Conference Paper2011Cited by 19

Rapid feature extraction for Bangla handwritten digit recognition

M Zahid Hossain, M Ashraful Amin, Hong Yan

2011 International Conference on Machine Learning and Cybernetics

IEEE, Vol. 4, pp. 1832–1837

DOI: 10.1109/icmlc.2011.6017001URL

Abstract

Feature extraction is one of the fundamental problems of character recognition. The performance of character recognition system is largely depending on proper feature extraction and correct classifier selection. In this article, a rapid feature extraction method is proposed and named as Celled Projection (CP) that compute the projection of each section formed through partitioning an image. The recognition performance of the proposed method is compared with other widely used feature extraction methods that are intensively studied for many different scripts in literature. The experiments have been conducted using Bangla handwritten numerals along with three different well known classifiers which demonstrate comparable results including 94.12% recognition accuracy using celled-projection.

Keywords

  • Image segmentation
  • Feature extraction
  • Bangla script
  • handwritten digit recognition
  • character recognition

CCDS Authors

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Professor

+1 more affiliation

Department of Information Sciences and Technology

George Mason University, USA

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

References

  1. 1.Ming-Kuei Hu. (1962). Visual pattern recognition by moment invariants. IRE Transactions on Information Theory, 8(2), 179–187[10.1109/tit.1962.1057692]
  2. 2.Øivind Due Trier, Anil K. Jain, Torfinn Taxt. (1996). Feature extraction methods for character recognition-A survey. Pattern Recognition, 29(4), 641–662[10.1016/0031-3203(95)00118-2]
  3. 3.Goesta H. Granlund. (1972). Fourier Preprocessing for Hand Print Character Recognition. IEEE Transactions on Computers, C-21(2), 195–201[10.1109/tc.1972.5008926]
  4. 4.B.B. Chaudhuri, Umapada Pal. (1998). A complete printed Bangla OCR system. Pattern Recognition, 31(5), 531–549[10.1016/s0031-3203(97)00078-2]
  5. 5.Yajun Li. (1992). Reforming the theory of invariant moments for pattern recognition. Pattern Recognition, 25(7), 723–730[10.1016/0031-3203(92)90135-6]
  6. 6.Mindy Bokser. (1992). Omnidocument technologies. Proceedings of the IEEE, 80(7), 1066–1078[10.1109/5.156470]
  7. 7.M. Shridhar, A. Badreldin. (1984). High accuracy character recognition algorithm using fourier and topological descriptors. Pattern Recognition, 17(5), 515–524[10.1016/0031-3203(84)90049-9]
  8. 8.Jun Cao, Majid Ahmadi, M. Shridhar. (2002). Handwritten numeral recognition with multiple features and multistage classifiers. , 6, 323–326[10.1109/iscas.1994.409591]
  9. 9.Saeed Mozaffari, Karim Faez, Majid Ziaratban. (2005). A Hybrid Structural/Statistical Classifier for Handwritten Farsi/Arabic Numeral Recognition.. Machine Vision and Applications, 218–221
  10. 10.PAN BAO-CHANG, WU SI-CHANG, Yan Guangyi. (1989). A METHOD OF RECOGNIZING HANDPRINTED CHARACTERS. WORLD SCIENTIFIC eBooks, 37–60[10.1142/9789814434195_0004]

Cited By

  1. 1.Md Shopon, Nabeel Mohammed, Md Anowarul Abedin. (2016). Bangla handwritten digit recognition using autoencoder and deep convolutional neural network. , 64–68[10.1109/iwci.2016.7860340]
  2. 2.A. B. M. Ashikur Rahman, Md. Bakhtiar Hasan, Sabbir Ahmed, Tasnim Ahmed, Md. Hamjajul Ashmafee, Mohammad Ridwan Kabir, Md. Hasanul Kabir. (2022). Two Decades of Bengali Handwritten Digit Recognition: A Survey. IEEE Access, 10, 92597–92632[10.1109/access.2022.3202893]
  3. 3.Talha Ibn Aziz, Al Shahriar Rubel, Md. Sirajus Salekin, Rafsanjany Kushol. (2017). Bangla handwritten numeral character recognition using directional pattern. , 1–5[10.1109/iccitechn.2017.8281820]
  4. 4.Venugopal Gundimeda, Ratan S. Murali, Rajkumar Joseph, N. T. Naresh Babu. (2018). An Automated Computer Vision System for Extraction of Retail Food Product Metadata. Advances in intelligent systems and computing, 199–216[10.1007/978-981-13-1580-0_20]
  5. 5.Mamatarani Das, Mrutyunjaya Panda, Shreela Dash. (2022). Enhancing the Power of CNN Using Data Augmentation Techniques for Odia Handwritten Character Recognition. Advances in Multimedia, 2022, 1–13[10.1155/2022/6180701]
  6. 6.Edwin Antonio Enriquez, Nelly Gordillo, Luis Miguel Bergasa, Eduardo Romera, Carlos Gómez Huélamo. (2018). Convolutional Neural Network vs Traditional Methods for Offline Recognition of Handwritten Digits. Advances in intelligent systems and computing, 87–99[10.1007/978-3-319-99885-5_7]
  7. 7.Olarik Surinta, Mahir F. Karaaba, Tusar K. Mishra, Lambert R. B. Schomaker, Marco A. Wiering. (2015). Recognizing Handwritten Characters with Local Descriptors and Bags of Visual Words. Communications in computer and information science, 255–264[10.1007/978-3-319-23983-5_24]
  8. 8.Mohammad M. Rahman, Bruce Poon, Md. Ashraful Amin, Hong Yan. (2014). Support System Using Microsoft Kinect and Mobile Phone for Daily Activity of Visually Impaired. , 425–440[10.1007/978-94-017-9588-3_32]
  9. 9.M. V. Jeya Greeba. (2014). Recognition of Ancient Tamil Characters in Stone Inscription Using Improved Feature Extraction.
  10. 10.Mir Pias, Aunnoy K. Mutasim, M. Ashraful Amin. (2017). Bangladeshi Number Plate Detection. , 1–6[10.1145/3095713.3095727]
  11. 11.Saima Afreen, Pradeep Kumar. (2022). Handwritten Digit Recognition using Ensemble learning techniques: A Comparative performance Analysis. , 1149–1155[10.1109/icac3n56670.2022.10074069]
  12. 12.Padma Ramkrushna Bagde, Ajay Anil Gurjar. (2016). A handwritten recognition for free style Marathi script using genetic algorithm. , 43–48[10.1109/icgtspicc.2016.7955267]
  13. 13.Mohammad Shakirul Islam, Md. Ferdouse Ahmed Foysal, Sheak Rashed Haider Noori. (2019). Bayanno-Net: Bangla Handwritten Digit Recognition using Convolutional Neural Networks. 2019 IEEE Region 10 Symposium (TENSYMP), 23–27[10.1109/tensymp46218.2019.8971167]
  14. 14.M. A. Haque Monil, MD. S. Q. Zulkar Nine, Bruce Poon, M. Ashraful Amini, Hong Yan. (2013). Bangla text processing and recognition based on Fuzzy unsupervised Feature Extraction and SVM. , 1272–1278[10.1109/icmlc.2013.6890784]
  15. 15.Md Zahid Hasan, K. M. Zubair Hasan, Shakhawat Hossain, Abdullah Al Mamun, Md Assaduzzaman. (2019). Handwritten Changma Numerals Recognition Using Capsule Networks. , 386–391[10.1109/icaee48663.2019.8975468]
  16. 16.YingChao Zhang, TaiLei Liu, XiaoLing Ye. (2012). Handwriting Digit Recognition Based on Fractal Edge Feature and BP Neural Net. Advances in intelligent and soft computing, 475–481[10.1007/978-3-642-30126-1_75]
  17. 17.K.N. Saravanan, R. Anitha. (2016). Recognition of Multi-lingual Handwritten Numerals Using Partial Derivatives. Research Journal of Applied Sciences Engineering and Technology, 12(1), 27–36[10.19026/rjaset.12.2300]
  18. 18.Xiaoming Zhao, Shiqing Zhang. (2012). Handwritten Digit Recognition Based on LS-SVM. Advances in intelligent and soft computing, 483–487[10.1007/978-3-642-29387-0_74]
  19. 19.Marcin Majak, Andrzej Żołnierek. (2016). Rough Sets and Fuzzy Logic Approach for Handwritten Digits and Letters Recognition. Advances in intelligent systems and computing, 713–722[10.1007/978-3-319-26227-7_67]
← All publications