Skip to content

Latest commit

 

History

History
79 lines (52 loc) · 2.57 KB

Project_Details.md

File metadata and controls

79 lines (52 loc) · 2.57 KB
Raw

HANDWRITTEN DIGIT RECOGNITION

This is a project to learn handwritten digit recognition on the MNIST dataset.

Basically, we will perform classification on various handwritten texts and judge whether they are valid digits or not using the MNIST dataset.

What is MNIST?

  • MNIST stands for Modified National Institute of Standards and Technology dataset.

  • It is a set of 70,000 small images of digits handwritten by high school students and employees of the US causes Bureau.

  • All images are labeled with the respective digit they represent.

  • MNIST is the hello world of the machine learning. Everytime a ML engineer makes a new algorithm for classification, they would always first check it's performance on the MNIST dataset.

  • There are 70k images and each images has 28*28 = 784 features.

  • Each image is 28*28 pixels and each features simply represents one-pixel intensity from 0 to 255. If the intensity is 0, it means that the pixel is white and if it is 255, it means it is black.

Representation of the handwritten digits in the MNIST dataset


We will use Python interactive notebook (ipynb) to make this ML model.

INSTALLATIONS

pip install numpy
pip install opencv-python
pip install matplotlib
pip install tensorflow

IMPORT STATEMENTS REQUIREMENTS

import os

# import os means that it is a module to interact with the underlying operating system.
import cv2

# cv2 is the module under the OpenCV(Open Computer Vision) it is used all sort of image and video analysis like: facial recognition, liscence plate reading, Optical character recognition etc..
import numpy as np

#NumPy is a Python library used for working with arrays. It also has functions for working in domain of linear algebra, fourier transform, and matrices.
import tensorflow as tf

#TensorFlow is an open source framework developed by Google researchers to run machine learning, deep learning and other statistical and predictive analytics workloads.
import matplotlib.pyplot as plt

#Pyplot is an API (Application Programming Interface) for Python's matplotlib that effectively makes matplotlib a viable open source alternative to MATLAB. Matplotlib is a library for data visualization, typically in the form of plots, graphs and charts.