SC-1 Introduction to practical AI image processing and analysis without programming
Bibliographic record
Abstract
I will introduce specific examples of easy-to-use AI image processing without programming. It can be realized by using package software called Dragonfly (Object Research Systems, Montreal, Canada). Its deep learning solution is powered by Google’s TensorFlow and Keras. It provides deep learning models can be trained for image segmentation, denoising, and super-resolution. Image Segmentation is the single most universal bottleneck to quantitative analysis. Deep Learning solution offers a straightforward, easy to use workflow that allows users of all levels to perform advanced segmentation tasks rapidly. This level of automated image segmentation is transformative for high-throughput quantitative image analysis. I will explain the workflow of the deep learning and how the segmentation was done without programming. Super Resolution is upscaling and improving image detail by applying super-resolution with Deep Learning solution. Denoising is suppressing noise and restoring the original image, denoising with Deep Learning solution plays a crucial role in preparing data for downstream analysis. Keywords: Machine Learning; Deep Learning; CNN; Image Segmentation; Super Resolution Automated segmentation of a denim fabric sample with Deep Learning's U-Net model. Dataset courtesy of Rigaku.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.178 | 0.109 |
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".