Hosted by Utah State University Libraries
Vision Based Extraction of Nutrition Information from Skewed Nutrition Labels
Abstract
dc:description.abstractVision-based extraction of nutritional information from nutrition labels (NLs) available on most product packages is critical to proactive nutrition management, because it improves the user’s ability to engage in continuous nutritional data collection and analysis. However, even users who are health conscious find it difficult to keep track of their nutrition intake due to lack of time, motivation, or training. In order to make nutrition management more proactive we present a Proactive NUTrition Management System (PNUTS), which aims to make nutrition management more user friendly and proactive using computer vision techniques running on smartphones which are ubiquitous and powerful computers at the same time. There are essentially two modules in PNUTS. First of all, a skewed barcode scanning module capable of reading barcodes irrespective of the camera alignment and a second module which can detect the skew angle of text in nutrition labels and eventually read the text using optical character recognition.
Degree
thesis:*- Name thesis:degree_name
- Doctor of Philosophy (PhD)
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Computer Science
- Grantor dc:publisher
- Hosted by Utah State University Libraries
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zaman, Tanwir
- Contributors dc:contributor
-
- Vladimir Kulyukin
- Nicholas Flann
- Xiaojun Qi