Barley Variety Identification by iPhone Images and Deep Learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The quality of barley seeds determines the quality and flavor aspects of malts and beers, and the purity of barley seeds is one of the primary considerations in the malting process. Visual discrimination between barley varieties is difficult and requires a barley specialist with intensive experience and years of training. Therefore, computational and automatic methods are in great demand to efficiently and effectively evaluate barley seed purity among different varieties. By using digital images, this research work developed a novel, automated, deep learning-based approach to accurately classify barley seeds. It implemented and compared different artificial neural networks for the classification problem based on the shape, color, and texture attributes of the barley seed. Data augmentation and transfer learning strategies were integrated into the deep convolutional networks to maximize the model’s performance and accuracy. The results demonstrate the feasibility and effectiveness of automatic classification of barley seeds with high validation accuracy and test accuracies at 95.71% and 95.70%, respectively.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| 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 | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it