digits-classification

An end to end deep learning project made by using streamlit for predicting handwritten drawn digits/alphabets via CNN & ANN.

Sudoku grid and digits detection

This project is the implementation of the sudoku solver using computer vision & backtracking algorithm

GAN to generate number images

A complete, straightforward digit classification project built with PyTorch, featuring CNN-based training, evaluation metrics, confusion matrix visualization, and XAI using Grad-CAM.

classify handwritten digits (0-9)

Unsupervised domain adaptation using feature aligned maximum classifier discrepancy (FAMCD)

Handwritten Digit Classification (SVM): This project implements a multiclass classification model to recognize handwritten digits (0-9) using a Support Vector Machine (SVM).

A Multi-Layer Perceptron (MLP) implemented from scratch with NumPy, trained to classify handwritten digits (0–9)

Digit recognition (MNIST dataset) using a fully connected neural network (97+ on test)

99% accurate CNN for MNIST handwritten digits

A project allowing to recognize handwritten numbers in the range 0-9.

Classification of digits in MNIST dataset

Implementing Classical Machine Learning solutions in Python using the Scikit-Learn library and other libraries , specifically classification methods applied to the Digits Dataset.

Digit recognition with tensorflow

Domain Adaptation for digits classification using Deep Reconstruction-Classification Network

Sudoku solver using OpenCV’s DNN

Comparing Logistic Regression and nonlinear SVM for handwritten digit classification.

Digit detection using Singular Value Decomposition

Classification of handwritten digits using classical machine learning methods with model optimization and evaluation on the Scikit-learn Digits dataset