Abstract
Digital forensics has a vital effect in several domains and mainly focuses on reactive measures, especially when facing digital incidents. Gender identification becomes the important problem in the realm of forensic techniques and handwriting recognition. In this paper, attention-based two-pathway Densely Connected Convolutional Networks (ATP-DenseNet) is proposed to identify the gender of handwriting. There are two pathways in ATP-DenseNet: Feature pyramid could extract hierarchical page feature, and attention-based DenseNet (A-DenseNet) could extract the word feature by fusing Convolutional Block Attention Module (CBAM) and dense connected block. Finally, ATP-DenseNet makes the final prediction combining the two pathways. Experimental results show the efficiency of ATP-DenseNet, and the proposed method performs better than other researches. And the visualization of the feature maps can help us to know which part of the image contributes most to the gender identity.
Similar content being viewed by others
References
Van Beek HMA, van Eijk EJ, van Baar RB, Ugen M, Bodde JNC, Siemelink AJ (2015) Digital forensics as a service: game on. Digit. Investig 15:20–38. https://doi.org/10.1016/j.diin.2015.07.004
Ellison D, Venter H (2016) An ontology for digital security and digital forensics investigative techniques. In: Proceedings of the 11th international conference on cyber warfare and security, ICCWS, pp. 119–127
Al-Masri E, Bai Y, Li J (2018) A fog-based digital forensics investigation framework for IoT systems. In: 2018 IEEE international conference on smart cloud (SmartCloud), pp. 196–201, IEEE
Shen MX, Wu ZX, Park TS (2012) Securing evidence of file wiping for digital forensic on flash memory. J KIISE: Databases 39(5):271–278
Akremi A, Sallay H, Rouached M, Bouaziz R (2020) Applying digital forensics to service oriented architecture. Int J Web Serv Res (IJWSR) 17(1):17–42. https://doi.org/10.4018/IJWSR.2020010102
Dargan S (2018) Writer identification system for indic and non-indic scripts: state-of-the-art survey. Arch Comput Methods Eng. https://doi.org/10.1007/s11831-018-9278-z
Bi N, Suen CY, Nobile N, Tan J (2019) A multi-feature selection approach for gender identification of handwriting based on kernel mutual information. Pattern Recogn Lett 121:123–132. https://doi.org/10.1016/j.patrec.2018.05.005
Tett RP, Palmer CA (1997) The validity of handwriting elements in relation to self-report personality trait measures. Personal Individ Differ 22:11–18. https://doi.org/10.1016/S0191-8869(96)00183-3
Beech JR, Mackintosh IC (2005) Do differences in sex hormones affect handwriting style? evidence from digit ratio and sex role identity as determinants of the sex of handwriting. Pers Individ Differ 39:459–468
Bulacu M, Schomaker L (2007) Text-independent writer identification and verification using textural and allographic features. IEEE Trans Pattern Anal Mach Intell 29(4):701–717. https://doi.org/10.1109/TPAMI.2007.1009
Du L, You X, Xu H, Gao Z, Tang Y (2010) Wavelet domain local binary pattern features for writer identification. In: Proceedings of 20th international conference on pattern recognition (ICPR), IEEE. pp. 3691–3694
Tan T (1992) Texture feature extraction via visual cortical channel modelling. In: Proceedings of 11th IAPR international conference on pattern recognition Vol. III. conference c: image, speech and signal analysis, IEEE. pp. 607–610
Liu CL (2007) Normalization-cooperated gradient feature extraction for handwritten character recognition. IEEE Trans Pattern Anal Mach Intell 29:1465–1469
Tan J, Lai JH, Zuo XX. (2012) The dataset system of economic dispute handwritten (dsedh) based on stroke shape and structure features. In: Proceedings of 21st international conference on pattern recognition (ICPR), IEEE. pp. 661–664
Xu L, Ding X, Peng L, Li X (2011) An improved method based on weighted grid micro-structure feature for text-independent writer recognition. In: Proceedings of international conference on document analysis and recognition (ICDAR), IEEE. pp. 638–642
Wen J, Fang B, Chen J, Tang Y, Chen H (2012) Fragmented edge structure coding for chinese writer identification. Neurocomputing 86:45–51
Newell AJ, Griffin LD (2014) Writer identification using oriented basic image features and the delta encoding. Pattern Recognit. 47(6):2255–2265. https://doi.org/10.1016/j.patcog.2013.11.029
Said H, Tan T, Baker K (2000) Personal identification based on handwriting. microprocessors 33(1):149–160. https://doi.org/10.1016/S0031-3203(99)00006-0
Chayan H, Md. Obaidullah Sk., Kaushik R (2016) Offline writer identification from isolated characters using textural features. In: Proceedings of the 4th international conference on frontiers in intelligent computing: theory and applications (FICTA) 2015. Springer India. http://dx.doi.org/10.1007/978-81-322-2695-6_20
Helli B, Moghaddam ME (2010) A text-independent persian writer identification based on feature relation graph (frg). Pattern Recogn 43(6):2199–2209. https://doi.org/10.1016/j.patcog.2009.11.026
H. Yaâcoub, I. Siddiqi, & M. E. Y. E. Kettani, 2015. Arabic writer identification using local binary patterns (lbp) of handwritten fragments. http://dx.doi.org/10.1007/978-3-319-19390-8_27
Arandjelovic R, Zisserman A (2012) Three things everyone should know to improve object retrieval. In: Computer vision and pattern recognition. IEEE. http://dx.doi.org/10.1109/CVPR.2012.6248018
Ghiasi G, Safabakhsh R (2013) Offline text-independent writer identification using codebook and efficient code extraction methods. Image Vis Comput 31(5):379–391. https://doi.org/10.1016/j.imavis.2013.03.002
Brink AA, Smit J, Bulacu ML, Schomaker LRB (2012) Writer identification using directional ink-trace width measurements. Pattern Recogn 45(1):162–171. https://doi.org/10.1016/j.patcog.2011.07.005
Siddiqi I, Vincent N (2010) Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features. Pattern Recognit 43(11):3853–3865. https://doi.org/10.1016/j.patcog.2010.05.019
Ahmadian A, Fouladi K, Araabi BN (2016) Writer identification using a probabilistic model of handwritten digits and approximate bayesian computation. In: International conference of signal processing and intelligent systems (ICSPIS), IEEE. http://dx.doi.org/10.1109/ICSPIS.2016.7869875
Abdi MN, Khemakhem M (2015) A model-based approach to offline text-independent arabic writer identification and verification. Pattern Recognit 48(5):1890–1903. https://doi.org/10.1016/j.patcog.2014.10.027
Schomaker L, Wiering M, He S (2015) Junction detection in handwritten documents and its application to writer identification. Pattern Recognit 48(12):4036–4048. https://doi.org/10.1016/j.patcog.2015.05.022
Schomaker L, Bulacu M (2004) Automatic writer identification using connected-component contours and edge-based features of uppercase western script. IEEE Trans Pattern Anal Mach Intell 26(6):787–798. https://doi.org/10.1109/tpami.2004.18
Wu YB, Lu HZ, Zhang ZY (2017) Text-independent online writer identification using hidden markov models. IEICE Trans Inf Syst E100.D(2):332–339. https://doi.org/10.1587/transinf.2016EDP7238
V. Christlein, M. Gropp, S. Fiel, and A. Maier, 2017. Unsupervised feature learning for writer identification and writer retrieval. In: Proc. 14th IAPR Int. Conf. Document Anal. Recognit. (ICDAR), vol. 1, pp. 991–997. https://doi.org/10.1109/icdar.2017.165
Stefan F, Robert S (2015) Writer identification and retrieval using a convolutional neural network. Computer analysis of images and patterns. Springer, Berlin. https://doi.org/10.1007/978-3-319-23117-4_3
Liu M, Jin L, Xie Z (2017) PS-LSTM: capturing essential sequential online information with path signature and LSTM for writer identification. In: IAPR international conference on document analysis & recognition. IEEE Computer Society. http://dx.doi.org/10.1109/ICDAR.2017.114
Yang W, Jin L, Liu M (2015) Chinese character-level writer identification using path signature feature, DropStroke and deep CNN. In: 13th international conference on document analysis and recognition (ICDAR). IEEE. https://doi.org/10.1109/icdar.2015.7333821
Sheng H, Schomaker L (2020) Fragnet: writer identification using deep fragment networks. IEEE Trans Inf Forensics Secur 15:99. https://doi.org/10.1109/TIFS.2020.2981236
Xing L, Qiao Y (2016) Deepwriter: a multi-stream deep CNN for text-independent writer identification. In: 2016 15th international conference on frontiers in handwriting recognition (ICFHR), pp. 584–589. IEEE. http://dx.doi.org/10.1109/ICFHR.2016.0112
Zhang XY, Xie GS, Liu CL, Bengio Y (2016) End-to-end online writer identification with recurrent neural network. IEEE Trans Hum-Mach Syst 47(2):285–292. https://doi.org/10.1109/THMS.2016.2634921
Woo S, Park J, Lee J.-Y, Kweon IS (2018) CBAM: convolutional block attention module. In: Proc. Eur. Conf. Comput. Vis. (ECCV), Munich, German, Sep. 2018, pp. 8–14
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, 2017, pp. 2261–2269
Lin TY, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2016) Feature pyramid networks for object detection
Zagoruyko S, Komodakis N (2017) Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: ICLR
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proc. IEEE conf. comput. vis. pattern recognit.(CVPR), Jun. 2016, pp. 770–778
D. P. Kingma and J. L. Ba, “Adam: A method for stochastic optimization,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2015
Hassaine A, Maadeed SA, Aljaam J, Jaoua A (2013) ICDAR 2013 competition on gender prediction from handwriting. In: International conference on document analysis & recognition. IEEE Computer Society
Maadeed SA, Ayouby W, Hassaine A, Aljaam JM (2012) QUWI: an Arabic and English handwriting dataset for offline writer identification. In: International conference on frontiers in handwriting recognition (ICFHR), IEEE, 2012, pp. 746–751
Marti U-V, Bunke H (2002) The IAM-database: an english sentence database for offline handwriting recognition. Int J Doc Anal. Recognit 5(1):39–46
Mahmoud SA, Ahmad I, AI-Khatib WG, Alshayeb M, Parvez MT, Margner V, Fink GA (2014) KHATT: an open arabic offline handwritten text database. Pattern Recognit 47(3):1096–1112
Abbasi H, Olyaee M, Ghafari HR (2013) Rectifying reverse polygonization of digital curves for dominant point detection. Int J Comput Sci Issues (IJCSI) 10:154–163
Blumenstein M, Liu XY, Verma B (2007) An investigation of the modified direction feature for cursive character recognition. Pattern Recogn 40:376–388
Siddiqi, I., Vincent, N., 2009. A set of chain code based features for writer recognition. In: Proceedings of 10th international conference on document analysis and recognition(ICDAR), IEEE. pp. 981–985
Siddiqi I, Vincent N (2010) Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features. Pattern Recognit 43:3853–3865
Ibrahim AS, Youssef AE, Abbott AL (2014) Global vs local features for gender identification using arabic and english handwriting. In: Proc. ISSPIT, pp 155–160, 2014
N. Bouadjenek, H. Nemmour and Y. Chibani, “Local descriptors to improve offline handwriting-based gender identification”, In Proc. ICSCP, pp 43-46, 2014
Bouadjenek N, Nemmour H, Chibani Y (2015) Age, gender and handedness prediction from handwriting using gradient features. In: Proc. ICDAR, pp 1116–1120, 2015
Navya BJ, Shivakumara P, Shwetha GC, Roy S, Lu T (2018) Adaptive multi-gradient kernels for handwritting based gender identification. In: International conference on frontiers in handwriting recognition
Brahmachary TK, Ahmed S, Mia MS (2018) Safety and quality management practices in construction sector: a case study. J Syst Manag Sci 8(2):47–64
Hai Li, Fan Chunxiao Wu, Yuexin Liu Jie, Lilin Rao (2014) Research of LDAP-based IOT object information management scheme. J Logist Inf Serv Sci 1(1):51–60
Zhao PX, Gao WQ, Han X, Luo WH (2019) Bi-objective collaborative scheduling optimization of airport ferry vehicle and tractor. Int J Simul Modell 18(2):355–365. https://doi.org/10.2507/IJSIMM18(2)CO9
Xu W, Yin Y (2018) Functional objectives decision-making of discrete manufacturing system based on integrated ant colony optimization and particle swarm optimization approach. Adv Prod Eng Manag 13(4):389–404. https://doi.org/10.14743/apem2018.4.298
Acknowledgments
This work was supported by Beijing Social Science Foundation Grant 19JDGLA002, Foundation for Distinguished Young Talents in Higher Education of Henan (CN) (Grant No. 19YJC630043), the National Natural Science Foundation (Grant No. J1824031). We appreciate their support very much.
Funding
This work was funded by Beijing Social Science Foundation Grant 19JDGLA002.
Author information
Authors and Affiliations
Contributions
DG and SL contributed to conceptualization; DG and GX helped with methodology; GX contributed to software; and GX and YM helped with writing—original draft preparation.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict 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
Xue, G., Liu, S., Gong, D. et al. ATP-DenseNet: a hybrid deep learning-based gender identification of handwriting. Neural Comput & Applic 33, 4611–4622 (2021). https://doi.org/10.1007/s00521-020-05237-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05237-3