Enhanced rice leaf disease classification via contour-driven segmentation and optimized deep transfer learning architectures
Ummer Shakeel, Muhammad Asif Habib, Muhammad Yasir, Muhammad Umar Chaudhry, Muhammad Munwar Iqbal, Mudassar Ahmad, Qaisar Abbas, Muhammad Abdul Qayum · 2026
Read Enhanced rice leaf disease classification via contour-driven segmentation and optimized deep transfer learning architectures by Ummer Shakeel, Muhammad Asif Habib, Muhammad Yasir, Muhammad Umar Chaudhry, Muhammad Munwar Iqbal, Mudassar Ahmad, Qaisar Abbas, Muhammad Abdul Qayum (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-0348290.txt.
Description
Ummer Shakeel and co-workers compare five deep learning designs for spotting diseases on rice leaves, adding an outlining step that shows where the sickness sits. Pakistan ranks among the world's top rice growers, and hand scouting cannot cover its fields. Their 2026 study trains the rival designs on a balanced public set of close to two thousand leaf photos.
Each design learned from pre-trained vision backbones rather than starting cold. After sorting, a guided cut-out method traced the diseased patches so farmers can see why the program flagged a leaf. The classification came from the networks alone; the outlines serve explanation. Clear visual proof could help skeptical growers trust and act on automated scouting.
Catalog record
| CREATOR | Ummer Shakeel, Muhammad Asif Habib, Muhammad Yasir, Muhammad Umar Chaudhry, Muhammad Munwar Iqbal, Mudassar Ahmad, Qaisar Abbas, Muhammad Abdul Qayum |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 136843 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |