Handwritten Essay Marking Software

Table of Contents

  1. Introduction
  2. Problem
  3. Solution
  4. Solution Architecture
  5. Use Case Diagram
  6. Functionalities and Work Flow
  7. Technology Stack
  8. Dataset
  9. Timeline
  10. Product Owner
  11. Team
  12. Links

Introduction

This innovative tool bridges the gap between traditional pen-and-paper assessments and digital grading systems, offering a seamless and efficient solution for evaluating handwritten assignments. Handwritten Essay Marking Software employs cutting-edge optical character recognition (OCR) and machine learning algorithms to convert handwritten text into digital format, enabling educators to assess and provide feedback on essays electronically. This revolutionary approach not only streamlines the grading process but also enhances accuracy, consistency, and accessibility in evaluation.

Problem

Traditional manual marking is a time-consuming and labor-intensive process, often leading to inefficiencies in grading. Educators spend significant amounts of time reviewing and evaluating each student’s essay, which can be impractical and burdensome. Also, grading is often influenced by the mood or biases of the marker, leading to inconsistencies in evaluation. Moreover, as the class size increases, the task becomes more challenging and time-consuming for educators.

Solution

In the dynamic landscape of education, the demand for efficient and accurate assessment methods has never been greater. Handwritten essay marking software emerges as a transformative solution, leveraging cutting-edge technology to streamline the grading process and provide insightful feedback to both educators and students. This software represents a paradigm shift in assessment methodology, combining advanced algorithms with intuitive user interfaces to revolutionize the way essays are evaluated. This essay explores the inception, functionality, and potential impact of handwritten essay marking software in modern education.

OCR is used to scan the handwritten essays and convert them into digital text. Natural Language Processing is used to identify key features of the essay such as relevance, duplication, grammar, syntax, and vocabulary. A machine learning model will be trained using our dataset when the marker gives an essay it will output the corresponding mark for that essay.

Solution Architecture

Machine Learning Model Creation

To convert the essays into digital texts, Google Cloud Vision which is the tool for OCR is used. Google Cloud Natural Language API is used to extract features from our essay. Those features are used to train our ML model and an API is used to store our data.

Alt Text

Data Flow

The following image shows the data flow of our system. When the marker uploads an essay it will converted to digital text. Then we give this digital text to our trained ML model and it will give the marks for the essay out of 100. We store those data and the users’ data in our database.

Alt Text

Use Case Diagram

Alt Text

Functionalities and Work Flow

Functionalities:

Work Flow:

Technology Stack

In today’s digitally-driven educational landscape, the demand for efficient and accurate methods of assessing student performance is paramount. Handwritten essay marking software stands as a testament to the convergence of cutting-edge technologies, enabling educators to streamline the grading process and provide constructive feedback to students. This essay delves into the technological foundations of such software, highlighting key components including React, Node.js, Python, TensorFlow, MongoDB Atlas, and Google Cloud Vision.

Alt Text

Data Set

The dataset that has been used to train the ML model is The Hewlett Foundation: Automated Essay Scoring Dataset by ASAP.

Timeline

Alt Text

Product Owner

Team