Deep Learning-Based Convolutional Neural Network Approach for Smart Automated Classification and Sorting of Vegetables
Bibliographic record
Abstract
The classification of vegetables plays a critical role in modern agriculture, food supply chains, and smart farming practices. Accurately identification of plants like vegetables apart is key for automating the classification, ensuring safe food and helping the environment. This project introduces a CNN type of model based on deep learning to aid in correctly classifying Bean, Bitter Guard, Bottle Guard, Brinjal, Broccoli, Cabbage, Capsicum, Carrot, Cauliflower and Cucumber. Twelve thousand images, each representing one class, were collected from Kaggle and organized into training, validation and testing subsets containing 70%, 20% and 10% of images, respectively. To make the CNN perform and generalize better, both dropout layers and max-pooling were used to improve the underlying structure. High accuracy of 99% was found in the experimental results and the precision, recall and F1-scores for all classes were consistently above 0.98. Loss and accuracy plots indicated that my model converged smoothly without strongly overfitting. Looking at the confusion matrix, we observed that the model performed well, because the main spots on the matrix were black and other spots were small and scattered. It backs the objectives of the Sustainable Development Goals by supporting food security, good health, advancements in industry, responsible purchases, infrastructure and actions against climate change through enhanced food processing and supply methods. This research confirms that the model can be used in automated vegetable sorting, development of agricultural technologies and smart food systems, boosting precision agriculture and digital security of food.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".