Bibliographic record
Abstract
Image recognition technology is now widely used in various industries, and CNN has played an indispensable role in it over the past decade. The paper discusses the use of Convolutional Neural Networks (CNN) for fruit image recognition, aiming to verify the impact of different CNN designs on model training time, test accuracy, and test accuracy. The experiment uses data from the Kaggle Fruits 360 project and focuses on ten different categories of fruit. The CNN model is built using 3*3 convolutional kernels and features four combinations of convolutional and relu layers. The final test accuracy is recorded as 98.1714%. The paper also discusses potential reasons for lower-than-expected accuracy and attempts to address these issues, including overfitting, image resolution, and the simplicity of the training set. The impact of regularization and different image resolutions on model accuracy is observed. The paper concludes by highlighting the practicality of CNN in image recognition, but also acknowledges limitations such as training time, computational resources, and the abstract nature of extracted features. It also emphasizes the importance of choosing an appropriate training set for model accuracy and suggests that other AI models may offer solutions to the shortcomings of CNN. Overall, the paper provides insights and experiences for those working with CNN in image recognition and acknowledges the rapid development of artificial intelligence in recent years.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 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".