Towards Natural Scene Rock Image Classification with Convolutional Neural Networks
Bibliographic record
Abstract
Autonomous image recognition has numerous potential applications in the field of planetary science and geology. During exploration, geologists could encounter an unknown rock and instead of having to bring back the sample to the laboratory for analysis, a better approach would be to have a mobile device classify the image of a rock. As well, instead of waiting a long time for a planetary rover to send back an image to Earth for classification, its on-board computer could have a software that could automatically classify images of outcrops. In 2017, Shu et. al. used a Support Vector Machine (SVM) classification algorithm to classify uniform rock images into 9 different classes with the image features extracted autonomously. Through this method, they achieved a classification accuracy of 96.71%. Recent publications have shown that Convolutional Neural Networks (CNNs) perform better than other algorithms in classifying images of everyday objects, more specifically for the ImageNet dataset. In light of this development, this paper demonstrates the use of CNNs to classify the same set of rock images. With the addition of dataset augmentation, a 3-layer CNN is shown to have a significant improvement over Shu et. al.'s results, achieving an average accuracy of 99.60% across 10 trials on the test set. Having proven that CNNs can classify uniform and clean images of rocks, this research then tackles a more interesting and practical problem in classifying natural scene images of rocks where the images are taken during field exploration without a standardized method and specialized equipment. The task has been simplified into a binary classification problem where the images are classified into breccia and non-breccia. This research shows that a 5-layer CNN achieves 89.43% classification accuracy for this task.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".