everything is listed down

This project will focus on Automatic Character Recognition using Principal Component Analysis (PCA) is a simple method of identifying the principal components of a dataset, then aligning characteristics of test sequences to one of many classes. The results of this project are important! If you do well on this project, you will have about 20% of the Final Project complete as well. The goal is to introduce students a very basic form of machine learning using a familiar tool in MATLAB. Students may use Python if they are comfortable with it, though it is not required.

DATASET: CHARS74K DATASET

This is a database of handwritten characters. It includes both English Characters, and Kannada Characters. This project will focus on English Characters only.

• 36 Classes (0-9, A-Z)
• 55 Samples of Each
• Consists strictly of PNG images
• Original Paper:
  • T. E. de Campos, B. R. Babu and M. Varma. Character recognition in natural images. In Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP), Lisbon, Portugal, February 2009.

PROJECT STEPS: THESE ARE THE HIGH-LEVEL STEPS FOR THIS PROJECT

The intent for these steps is to provide students with a High-Level roadmap for successfully completing this project. As a general guideline, completing one part each week is a pretty good pace for completion on time.

• Part 1: Convert the data to a usable form for performing PCA.
• Part 2: Isolate training data from testing data. Generate the Principal Components.
• Part 3: Project the testing data onto the Principal Components to determine the most similar class
• Part 4: Collect Statistics and show results.

PROJECT 1 DELIVERABLES

• Present all files in a SINGLE zip file.
• Should include all MATLAB code used to execute the project.
• Final Presentation
  • USE THE TEMPLATE GENERATED AS PART OF HW 1!
  • Required Sections:
    • Problem Introduction
    • Technical Solution Approach
    • Implementation and Results
    • Conclusion