venkatesh vijaykumar

Implements Ridge detection similar to the one in Mathematica using the eigen values from the Hessian Matrix of the input image using Sobel Derivatives.

The project is now part of the OpenCV-Contrib module code-base

A multimodal classifier for recognizing hate content (speech, imagery or a combination).
The approach involves the development of an intermediate data fusion algorithm.

A collection of implementations of state of the art convolutional neural network (CNN) architectures for computer vision applications.
Implementations are in Keras, using a Tensorflow 1.xx back end, and contains a basic Tensorflow 2.xx port with a few simple tweaks.

The study aims at developing a non-invasive method for diagnosing blood glucose saturation, based upon the principles of near infrared spectrometry.

The study also aims at developing a mathematical model for estimating blood glucose saturation values

The project involved building a reinforcement learning agent to effectively solve the LunarLander v2.0 environment on OpenAI Gym.
A double deep Q-network was utilized as opposed to a deep Q-network for mitigating any possible information bleed back to the neural network.

A basic convolutional neural network applied to the Medissor diabetic retinopathy image database from Kaggle and UCI-DB.
The project is essentially a reflection of the attempts made to teach myself about convolutional neural networks by undertaking a project in that space.