Week 2: Coding begins!

Introduction

After finishing up learning about GUI's last week, all research aspects of the project were complete. This week focused more on the coding aspects of the project as most of the code for the handwriting recognition software had been written during this week. Additionally, a start was made towards the report writing.

Project Progression


The practice code that was used for image recognition of animals in week 0 was used as a basis to begin writing the code for the handwriting recognition software. Throughout the week, with continuous testing and improvements to the code, significant progress had been made towards developing the final software. 

Initially, the first draft of the code had problems recognising many of the written characters, specifically the letter 'O'. 




As can been seen from the examples above, the code had difficulty recognising the character 'O' with a reasonable level of accuracy. Furthermore, sometimes the testing of the code would give nonsensical results as in the second case above with the word 'MOMO' where the two 'M' characters are recognised as different letters by the program. As in the second case above, the code would on occasion fail to read any of the letters in word. 

Through further testing of words written in different types of handwriting, it was discovered that words and even sentence would have a higher chance of being recognised correctly if written with a thicker handwriting. 
 


As can be observed from the example above, thicker handwriting had a greater chance of being recognised accurately.

With further specific testing (like on the character 'O' that had great difficulty in being identified by the program) and subsequent improvements to the program, a perfectly recognised sentence was observed (as seen below).



All the characters in the sentence above with the exception of the letter 'O' have a recognition accuracy of 98-100%. Even the letter 'O' had a recognition accuracy of 90.08%.
  
Even with significant progress towards the code, there were still improvements left to be made during week 3 such as the implantation of a GUI in the program for modularity purposes.

Lastly, using the draft of the requirements specification created last week (week 1), a start was made into the report writing.

Plans for week 3


  • Implement the GUI system in the handwriting recognition program 
  • Finish the coding aspect of the project i.e. have the program working accurately up to a reasonable standard (above 85% accuracy) on various types of handwriting, words, sentences.
  • Begin thinking about ideas for the project poster 
  • Start thinking about how the software would be maintained during its lifetime (ideas from which could be used towards the sustainable development assignment aspect of this project)
Location: United Kingdom

Comments

Post a Comment

Popular posts from this blog

Week 1: A Start To The Project

Image
Introduction After completing initial research into handwriting recognition systems and understanding how they work, plans were made to begin developing the final code on Python. Furthermore, the first academic advisor meeting regarding the project was held where ideas for how the project would be developed was discussed. Project Progression After researching into different types of handwriting recognition software , a word document summarising the useful information that was learnt was created. This document contains information such as definitions for key terminology used in a handwriting recognition software (e.g. neural networks, activation function, epoch etc..) as well as notes on training, validation and test sets that will be implemented into the program during its development. Below are a few pictures highlighting some of the information found in this document. In short, this document will be used by the team to quickly refer back to concepts they learnt during the research we
Read more

Week 4: Finished Product

Image
  Introduction The aim of this week was to carry out further tests on the handwriting recognition software program to make certain that it works as expected and any limitations are known and considered. This main objective was to have a deliverable product ready by the end of the week for assessment (during week 5's bench inspection). Project Progression Some of the results form further tests carried out during this week:  Test Result 1 (unsuccessful at fully recognising all the written characters) Test Result 2 (unsuccessful at f ully recognising all the written characters) As can be seen from the pictures above, further testing on the program revealed a limitation that hadn't been observed prior: some letters being completely ignored by the program and therefore not being recognised at all. After several attempts of testing different handwritings, it was found that writing characters straighter and each with the same size had a greater chance of being recognised by the progra
Read more