FreshNet: A Lightweight Computer Vision System for Real-Time Freshness Assessment of Vegetables
Bibliographic record
Abstract
According to the Food and Agriculture Organization (FAO), nearly 40% of fruits and vegetables produced globally are lost before reaching consumers, primarily due to spoilage and improper post-harvest handling. In India alone, the post-harvest loss of vegetables is estimated at over ₹13,000 crore annually, largely because of the absence of affordable freshness monitoring tools. While high-end solutions such as hyperspectral imaging or chemical analysis exist, they are inaccessible to small-scale farmers, street vendors, or low-income households due to their cost and technical complexity. To address this gap, we propose FreshNet, a lightweight, computer vision-based system that can assess the freshness of vegetables in real time using basic RGB imagery. The system uses classical techniques such as colour histograms, brightness thresholding, and texture variation detection to classify vegetables as fresh, moderately stale, or rotten — without relying on cloud connectivity, expensive hardware, or high-performance GPUs. Designed to run on laptops, mobile phones, or single-board computers like Raspberry Pi, FreshNet integrates offline voice feedback, multilingual support, and a low-memory footprint, making it ideal for deployment in rural areas, local marketplaces, and smart kitchens. By enabling accessible and cost-free freshness evaluation, FreshNet aims to reduce food waste, enhance food safety, and empower underrepresented communities with practical AI-driven tools.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".