I developed this project while working with my Machine Learning Instructor at Hochschule Rhein-Waal

LittleAdversary is an adversarial machine learning library made to aid research into adversarial attacks and defences, with a primary focus on one-shot defences. It contains an end-to-end implementation of the proposed defence in 'Siamese Neural Networks for Adversarial Robustness ', complete with statistical analysis of the results.

Oneshot face recognition is a system that detects the face of a person and recognizes who the person is by comparing the extracted faces with the faces on the database. The system also trains the neural network model for predictions.

Face recognition one shot learning using MTCNN, FaceNet, Pinecone DB, hosted using streamline and render.

Face recognition using Pytorch, Facenet and Siamese Network

This project is an advanced facial verification application built using a Siamese Neural Network, offering a robust and secure method for identity verification. This project leverages the power of deep learning and computer vision techniques to provide reliable and accurate facial verification capabilities.

Our web app uses AI (VGG-16, CNN, N-shot Learning, Lstm) to detect employee emotions and identification in real-time. It aims to improve well-being and work-life experiences by visualizing an emotional index linked to workplace videos, fostering a healthier work environment.

Experimenting with various approaches to NER.

Design of a Face recognition payment system prototype

Face Recognition.

Implementation of Siamese network for handwritten Arabic characters using Keras.

An advanced system integrating RFID, facial recognition, and AI-based activity detection to enhance campus safety

[MICCAI 2023] (early accept) UOD: universal oneshot detection of anatomical landmarks. https://arxiv.org/abs/2306.07615

Example of one shot learning and few shot learning with omniglot dataset.

Recursive Leasting Squares (RLS) with Neural Network for fast learning

Kernel Fisher Discriminant Analysis implementation following https://arxiv.org/abs/1906.09436