A calculator that uses handwritten Kannada digits and operators to calculate the result, using contour detection and CNN model predictions. PyTorch, OpenCV, PIL and CustomTkinter.

Using a Convolutional Neural Network (CNN) to identify the Kannada numerical digits. Tensorflow (Keras) is used to create, train and load the neural network model. CustomTKinter/TKinter are used to provide the GUI and OpenCV is used to read input form the GUI.

Kannada OCR (Optical Character Recognition) with ML (Machine Learning) classification algorithm involves training a machine learning model to recognize and classify Kannada characters from scanned or digital images.

Comparison of Keras and Koch's Siamese neural networks for image recognition.

This project recognizes 49 Kannada letters using a CNN classifier (TensorFlow/Keras). A FastAPI backend and Next.js (TypeScript) frontend enable users to draw letters and get predictions.

Handwritten Numeral Recognition using Convolutional Neural Networks

capsule network for handwritten digit recognition

BNN trained on Kannada MNIST

I choosed to build it with keras API (Tensorflow backend) which is very intuitive. Firstly, I will prepare the data (handwritten digits images) then i will focus on the CNN modeling and evaluation.

ಅಕ್ಷರ ಕಲಿ - Kannada Alphabet Learning Application

Repository for Kaggle Kannada MNIST Digit Recognition Challenge 2019

CNN Model for Kannada Hand-written Digit Recognition

This is CNN based number classification on the Kannada mnist data set

Simple feedforward NN for Kannada Digits.

This project aims to classify handwritten Kannada digits using multiple layers of algorithms.

Repository containing codes made for different Kaggle's Competitions. Competitions in this repository: Digit Recognizer, Titanic and Kannada MNIST.

Classification & Prediction of Images of Handwritten Digits in the Kannada Language.