NutriFoodNet: A High-Accuracy Convolutional Neural Network for Automated Food Image Recognition and Nutrient Estimation
Bibliographic record
Abstract
To detect food items in images using Convolutional Neural Networks (CNNs) plays a crucial role in promoting healthier dietary decisions and addressing global nutrition issues.With the rise of online food delivery systems, precisely discerning food items within images and gauging their nutritional components stands as a pivotal undertaking to ensure that people are consuming a balanced diet.Due to its capacity to identify and reliably classify images, CNN is a successful approach for image recognition.By using CNN for food recognition, it is possible to automate the process of nutrient estimation and provide users with more information about their food choices.This might have a substantial effect on public health by encouraging a healthy diet and reducing the incidence of malnutrition in all its forms.An efficient food image recognition method is developed using a convolutional neural network named NutriFoodNet.Popular pre-trained models like ResNet-18, ResNet-50 and Inception V3 were at the center of our attention.A model called NutrifoodNet is developed by modifying the Inception V3 model by using the well-known Food101 dataset, which includes 101,000 picture samples of 101 food varieties.To gauge the model's efficacy, it's imperative to consider metrics such as precision, classification accuracy, F1 score, and recall as fundamental benchmarks.A comparative study was also conducted using up-to-date benchmarks.The results indicated that NutriFoodNet achieved a classification accuracy of 97.3%, outperforming other leading-edge models.An Algorithm is proposed to find the calorie information from different nutrients and comparison with the existing models is also done.
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) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".