A Hybrid Mining Approach: Gender Prediction from Handwriting
Although after many current technological achievements, there is still not any methodology which will allow a computer to perfectly copy the content of any complex handwritten document.
The cursive nature of handwriting
Use of different pen types or the presence of paper with noisy background etc.
The individuality of handwriting has been studied and determined with specific precision.
Online recognition problem deals with handwriting written with some electronic device that means it deals with real-world problems. whereas offline handwriting problem deals with handwriting which has been written previously and is kept stored. In the field of Human and Computer Interaction, if the gender of a user can automatically be predicted, just by using his or her signature, the system could offer him/her a more personalized interaction and care.
In spite of the fact that the facts confirm that females composing is alluring and neater than male one, this isn’t valid for every one of the cases. There are numerous precedents where we can discover ladylike appearance in manly penmanship. we intend to investigate the connections between the penmanship of various sexual orientations. To foresee the sexual orientation of people from examined pictures of their penmanship. This is finished by removing the arrangement of highlights from composing tests and preparing classifier to learn and separate between them. Highlights which is utilized for arrangement is tortuosity, shape, heading, chain code, and edge bearing. In this article, we mean to break down the connections between the penmanship of various sexual orientations. In this examination utilized, half breed classifiers are utilized and dissected their resultant. Furthermore, the resultant demonstrates the half and half classifiers give better outcomes.
KeywordsData mining Feature extraction Data cleaning Hybrid classification methods
- 1.De Pauw W, Jensen E, Mitchell N, Sevitsky G, Vlissides J, Yang J (2002) Visualizing the execution of Java programs. In: software visualization, Springer. pp 151–162Google Scholar
- 2.Fayyad U, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery in databases. AI Mag 17(3):37Google Scholar
- 3.Ghorashi SH, Ibrahim R, Noekhah S, Dastjerdi NS (2012) A frequent pattern mining algorithm for feature extraction of customer reviews. Int J Comput Sci Issues (IJCSI) 9:29–35Google Scholar
- 4.Sah, R.D., et al.: Pattern extraction and analysis of health care data using rule based classifier and neural network model. Int. J. Comput. Technol. Appl. 8(4), 551–556 (2017). ISSN: 2229-6093Google Scholar
- 6.Hu M, Liu B: Mining and summarizing customer reviews. In: Proceedings of the international conference on knowledge discovery and data mining (KDD), pp 168–177. ACM (2004)Google Scholar
- 8.Knauss E, Damian D, Poo-Caamano G, Cleland-Huang J (2012) Detecting and classifying patterns of requirements clarifications. In: 20th international requirements engineering conference (RE), pp 251–260. IEEEGoogle Scholar
- 10.Marcus A, Feng L, Maletic JI: 3D representations for software visualization. In: Proceedings of the symposium on software Visualization, pp 27–36. ACM (2003)Google Scholar
- 11.Padhy, N., Singh, R.P., Satapathy, S.C.: Cost-effective and fault-resilient reusability prediction model by using adaptive genetic algorithm based neural network for web-of-service applications. Clust. Comput., 1–23 (2018). https://doi.org/10.1007/s10586-018-2359-9
- 12.Popescu A-M, Etzioni O (2005) Extracting product features and opinions from reviews. In: Proceedings of the conference on human language technology and empirical methods in natural language processing (HLT), pp 339–346. Association for Computational LinguisticsGoogle Scholar
- 13.Al Maadeed S, et al (2012) QUWI: an Arabic and English handwriting dataset for offline writer identification. In: International conference on frontiers in handwriting recognitionGoogle Scholar
- 14.Hassaïne A, Al-Maadeed S, Bouridane A (2012) A set of geometrical features for writer identification. In: International conference on neural information processing ICONIP 2012: neural information processing, pp 584–591Google Scholar
- 15.Cao H, Prasad R, Natarajan P (November 2010) Improvements in hmm adaptation for handwriting recognition using writer identification and duration adaptation. In: 2010 International conference on frontiers in handwriting recognition (ICFHR), pp 154–159Google Scholar
- 16.Cheng-Lin L, Fei Y, Da-Han W, Quaffing W (2011) CASIA online and offline Chinese handwriting databases. In: International conference on document analysis and recognition, pp 37–41. IEEE Computer Society, Los AlamitosGoogle Scholar
- 17.Morera Á, Sánchez Á, Vélez JF, Moreno AB Gender and handedness prediction from offline handwriting using convolutional neural networks. Hindawi Complexity 2018, 14. https://doi.org/10.1155/2018/3891624. Article ID 3891624