Keras

Plantify: a plant leaf recognition model - CNN species classifier, FastAPI backend, and an active-learning retraining pipeline.

Centralized Streamlit AI application integrating Deep Learning and NLP models for spam classification and tumor detection.

AIShield Watchtower: Dive Deep into AI's Secrets! 🔍 Open-source tool by AIShield for AI model insights & vulnerability scans. Secure your AI supply chain today! ⚙️🛡️

Music control with hand gesture recognition using Mediapipe, OpenCV, Tensorflow and PyGame

Text classification

Multilabel classification of text medical records (chest R-grams) by LSTM

This project had been migrated from my previous GitHub

Teremin musical baseado em visão computacional e reconhecimento de gestos de mão utilizando OpenCV

Trying to solve the anti-aliasing problem with machine learning

This project adapts Google's Dinosaur Game with Gesture Recognition, enabling players to control the dinosaur's actions via hand movements. It employs TensorFlow and OpenCV for gesture recognition and Python for scripting. This fusion of gaming and technology enhances user engagement, showcasing the innovation achievable through computer vision.

Mobile Messanger Application with Automatic Facial Emotion Classification

An agricultural surveillance and control mobile application's backend with 2 AI models integrated

A Python-based computer vision and AI system for skin disease recognition and diagnosis. Led end-to-end project pipeline, including data gathering, preprocessing, and training models. Utilized Keras, TensorFlow, OpenCV, and other libraries for image processing and CNN models, showcasing expertise in deep learning and machine learning techniques.

Build and train a deep learning model to classify cat and dog images, with model performance analysis.

A Keras neural network covered in a PyQt5 UI. Allows to recognize hand-written numbers [SCHOOL PROJECT]

The Dog Breed Identifier is a Python program that utilizes a pre-trained ResNet50V2 model to classify images of dogs into their respective breeds.

A food image classification project using TensorFlow and CNNs.

A Tensorflow image classification model trained using Keras on around 5,000 pictures to accurately predict whether an object identifies more similar to a human or banana with 89% confidence after processing.

This GitHub repository contains a simple Python project for handwritten digit recognition using the MNIST dataset and TensorFlow.

Attention Based Image Captioning Using Object Features