https://github.com/davidgasquez/letter-recognition

:information_source: Application of Machine Learning techniques to identify randomly distorted capital letters in the English alphabet.
https://github.com/davidgasquez/letter-recognition

letter-recognition machine-learning

Last synced: about 1 month ago
JSON representation

:information_source: Application of Machine Learning techniques to identify randomly distorted capital letters in the English alphabet.

• Host: GitHub
• URL: https://github.com/davidgasquez/letter-recognition
• Owner: davidgasquez
• License: gpl-2.0
• Created: 2014-12-11T20:39:02.000Z (over 10 years ago)
• Default Branch: master
• Last Pushed: 2015-06-30T14:53:09.000Z (almost 10 years ago)
• Last Synced: 2025-04-12T03:53:02.730Z (about 1 month ago)
• Topics: letter-recognition, machine-learning
• Language: R
• Homepage:
• Size: 426 KB
• Stars: 13
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
Letter Recognition

==================

The objective is to identify each of a large number of black-and-white

rectangular pixel displays as one of the 26 capital letters in the English

alphabet. The character images were based on 20 different fonts and each

letter within these 20 fonts was randomly distorted to produce a file of

20.000 unique stimuli. Each stimulus was converted into 16 primitive numerical

attributes (statistical moments and edge counts) which were then scaled to fit

into a range of integer values from 0 through 15.

Data Set Information

--------------------

 - [Letter Recognition Data Set](https://archive.ics.uci.edu/ml/machine-learning-databases/letter-recognition/letter-recognition.names)

 - [Data Folder](https://archive.ics.uci.edu/ml/machine-learning-databases/letter-recognition/)

  

    Data Set Characteristics

    Multivariate

  

  

    Attribute Characteristics

    Integer

  

  

    Number of Attributes

    16

  

  

    Number of Instances

    20.000

  

  

    Associated Tasks

    Classification

  

Results

-------

We are going to measure the accuracy rate into the *test*

subset(4.000 instances)

| Technique      | Test Rate |

|----------------|-----------|

|            LDA |  0.8955   |

|            QDA |  0.9497   |

|            KNN |  0.9641   |

|   Tree(simple) |  0.4799   |

|        Bagging |  0.9454   |

| Random Forests |  0.9915   |

|       Boosting |  0.5805   |

|            SVM |  0.9487   |

Source

------

David J. Slate

Odesta Corporation;

1890 Maple Ave; Suite 115;

Evanston, IL 60201