Hawks, Justin
(2018)
Intelligent UPC-A Barcode Scanning Using Machine Learning.
Master's Thesis, University of Pittsburgh.
(Unpublished)
This is the latest version of this item.
Abstract
Encoding data in barcodes that can be decoded electronically with barcode scanners is useful in numerous industries and barcodes are used in various aspects of everyday life. This paper proposes a barcode scanner algorithm that unlike conventional barcode scanners, implements a machine learning algorithm in order to decode UPC-A barcodes. The machine learning algorithm makes use of the SURF algorithm for feature point extraction along with K-means clustering to create the visual vocabulary. The classifiers are trained using Support Vector Machines (SVMs) using a Sequential Minimal Optimization (SMO) solver. The proposed algorithm was tested and compared to the results obtained using a conventional barcode scanner algorithm developed in MATLAB, as well as to general distribution test data collected with an experimental setup using imaging scanners. Test results show that the barcode scanner algorithm with the trained image classifiers implemented outperform both the conventional barcode scanner algorithm tested as well as the barcode scanners used in the experimental test when it comes to accuracy. The results clearly depict that machine learning is a valuable tool for the future of barcode scanners. The improved read rates can drastically increase processing times in industrial settings such as delivery services.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
20 June 2018 |
| Date Type: |
Publication |
| Defense Date: |
19 February 2018 |
| Approval Date: |
20 June 2018 |
| Submission Date: |
20 February 2018 |
| Access Restriction: |
5 year -- Restrict access to University of Pittsburgh for a period of 5 years. |
| Number of Pages: |
65 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
Swanson School of Engineering > Electrical and Computer Engineering |
| Degree: |
MS - Master of Science |
| Thesis Type: |
Master's Thesis |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
Barcodes, UPC-A, machine learning, image classifier, speeded-up robust features, support vector machine, sequential minimal optimization, K-means clustering, linear kernel, defects, contrast, decodability, accuracy |
| Date Deposited: |
20 Jun 2019 05:00 |
| Last Modified: |
20 Jun 2023 05:15 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/33856 |
Available Versions of this Item
-
Intelligent UPC-A Barcode Scanning Using Machine Learning. (deposited 20 Jun 2019 05:00)
[Currently Displayed]
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}