Optimizing Hyperparameters for Thai Cuisine Recognition via Convolutional Neural Networks
Bibliographic record
Abstract
Automated food logging is an essential component of modern dietary management, and food recognition plays a crucial role in this process.However, the recognition of dishes and food items unique to specific cultures or regions remains a less explored area.In this study, we focus on the automatic recognition of Thai cuisine, employing transfer learning techniques and comparing the performance of 20 state-of-the-art convolutional neural networks.We investigate the impact of hyperparameters, such as batch size and image resolution, as well as image preprocessing methods on classification accuracy and training time for the topperforming models.Our evaluation, using the THFOOD-50 dataset consisting of 15,688 images across 50 classes, demonstrates that the optimal model achieves top-1 and top-5 classification accuracies of 90.44% and 99.97%, respectively, representing a significant improvement over previous results.We find that increasing image resolution substantially enhances accuracy, while batch size exerts a negligible effect.Moreover, cropping the edges of images can further improve accuracy, but this technique is only effective when employing low image resolution.Our findings contribute to the development of advanced food recognition algorithms, with potential applications in dietary management and nutrition planning.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| 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".