Explainable CNN framework for accurate crop disease detection using plant leaf images
Avik Ray, Tamilarasi Kathirvel Murugan, Logeswari Govindaraj, Iran Hussain · 2026
Read Explainable CNN framework for accurate crop disease detection using plant leaf images by Avik Ray, Tamilarasi Kathirvel Murugan, Logeswari Govindaraj, Iran Hussain (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/PMC13538365.txt.
Description
Avik Ray and colleagues present a lightweight explainable neural network for spotting crop disease from leaf photos in a 2026 study. Early spotting saves yield and cuts needless spraying, yet expert checks are slow and scarce in rural areas. The design uses efficient layered filters, attention blocks, and skip links to cut computing load, plus heat maps that show which leaf areas drove each call. Testing used a large public leaf collection.
The collection held more than fifty-four thousand images covering thirty-eight diseases across fourteen crops. Test accuracy ran high, with strong balance across disease classes and near-perfect ranking scores. Comparisons showed rival accuracy to heavier models while staying light enough for phones and field devices. The authors offer the tool for real-time farm diagnosis that users can visually verify.
Catalog record
| CREATOR | Avik Ray, Tamilarasi Kathirvel Murugan, Logeswari Govindaraj, Iran Hussain |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 115886 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |