Improved Text recognition algorithms on different text domains like scene text, handwritten, document, Chinese/English, even ancient books

The first event stream based scene text recognition benchmark dataset and framework

The hand-writing recognition engine built with TypeScript. Forked from KanjiCanvas.

an option selector mechanism to select the best option against actual(unlabeled) dataset based on the previous training(Labeled) datasets ,written in pure/vanilla JavaScript

This a Machine Learning Project which Recognises handwritten digits .i.e. 0 to 9.

handwritten image recognition without using common nueral network libraries

Tifinagh Character Classifier is a Python-based application that uses a pre-trained deep learning model to recognize and classify Tifinagh script characters. Built with TensorFlow and Tkinter, this project provides an intuitive graphical interface for users to upload images of Tifinagh characters and receive predictions with confidence scores.

Using computer vision to recognize hand written digits

Training a sequential model to classify handwritten digits by using the mnist dataset and creating a interface to classify your own handwritten digits.

A Java implementation of Self-Organizing Kohonen Map that classifies hand-written characters.

Multiple machine learning algorithms to solve associated problems coupled with varying theoretical examinations.

🚀 Built a CNN-based digit classifier using the MNIST dataset 🧠✍️. Integrated with a Python GUI using Tkinter 🖼️, allowing users to draw digits and get real-time predictions 🔢✨. A fun fusion of deep learning and user interaction! 🖌️📊

Simple Neural Network, Deep Learning for hand written digits recognition.

Domain adversarial network trained on MNIST-M, SVHN, and USPS

On Anonymous Commenting: A Greedy Approach to Balance Utilization and Anonymity for Instagram Users - Accepted at SIGIR 2019