Biblioteca para manipulação de modelos de Redes Neurais inteiramente em Java

Manual implementation and training of a dense CNN in Java, including normalization, validation, and testing, achieving ~5% error on a nonlinear function approximation.

PlantAi is a ResNet-based CNN model trained on the PlantVillage dataset to classify plant leaf images as healthy or diseased. This repository includes PyTorch training code, tools to convert the model to TensorFlow Lite (TFLite) for deployment, and an Android app integrating the model for real-time leaf disease detection from camera images.

An Android Mobile application which detects the presence of tumor based on given MRI image. Implemented using Convolutional Neural Network (CNN)

Aplikasi Deteksi Penyakit Pada Daun Tomat menggunakan CNN

Flutter ALPR/ANPR For Android & iOS: license plate recognition, vehicle number plate recognition, ALPR reader, ALPR scanner, license plate OCR, car number plate recognition

My first attempt on a Convolutional Neural Network written in Java. The CNN is trained with mnist data to recognize handwritten digits form 0-9

Android app that recognize MNIST Handwritten Digits using a CNN.

A Java-based implementation of Convolutional Neural Networks (CNN) for character recognition. This repository includes the necessary code, datasets, and documentation to train and evaluate a CNN model for recognizing handwritten or printed characters.

This is a repository of the educational project within CS306 Software Engineering course at the University of Mannheim

Object-Oriented Convolutional Neural Network developed from Scratch.

Aplikasi Berbasis Android untuk Mengklasifikasikan Spesies Ikan Cakalang dan Tongkol

Creation of Convolution Neural Network and improvement

Watermelon disease classification with CNN based Android

SUTD 50.003 ESC Indoor Tracking Project with UnaBiz

An Android app for real-time facial emotion recognition, designed to improve accuracy for Middle Eastern faces and women wearing hijabs. The CNN model is trained on a hybrid dataset (FER2013, CK+, JAFFE, and IEFDB), achieving 88% accuracy on the hybrid test set and 90% on IEFDB test set.

Android app that uses CNN and IDA* algorithms to detect and solve 15-Puzzles

My first attempt at making a semi-customizable convolutional neural network for grayscale images. Note that it is very poorly optimized.

Sign Language Recognition System - Sign Aloud

A mobile application to track your macronutrients intake, calories and set up goals on your fitness journey