Image-based identification and DEA-based optimization modeling of antibiotic packaging using unsupervised learning techniques
Phakdee Sukpornsawan, Yutthapoom Meepradist, Titinun Auamnoy, Ureerat Suksawatchon, Somchart Chokchaitam, Suthabordee Muongmee · 2026
Read Image-based identification and DEA-based optimization modeling of antibiotic packaging using unsupervised learning techniques by Phakdee Sukpornsawan, Yutthapoom Meepradist, Titinun Auamnoy, Ureerat Suksawatchon, Somchart Chokchaitam, Suthabordee Muongmee (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0354277.txt.
Description
Sukpornsawan and colleagues, in a 2026 study, explore how computers can recognize antibiotic packages in Thai pharmacies. Look-alike packaging is a safety risk when staff check medicines by eye under time pressure. Their approach reads both the look of a package and the words printed on it.
Thirty-six products were photographed and measured for traits such as image complexity, how much of the package is printed area, and how confidently a text reader could read the words. A clustering method sorted the packages into nine groups with shared traits. Packages in a middle range for complexity and printed area were recognized most consistently, and text reading confidence mattered too. A second analysis rated which groups used their inputs most efficiently. The authors offer their framework as a structured way to judge packaging for automated checking systems.
Catalog record
| CREATOR | Phakdee Sukpornsawan, Yutthapoom Meepradist, Titinun Auamnoy, Ureerat Suksawatchon, Somchart Chokchaitam, Suthabordee Muongmee |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34805 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |