 63:258–267
Abdi M N and Khemakhem M 2012 Arabic writer identification and verification using template matching analysis of texture. In: IEEE 12th International Conference on Computer and Information Technology (CIT), pp. 192–197
Abdi M N and Khemakhem M 2015 A model-based approach to off-line text-independent arabic writer identification and verification. Pattern Recognit. 48(5):1890–1903
Adak C, Chaudhuri B B and Blumenstein M 2017 Writer identification and verification from intra-variable individual handwriting. arXiv:1708.03361
Kore S and Apte S 2013 Ink width independent global features for writer verification. In: International Conference on Advances in Computing, Communications and Informatics (ICACCI), IEEE, pp. 1770–1774
Kore S L and Apte S D 2016 Writer verification using spatial domain features under different ink width conditions. J. Comput. Sci. Eng. 10(2):39–50
Siddiqi I and Vincent N 2010 Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features. Pattern Recognit. 43(11):3853–3865
Siddiqi I and Vincent N 2009 A set of chain code based features for writer recognition. Document analysis and recognition. In: 10th International Conference on ICDAR’09. IEEE, pp. 981–985
Hanusiak R K, Oliveira L S, Justino E and Sabourin R 2012 Writer verification using texture-based features. Int. J. Doc. Anal. Recognit. 1–14
Bertolini D, Oliveira L S, Justino E and Sabourin R 2013 Texture-based descriptors for writer identification and verification. Expert Syst. Appl. 40(6):2069–2080
Okawa M and Yoshida K 2017 Off-line writer verification based on forensic expertise: Analyzing multiple characters by combining the shape and advanced pen pressure information. Jpn. J. Forensic Sci. Technol. 1–15
Nelder J A and Mead R 1965 A simplex method for function minimization. Comput. J. 7(4):308–313
Czarnecki W M, Podlewska S and Bojarski A J 2015 Robust optimization of SVM hyperparameters in the classification of bioactive compounds. J. Cheminformatics 7(1):1–15
Otsu N 1979 A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1):62–66
Acharya T and Ray A K 2007 Image processing: principles and applications. IEEE Trans. Neural Netw. 18(2):610–620
Zhang T Y and Suen C Y 1988 A modified fast parallel algorithm for thinning digital patterns. Pattern Recognit. Lett. 7(2):99–106
Tyagi S K and Khanna P 2012 Face recognition using discrete cosine transform and nearest neighbor discriminant analysis. Int. J. Eng. Technol. 4(3):3–11
Jiong S and Harris S L 2018 Handwritten digit recognition system on an FPGA. In: IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC), pp. 402–407
Maheshkar V, Kamble S, Agarwal S and Srivastava V K 2012 DCT-based reduced face for face recognition. Int. J. Inf. Technol. Knowl. Manag. 5(1):97–100
Kyrki V and Kragic 2011 Computer and robot vision. IEEE Robot. Autom. Mag. 18(2):121–122
Cruz F, Sidère N and Coustaty M 2017 Local binary patterns for document forgery detection. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol 1, pp. 1223–1228
Hastie T, Tibshirani R and Friedman J 2009 The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd Edition. Springer, Berlin, pp. 261–294
Khan N M, Ksantini R, Ahmad I S and Boufama B 2012 A novel SVM + NDA model for classification with an application to face recognition. Pattern Recognit. 45(1):66–79
Rai H and Yadav A 2014 Iris recognition using combined structural-support-vector-machine (S-SVM) and hamming distance approach. Expert Syst. Appl. 41(2):588–593
Sharma M K and Dhaka V P 2015 Offline language-free writer identification based on speeded-up robust features. Int. J. Eng. (IJE) 28(7):984–994
Sharma M K and Dhaka V P 2015 Offline scripting-free author identification based on speeded-up robust features. Int. J. Doc. Anal. Recognit. (IJDAR) 18(4):303–316
Wanga X Y, Wang T and Bua J 2011 Color image segmentation using pixel wise structural-support-vector-machine (S-SVM) classification. Pattern Recognit. 44(4):777–787
Sharma M K and Dhaka V P 2019 Segmentation of handwritten words using structured support vector machine. Int. J. Pattern Anal. Appl. 1–13
Dhaka V P and Sharma M K 2015 An efficient segmentation technique for Devanagari offline handwritten scripts using the feedforward neural network. Neural Comput. Appl. 26(8):1881–1893
Sharma M K and Dhaka V P 2016 Pixel plot and trace based segmentation method for bilingual handwritten scripts using feedforward neural network. Neural Comput. Appl. 27(7):1817–1829
Sharma M K and Dhaka V P 2016 Segmentation of english Offline handwritten cursive scripts using a feedforward neural network. Neural Comput. Appl. 27(5):1369–1379
Lin S W, Lee Z J, Chen S C and Tseng T Y 2008 Parameter determination of structural-support-vector-machine (S-SVM) and feature selection using simulated annealing approach. Appl. Soft Comput. 8(4):1505–1512
Liu J P, Niu D X, Zhang H Y and Wang G Q 2013 Forecasting of wind velocity: an improved SVM algorithm combined with simulated annealing. J. Cent. South Univ. 20:451–456
Wanling L, Yaozhou L and Daquan D 2014 Research on combination optimization of parameters and character choice for SVM based on simulated annealing and improved QPSO. Appl. Mech. Mater. 3384–3387
Yamazaki F, Samuta N and Liu W 2017 Land-cover classification of suburban areas based on multi-polarized airborne SAR data using texture measures. In: Progress in Electromagnetics Research Symposium-Spring (PIERS), pp. 2772–2778
He Y and Sang N 2011 Robust illumination invariant texture classification using gradient local binary patterns. In: International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping, pp. 1–6
Ferrer M A, Morales A and Pal U 2013 LBP based line-wise script identification. In: 12th International Conference on Document Analysis and Recognition (ICDAR), IEEE, pp. 369–373
Wei H, Chen K, Nicolaou A, Liwicki M and Ingold R 2014 Investigation of feature selection for historical document layout analysis. In: 4th International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE, pp. 1–6
Vargas J F, Ferrer M A, Travieso C M and Alonso J B 2011 Off-line signature verification based on grey level information using texture features. Pattern Recognit. 44(2):375–385
Serdouk Y, Nemmour H and Chibani Y 2014 Combination of OC-LBP and longest run features for off-line signature verification. Signal-image technology and internet-based systems (SITIS). In: 10th International Conference on, IEEE, pp. 84–88
Filippov A I, Iuzbashev A V and Kurnev A S 2018 User authentication via touch pattern recognition based on isolation forest. In: IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), pp. 1485–1489
Serdouk Y, Nemmour H and Chibani Y 2015 Orthogonal combination and rotation invariant of local binary patterns for off-line handwritten signature verification. In: International Conference on Telecommunications and ICT, At Oran/Algeria, vol 1, pp. 1–4
Hu J and Chen Y 2013 Off-line signature verification using real adaboost classifier combination of pseudo-vigorous features. In: 12th International Conference on Document Analysis and Recognition (ICDAR), IEEE, pp. 1345–1349
Du L, You X, Xu H, Gao Z and Tang Y 2010 Wavelet domain local binary pattern features for writer identification. In: Pattern Recognition (ICPR), 20th International Conference on IEEE, pp. 3691–3694
Nicolaou A, Bagdanov A D, Liwicki M and Karatzas D 2015 Sparse radial sampling LBP for writer identification. In: 13th International Conference on Document Analysis and Recognition (ICDAR), IEEE, pp. 716–720
Author information
Authors and Affiliations
Corresponding author
Additional information
This article has been retracted. Please see the retraction notice for more detail:https://doi.org/10.1007/s12046-020-01516-w
About this article
Cite this article
Sharma, M.K., Chanderiya, V. RETRACTED ARTICLE: Writer identification using graphemes. Sādhanā 45, 42 (2020). https://doi.org/10.1007/s12046-020-1276-9
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12046-020-1276-9