Abstract
In this paper, the problem of classifying handwritten data with respect to gender is addressed. A classification method based on Gaussian Mixture Models is applied to distinguish between male and female handwriting. Two sets of features using on-line and off-line information have been used for the classification. Furthermore, we combined both feature sets and investigated several combination strategies. In our experiments, the on-line features produced a higher classification rate than the off-line features. However, the best results were obtained with the combination. The final gender detection rate on the test set is 67.57%, which is significantly higher than the performance of the on-line and off-line system with about 64.25 and 55.39%, respectively. The combined system also shows an improved performance over human-based classification. To the best of the authors’ knowledge, the system presented in this paper is the first completely automatic gender detection system which works on on-line data. Furthermore, the combination of on-line and off-line features for gender detection is investigated for the first time in the literature.
Notes
eBeam System by Luidia, Inc., http://www.e-Beam.com.
The test is available under http://www.iam.unibe.ch/~smueller/.
References
Bandi K, Srihari SN (2005) Writer demographic classification using bagging and boosting. In: Proceedings of the 12th international graphonomics society conference, pp 133–137
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 Dif 39(2):459–468
Broom ME, Thompson B, et al. (1929) Sex differences in handwriting. J Appl Psychol 13:159–166
Cha S-H, Srihari SN (2001) Apriori algorithm for sub-category classification analysis of handwriting. In: Proceedings of the 6th international conference on document analysis and recognition, pp 1022–1025
Czyz J, Kittler J, Vandendorpe L (2004) Multiple classifier combination for face-based identity verification. Pattern Recognit 37(7):1459–1469
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc B 39(1):1–38
Hamid S, Loewenthal KM (1996) Inferring gender from handwriting in Urdu and English. J Social Psychol 136(6):778–782
Hattori T, Izumi T, Kitajima H, Yamasaki T (2004) KANSEI information extraction from character patterns using a modified Fourier transform. In: Proceedings of the Sino-Japan symposium on KANSEI & artificial life, pp 36–39
Hecker MR (1996) Die Untersuchung der Geschlechtsspezifität der Handschrift mittels Rechnergestützter Merkmalsextraktionsverfahren. PhD thesis, Humboldt-University, Berlin
Huber RA (1999) Handwriting identification: facts and fundamentals. CRC Press, Boca Raton
Jaeger S, Manke S, Reichert J, Waibel A (2001) Online handwriting recognition: the NPen++ recognizer. Int J Doc Anal Recognit 3(3):169–180
Jiang X, Chen Y-F (2008) Facial image processing. In: Bunke H, Kandel A, Last M (eds.), Applied pattern recognition. Springer, Berlin
Kuncheva LI (2004) Combining pattern classifiers: methods and algorithms. Wiley, London
Liwicki M, Bunke H (2005) IAM-OnDB - an on-line English sentence database acquired from handwritten text on a whiteboard. In: Proceedings of the 8th internetional conference on document analysis and recognition, vol 2, pp 956–961
Liwicki M, Schlapbach A, Bunke H, Bengio S, Mariéthoz J, Richiardi J (2006) Writer identification for smart meeting room systems. In: Proceedings of the 7th IAPR workshop on document analysis systems, vol 3872 of LNCS. Springer, pp 186–195
Melin H, Koolwaaij JW, Lindberg J, Bimbot F (1998) A comparative evaluation of variance flooring techniques in HMM-based speaker verification. In: Proceedings of the 5th international conference on spoken language processing, pp 2379–2382
Newhall SM (1926) Sex differences in handwriting. J Appl Psychol 10:151–161
Reynolds DA, Quatieri TF, Dunn RB (2000) Speaker verification using adapted gaussian mixture models. Digit Signal Process 10:19–41
Richiardi J, Ketabdar H, Drygajlo A (2005) Local and global feature selection for on-line signature verification. In: Proceedings of the 8th international conference on document analysis and recognition, pp 625–629
Scheidat T, Wolf F, Vielhauer C (2006) Analyzing handwriting biometrics in metadata context. In: Proceedings of the 8th SPIE conference on the security, steganography, and watermarking of multimedia contents, vol 6072, pp 182–193
Schlapbach A, Bunke H (2008) Off-line writer identification and verification using Gaussian mixture models. In: Marinai S, Fujisawa H (eds.), Machine learning in document analysis and recognition, vol 11. Springer, Berlin, pp. 409–428
Schlapbach A, Liwicki M, Bunke H (2008) A writer identification system for on-line whiteboard data. Pattern Recognit 41:2381–2397
Tenwolde H (1934) More on sex differences in handwriting. J Appl Psychol 18:705–710
Wiskott L, Fellous J-M, Krüger N, von der Malsburg C (1995) Face recognition and gender determination. In: Proceedings of the international workshop on automatic face- and gesture-recognition, pp 92–97
Wu B, Ai H, Huang C (2003) Audio- and video-based biometric person authentication, vol 2688 of LNCS, chapter LUT-based adaboost for gender classification. Springer, Berlin, pp 104–110
Acknowledgments
This work was supported by the Swiss National Science Foundation program “Interactive Multimodal Information Management (IM)2” in the Individual Project “Visual/Video Processing”, as part of NCCR. Special thanks go to Petra and Michael Liwicki, who provided assistance in getting references from the Humboldt-University, Berlin. Furthermore, we thank all volunteers who participated in the on-line classification test.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liwicki, M., Schlapbach, A. & Bunke, H. Automatic gender detection using on-line and off-line information. Pattern Anal Applic 14, 87–92 (2011). https://doi.org/10.1007/s10044-010-0178-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-010-0178-6