Deep Learning and Indian Heritage


  • B S.Charulatha
  • Arun Rajaraman





content extraction, deep learning, Indian heritage, web pages.


Deep learning is becoming increasingly necessary as data, information and web and mobile interaction are proliferating with form, type and volume of data becoming easy to store, retrieve and process. This necessity is felt not only in science and engineering but also in social and commercial internet activity. The paper explores some ideas of deep learning to process large data in the context of content extraction in a heterogeneous web page containing multi-lingual information, in the Indian context. This basis is used to explore how Indian heritage over several thousands of years, is able to maintain information and knowledge in certain areas through oral, palm leaf and stone-cut data forms. The paper extends the proposed method to some heritage data and concludes how complex from computing point of view to extract the knowledge and essence of some texts like Bhagavad Gita.



[1] Li, Y, C, C, Kuo, J, Wan, X : Introduction to content-based image retrieval — Over view of key techniques, in Image Databases: Search and Retrieval of Digital Imagery, eds. , JohnWiley, New York, pp. 261–284(2002)

[2] Bhanu Prakash, Kolla, Dorai RangaSwamy, M, A, Raja Raman, Arun : ANN for Multi-lingual Regional Web Communication, ICONIP 2012, Part V, LNCS 7667, pp. 473-478(2012)

[3] Bhanu Prakash, Kolla, Dorai RangaSwamy, M, A, Raja Raman, Arun , Performance of Content Based Mining Approach for Multi-lingual Textual Data, International Journal ofModern Engineering Research, Vol.1, No. 1, pp. 146-150 (2011)

[4] B.S.Charulatha, Paul Rodrigues, T.Chitralekha, Arun Rajaraman Mining Ambiguities using Pixel-based Content Extraction, Advances in Intelligent Systems and Computing DOI 10.1007/978-81-322-2674-1,Springer India (2016)

[5] B.S.Charulatha, Paul Rodrigues, T.Chitralekha, Arun Rajaraman Clustering for knowledgeable web mining, Advances in Intelligent Systems and Computing 324,DOI 10.1007/978-81-322-2126-5_54,Springer India (2015)

[6] B.S.Charulatha , Thesis titled Generic and Novel Approach for Web Content Mining for Indian Languages, July 2016.

[7] Rajaraman,A, Paradigm changes needed for Infra structural systems in Indian context, talk in NIT, Tiruchy, January 2017.

View Full Article:

How to Cite

S.Charulatha, B., & Rajaraman, A. (2018). Deep Learning and Indian Heritage. International Journal of Engineering & Technology, 7(3.12), 89–91.
Received 2018-07-19
Accepted 2018-07-19
Published 2018-07-20