VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/564| Title: | K-nearest neighbor method for optical character recognition | Authors: | Nguyen Phuc Vinh Phat | Keywords: | Optical character recognition;K-nearest neighbor method | Issue Date: | 2016 | Publisher: | Vietnamese-German University | Abstract: | The advancement of computer vision technology has significantly improved various areas. One of the most useful applications of computer vision is Optical Character Recognition (OCR). One problem in an OCR system is how to extract. and recognize the characters inside the document image. This thesis proposes an approach to solving such a problem by using the k-nearest neighbor (k-NN) method, one of the simplest but most effective machine learning algorithms. This thesis also provides a simple fully-functional OCR program to calculate the accuracy and robustness of k-NN in an OCR. system. The program is implemented in Python with supporting packages such as OpenCV and scikit-learn. The result of this research yielded an average accuracy of 94% for the implemented OCR system, with acceptable building and query time. |
URI(1): | http://epub.vgu.edu.vn/handle/dlibvgu/564 | Rights: | Attribution-NonCommercial 4.0 International |
| Appears in Collections: | Electrical Engineering and Information Technology (EEIT) |
Files in This Item:
| File | Description | Size | Format | Existing users please Login |
|---|---|---|---|---|
| K-nearest neighbor method for optical character recognition.pdf | 132.94 MB | Adobe PDF |
Page view(s)
31
checked on Oct 16, 2025
Download(s)
22
checked on Oct 16, 2025
Google ScholarTM
Check
This item is licensed under a Creative Commons License