SE-DBIRNet: Squeeze-and-Excitation Driven Dual-Path Residual Network for Mango Shelf-Life Stages Classification
Ibrar Ahmad, Bushra Siddique, Muhammad Junaid, Mostafa Gouda, Aftab Khaliq, Zia Ul Haq, Zhengjun Qiu · 2026
Read SE-DBIRNet: Squeeze-and-Excitation Driven Dual-Path Residual Network for Mango Shelf-Life Stages Classification by Ibrar Ahmad, Bushra Siddique, Muhammad Junaid, Mostafa Gouda, Aftab Khaliq, Zia Ul Haq, Zhengjun Qiu (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/PMC13362431.txt.
Description
Ibrar Ahmad and colleagues introduce a 2026 computer vision study that sorts mangoes into five shelf-life stages, from unripe to spoiled. Sorting by eye is slow and uneven, and poor sorting wastes a large share of the crop in poorer countries. Their model reads a photo and judges ripeness from color and skin texture, using a design built to run fast on small devices.
Trained on 4,428 mango photos, the model sorted the stages with about 98 percent accuracy in repeated tests. It beat other light models while staying quick and lean on memory. Photo maps show it looks at the same skin cues a human grader would. The tool could suit packing sheds with cheap hardware.
Catalog record
| CREATOR | Ibrar Ahmad, Bushra Siddique, Muhammad Junaid, Mostafa Gouda, Aftab Khaliq, Zia Ul Haq, Zhengjun Qiu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53124 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |