SDS 439: Deep Learning for Machine Vision — with Deblina Bhattacharjee

Earthquake Detection

Deblina Bhattacharjee shares her innovative work in using computer vision for early earthquake detection. She explains how computer vision algorithms can analyze building movements to detect primary and secondary seismic waves, which are crucial for predicting earthquakes. This approach uses visual magnification techniques to capture subtle vibrations invisible to the human eye, thus enabling timely alerts.

You're using computer vision to detect changes in the movement of a building, and that can be used to predict when an earthquake is going to hit. Wow. Yeah, that is super cool.

--- Jon Krohn

This groundbreaking work highlights the potential of computer vision in addressing real-world challenges 1.

   

Medical Imaging

In the realm of medical imaging, Deblina applies computer vision techniques to enhance diagnostic processes. She developed algorithms to detect white blood cells in medical images, which aids in faster and more accurate diagnoses. This method reduces the time and variability associated with manual detection, showcasing the efficiency of automated systems.

Detecting white blood cells from medical images from the blood samples are very, very difficult. So I thought, maybe I can use it.

--- Deblina Bhattacharjee

Her work demonstrates the transformative impact of AI in healthcare, improving both speed and precision 2.

   

Art & Style Transfer

Deblina's research also bridges the gap between digital humanities and computer vision, focusing on style transfer and immersive technology. At EPFL, she works on projects that transform artistic landscapes and historical periodicals into digital experiences. The goal is to create immersive environments using VR and AR, enhancing how we interact with art.

The end goal would be to turn it into an immersive experience, but right now, because it's still, at its very inception, the project, and we are taking baby steps.

--- Deblina Bhattacharjee

This ambitious project aims to redefine artistic engagement through technology 3.