Skip to content

Latest commit

 

History

History
65 lines (48 loc) · 3.31 KB

README.md

File metadata and controls

65 lines (48 loc) · 3.31 KB

Handwritten-Character-Recognition

Deep Learning Model for character recognition.

Ask Me Anything !

Dataset: A-Z Handwritten Alphabets in .csv format

Overview

This repository contains all the codes and reference data for building the Handwritten Character recognition Model from scratch.

Abstract

A Deep Learning Model for handwritten character recognition (A-Z). The Dataset containg 26 folders from A to Z containing handwritten images in size 28*28 pixels, each alphabet in the image is centre fitted. Each Image is stored as Gray-level. The feature extraction technique is obtained by normalizing the pixel values. Pixel values will range from 0 to 255 which represents the intensity of each pixel in the image and they are normalized to represent value between 0 and 1. Convolutional neural network is used as a classifier which trains the kaggle dataset. The prediction for the given input image is obtained from the trained classifier.

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 372450 entries, 0 to 372449
Columns: 785 entries, 0 to 0.648
dtypes: int64(785)
memory usage: 2.2 GB

data.shape()

(372450, 785)

Packages used

All Files

  1. (A-Z) Images : Contains the Handwritten images written by me;
  2. best_model.h5 : Deep Learning Model;
  3. Character recoginition.ipynb : Code for building the model from scratch;
  4. Hand Written character Recognition.ipynb : contains the code for recogizing the handwritten characters written by me.

Screenshots/Images

Random Images From the Dataset

Screenshot 2022-04-12 230514

Making Prediction On Test Dataset

Screenshot 2022-04-12 231418

Handwritten Alphabets written by me

Screenshot 2022-04-12 231712

Making Predictions on the Handwritten Characters

Screenshot 2022-04-12 231922

Further Improvement

  • Real Time Character Recognition
  • Better Image Processing such as: reduce background noise to handle real time image or images in different lighting conditions more accurately.

Feel Free to suggest an improvemet in this project.

This is a work from my 4th semester in Computer Enginnering from Saffrony Institute of Technology. Also I was assigned this project work from the Nano Degree course of Autonomous Vehicles by Elite Techno Groups in April 2022.