Recognition of font and tamil letter in images using deep learning

• Autorzy: Sridharan Manikandan , Arulanandam Delphin Carolina Rani , Chinnasamy Rajeswari K , Thimmanna Suma , Dhandapani Sivabalaselvamani

Identyfikatory

DOI

10.23743/acs-2021-15

• Języki publikacji: EN

Abstrakty

EN

This paper proposes a deep learning approach to recognize Tamil Letter from images which contains text. This is recognition process, the text in the images are divided to letter or characters. Each recognized letters are sending to recognition system and filter the text using deep learning algorithms. Our proposed algorithm is used to separate letter from the text using convolution neural network approach. The filtering system is used for identifying font based on that letters are found. The Tamil letters are test data and loaded in recognition systems. The trained data are input which contains filtered letter from image. For example, Tamil letters such as are available in test dataset. The trained data are applied into deep convolution neural network process. The two dataset are created which contains test data with Tamil letter and second one for recognized input data or trained data. 15 thousands of letters are taken and 512 X 512 X 3 size deep convolution network is created with font and letters. As the result, 85% Tamil letters are recognized and 82% are tested using font. TensorFlow is used for testing the accuracy and success rate.

Słowa kluczowe

EN

deep convolution network; Tamil Letter; recognition system; font recognition; filtering

PL

głęboka sieć konwolucyjna; Tamil Letter; system rozpoznawania; rozpoznawanie czcionek; filtrowanie

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2021
• Tom: Vol. 17, no 2
• Strony: 90--99
• Opis fizyczny: Bibliogr. 15 poz., fig., tab.

Twórcy

autor

Sridharan Manikandan

• Department of Information Technology, E. G. S. Pillay Engineering College, Nagapattinam, Tamil Nadu, India

• https://orcid.org/0000-0002-9378-518X

autor

Arulanandam Delphin Carolina Rani

• Department of Computer Science and Engineering, K. Ramakrishnan College of Technology, Samayapuram, Tiruchirappalli, Tamil Nadu, India

• https://orcid.org/0000-0002-3206-1305

autor

Chinnasamy Rajeswari K

• Department of Computer Science and Engineering, Sona College of Technology, Salem, Tamil Nadu, India

• https://orcid.org/0000-0003-4579-3166

autor

Thimmanna Suma

• Sri Venkateshwara College of Engineering, Bengaluru, Karnataka, India

• https://orcid.org/0000-0002-1761-7889

autor

Dhandapani Sivabalaselvamani

• Department of Computer Applications, Kongu Engineering College, Perundurai, Erode, Tamil Nadu, India

• https://orcid.org/0000-0002-3373-7610

Bibliografia

• [1] Adomavicius, G., & Tuzhilin, A. (2018). Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering, 17(6), 734–749. http://dx.doi.org/10.1109/TKDE.2005.99
• [2] Bati, E. (2014). Deep convolutional neural networks with an application towards geospatial object Recognition. Diss. Middle East Technical University Ankara.
• [3] Elitez, E. (2015). Handwritten digit string segmentation and recognition using deep learning. Diss. Middle East Technical University Ankara.
• [4] Jaiem, F.K., Slimane, F., & Kherallah, M. (2017). Arabic font recognition system applied to different text entity level analysis. 2017 International Conference on Smart, Monitored and Controlled Cities (SM2C), 36–40. http://dx.doi.org/10.1109/SM2C.2017.8071847
• [5] Koyun, A., & Afsin, E. (2017). 2D optical character recognition based on deep learning. Journal of Turkey Informatics Foundation of Computer Science and Engineering, 10(1), 11–14.
• [6] Manikandan, S., & Chinnadurai, M. (2019). Intelligent and Deep Learning Approach OT Measure E- Learning Content in Online Distance Education. The Online Journal of Distance Education and e-Learning, 7(3), 199–204.
• [7] Manikandan, S., & Chinnadurai, M. (2020). Evaluation of Students’ Performance in Educational Sciences and Prediction of Future Development using TensorFlow. International Journal of Engineering Education, 36(6), 1783–1790.
• [8] Manikandan, S., Chinnadurai, M., Maria Manuel Vianny, D., & Sivabalaselvamani, D. (2020). Real Time Traffic Flow Prediction and Intelligent Traffic Control from Remote Location for Large-Scale Heterogeneous Networking using TensorFlow. International Journal of Future Generation Communication and Networking, 13(1), 1006–1012.
• [9] Manikandan, S., Dhanalakshmi, P., Priya, S., & Mary OdilyaTeena, A. (2021). Intelligent and Deep Learning Collaborative method for E-Learning Educational Platform using TensorFlow. Turkish Journal of Computer and Mathematics Education, 12(10), 2669–2676.
• [10] Sathiyamoorthi, V. (2016). A novel cache replacement policy for Web proxy caching system using Web usage mining. International Journal of Information Technology and Web Engineering, 11(2), 1–13. http://dx.doi.org/10.4018/IJITWE.2016040101
• [11] Sevik, A., Erdogmus, P., & Yalein, E. (2018). Font and Turkish Letter Recognition in Images with Deep Learning. International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (pp. 61–64). IEEE. http://dx.doi.org/10.1109/IBIGDELFT.2018.8625333
• [12] Shanthi ,T., & Sabeenian, R.S. (2019). Modified Alexnet architecture for classification of diabetic retinopathy images. Computers and Electrical Engineering, 76, 56–64. http://dx.doi.org/10.1016/j.compeleceng.2019.03.004
• [13] Tajmir, S.H., & Alkasab, T.K. (2018). Toward augmented radiologists: changes in radiology education in the era of machine learning and artificial intelligence. Academic radiology, 25(6), 747–750. https://doi.org/10.1016/j.acra.2018.03.007
• [14] Yuan, Y., Mou, L., & Lu, X. (2015). Scene recognition by manifold regularized deep learning architecture. In IEEE Transactions on Neural Networks and Learning Systems, (vol. 26(10), pp. 2222–2233). IEEE. http://dx.doi.org/10.1109/TNNLS.2014.2359471
• [15] Zhou, Y., & Tuzel, O. (2017). Voxelnet: End-to-end learning for point cloud based 3d object detection. arXiv:1711.06396. https://arxiv.org/abs/1711.06396

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).