تشخیص جنسیت نویسنده مستقل از متن و زبان نوشتاری با استفاده از پالایش پویای نمادین مبتنی بر تبدیل رادن
محورهای موضوعی : مهندسی برق و کامپیوترکاظم نوری هفت‌چشمه 1 , رضا خدادادي 2 , یونس اکبری 3 , سيدمحمد رضوي 4 , حسن احمدی ترشیزی 5
1 - دانشگاه سمنان
2 - دانشگاه آزاد اسلامی، واحد مشهد
3 - دانشگاه سمنان
4 - دانشگاه بیرجند
5 - دانشگاه آزاد اسلامی، واحد مشهد
کلید واژه: پالایش پویای نمادین تبدیل رادن تشخیص جنسیت نویسنده دست‌خط برون‌خط,
چکیده مقاله :
در این مقاله یک سیستم خودکار بر مبنای روشی جدید در استخراج ویژگی برای تشخیص جنسیت افراد از روی تصاویر اسکن‌شده نمونه دست‌خط ارائه شده است. در روش پیشنهادی به منظور نشان‌دادن تمایز بین نمونه‌های دست‌خط زنان و مردان، ابتدا از تصویر دست‌نوشته، تبدیل رادن گرفته می‌شود و سپس با استفاده از یک ابزار تحلیلی در سیستم‌های دینامیکی با عنوان پالایش پویای نمادین، ویژگی‌های هر نمونه دست‌خط استخراج می‌گردد. آموزش و طبقه‌بندی ویژگی‌های استخراج‌شده از نمونه‌های دست‌خط با شبکه عصبی پرسپترون چندلایه انجام شده است. در پایان با هدف بررسی کارایی روش پیشنهادی، آزمایش‌هایی بر روی بانک اطلاعاتی MSHD صورت پذیرفت. علاوه بر آزمایش تشخیص جنسیت بر روی کل بانک اطلاعاتی، دو چالش جدید تشخیص جنسیت مستقل از متن و زبان نوشتاری نیز بررسی شده است. آزمایش‌های انجام‌شده نشان می‌دهد روش پیشنهادی میزان دقت تشخیص را نسبت به کارهای قبلی که از روش‌های جدیدی در تحلیل دست‌خط از قبیل فرکتال‌ها، کدهای زنجیره‌ای و بافت‌ها بهره می‌برند، بهبود داده است. بهترین نرخ دقت به دست آمده در آزمایش‌ها 9/84 درصد گزارش شده است.
In this paper an automated system based on feature extraction of new techniques is presented to detect the gender from the scanned images (off-line) handwriting samples. In order to show the difference between examples of handwriting, in the first step Radon transform is taken from the handwritten image, and then each handwriting sample features are extracted using symbolic dynamic filtering. Training and classification of extracted features from the samples are carried out by the multi-layer perceptron neural network. At the end, to determine the effectiveness of the proposed method, experiments are carried out on the Multi Script Handwritten Database (MSHD). In addition, two new challenges of text and script-independent gender detection are explored. Experiences show that the proposed method improves the detection rate compared to the previous works such as fractals, chain codes and textures. The best detection rate is able to achieve accuracy of 84.9% in experiences.
[1] F. Adrian and G. Barrie, "Graphology and personality: another failure to validate graphological analysis," Personality and Individual Differences, vol. 8, no. 3, pp. 433-435, 1987.
[2] R. J. Klimoshk and A. Rafaeli, "Inferring personal qualities through handwriting analysis," J. of Occupational and Organizational Psychology, vol. 56, no. 3, pp. 191-202, 1987.
[3] E. Neter and G. Ben-Shakhar, "The predictive validity of graphological inferences: a meta-analytic approach," Personality and Individual Differences, vol. 10, no. 12, pp. 735-745, 1989.
[4] R. P. Tett and C. A. Palmer, "The validity of handwriting elements in relation to self-report personality trait measures," Personality and Individual Differences, vol. 22, no. 1, pp. 11-18, 1997.
[5] S. Hamid and K. M. Loewenthal, "Inferring gender from handwriting in Urdu and English," The J. of Social Psychology, vol. 136, no6, pp. 778-782, 1996.
[6] H. James, "Sex differences in handwriting: a comment on spear," British Educational Research J., vol. 17, no. 2, pp. 141-145, 1991.
[7] W. N. Hayes, Identifying Sex from Handwriting, Percept Motor Skills, pp. 91-800, 1996.
[8] I. Siddiqi, C. Djeddi, A. Raza, and L. Souici-Meslati, "Automatic analysis of handwriting for gender classification," Pattern Analysis and Applications, vol. 18, no. 8, pp. 887-899, 2014.
[9] V. Burr, "Judging gender from sampels of adult handwriting: accuracy and use of cues," the J. of Social Psychology, vol. 142, no. 6, pp. 691-700, 2002.
[10] A. Chaabouni, H. Boubaker, M. Kherallah, and A. Alimi, "Fractal and multi-fractal for Arabic offline writer identification," in Proc. of Int. Conf. on Pattern Recognition, ICPR'10, pp. 3793-3796, 23-26 Aug. 2010.
[11] M. Liwicki, A. Schlapbach, and H. Bunke, "Automatic gender detection using on-line and off-line information," Pattern Analysis and Applications, vol. 14, no. 1, pp. 87-92, 2011.
[12] M. Blumenstein, X. Liu, and B. Verma, "An investigation of the modified direction feature for cursive character recognition," Pattern Recognition, vol. 40, no. 2, pp. 376-388, 2007.
[13] M. Blumenstein, B. Verma, and H. Baseli, "A novel feature exteraction technique for the recognition of segmented handwriten characters," in Proc. of Int. Conf. on Document Analysis and Recognition, ICDAR'03, pp. 137-141, 6 Aug. 2003.
[14] N. Bouadjenek, H. Nemmour, and Y. Chibani, "Age, gender and handedness prediction from handwriting using gradient features," in Proc. of 13th Int. Conf. on Document Analysis and Recognition, ICDAR'15, pp. 1116-1120, 23-26 Aug. 2015.
[15] E. Sokic, A. Salihbegovic, and M. Ahic-Djokic, "Analysis of off-line handwritten text samples of different gender using shape descriptors," in Proc. of Int. Symp. on Telecommunications, pp. 114-120, 25-27 Oct. 2012.
[16] S. Al Maadeed and A. Hassaine, "Automatic prediction of age, gender, and nationality in offline handwriting," EURASIP J. on Image and Video Processing, vol. 10, no. 1, pp. 19-29, 2015.
[17] R. Hussain, A. Reza, I. Siddiqi, K. Khurshid, and C. Djeddi, "A comprehensive survey of handwritten document benchmarks: structure, usage and evaluation," EURASIP J. on Image and Video Processing, vol. 56, no. 6, pp. 1-24, Dec. 2015.
[18] R. N. Bracewell, Two - Dimensional Imaging, Prentice Hall, 1995.
[19] J. S. Lim, Two - Dimensional Signal and Image Processing, Prentice Hall, 1990.
[20] S. Bahrampour, A. Ray, S. Sarkar, T. Damarla, and N. Nasrabadi, "Performance comparsion of feature extraction algorithms for target detection and classification," Pattern Recognition Letter, vol. 34, no. 16, pp. 2126-2134, 1 Dec. 2013.
[21] A. Ray, "Symbolic dynamic analysis of complex systems for anomaly detection," Signal Process, vol. 84, no. 7, pp. 1115-1130, Jul. 2004.
[22] A. Subbu, A. Srivastav, A. Ray, and E. Keller, "Symbolic dynamic filtering for image analysis: theory and experimental validation," Signal Image and Video Processing, vol. 4, no. 3, pp. 319-329, Sept. 2010.
[23] C. Djeddi, et al., "LAMIS-MSHD: a multi-script offline handwriting database," in Proc. of the 14th Int. Conf. on Frontiers in Handwriting Recognition, ICFHR'14, pp. 93-97, 2014.
[24] N. Otsu, "A threshold selection method from gray-level," IEEE Trans. on Systems, vol. 9, no. 1, pp. 62-66, Jan. 1979.
[25] M. Cheriet, N. Kharma, C. L. Liu, and C. Suen, Character Recognition Systems: A Guide for Students and Practitioners Anomaly Detection, John Wiley and Sons Inc, 2007.
