November 4, 2020
TED NewsDesk, Roorkee: A group of dedicated learners from Indian Institute Technology (IIT) Roorkee won first prize at a tech fest. The event Tech4Heritage, took place recently where the IIT Roorkee team ‘Ancient AI’ won for building an AI model by using data file of reference paintings. The team yielded curative results through the methods of deep learning for the destroyed frescoes of Ajanta Caves.
The enthusiasts- Parth Chhabra, Kushagra Babbar, Arjav Jain and Aryan Prasad, are in the 2nd year of mechanical engineering under BTech programme. The team landed in the hackathon to use their lockdown period productively.
“The idea of undertaking the challenge came in September when Covid cases in India were at its peak. Our common interests in deep learning helped us in teaming up and engaging in the restorative process of the heritage site,” said Parth, the leader of Ancient AI.
“We came across multiple impediments at the hackathon such as errors in logic, programming, syntax, which when addressed effectively, gave us an edge over other participants with less exposure. We had to leverage our skills to explore AI-assisted image processing and reconstruction in great depth,” he added.
Restoration of paintings required useful virtual technologies beside sufficient data of ruinous murals and the renovated once in their correspondence. The team solved the problem of restoring the affected regions by mending them by changing the pixels of those areas with the help of mathematical speculation from the adjoining undamaged parts. The team took four days to coach their AI model to help it recognize the ways to fill the ruinous paintings rightly.
The Positive Aspects of the Project
Parth assured, “We have been able to produce excellent outputs but to replicate what was done 2000 years ago requires perfection and we are striving towards it with more advanced techniques and AI models which will get better via continuous finetuning of the algorithms.”
Kushagra highlighted that it taught them beneficial ways of communicating, punctuality and importance of time limits, project management. Besides it also trained them for practical implementation.
“We got an opportunity to innovate and create socially constructive projects that may help humanity, and the future generations as a whole,” expressed Kushagra. He has experience in various machine learning projects. The third member, Arjav, is an automobile enthusiast passionately willing to work on futuristic locomotives. Aryan, the fourth member, is a quizzer and fanatic about amalgamating mechanical engineering and data science.
Post victory, the team will collaborate with one of the organizers of the initiative, the Sapio Analytics, to acquaint themselves with the technicalities of professional working space. “There are many historical sites and artefacts which need restoration and we plan to scale up the initiative after understanding the viability and potential,” explained Kushagra.
The code after improvement and retesting process will become a part of Arctic Digital Archive. ADA constitutes data of cultural and historical interest from various countries, for the preservation of over 1000 years.
“We have worked on digital restoration, but it can be easily followed by physical restoration through 3D printing which can aid in the reconstruction,” Kushagra said.
Their priority is to learn and perform without planning a career from digital restoration for the time being.
Digital restoration technique
“Under the guidance of an art historian, digital restoration can be accurate and effective. The best part is, the original art masterpieces are preserved as they are, while the public gets an idea of their true beauty through digital restoration,” elaborated Benoy K Behl, an art historian, filmmaker and a photographer.
Electronic renovation does not affect the original painting. It works on the images to showcase the grandeur of the original form of the art.
Source: Times of India