Adaptable and Efficient Digit Recognition System for Challenging Datasets: A Case Study on Pump Flowmeter Digits
Bibliographic record
Abstract
Machine digit recognition from various multi-digit displays is a complex task due to the sheer number of unique digit forms, each varying significantly in shape, size, and orientation.Traditional digit recognition libraries may not perform well for all cases, especially when dealing with digital screens that can be highly variable in terms of style, fonts, colour, contrast, intensity, pixel resolution, digit aspect ratio, and spacing.To address these challenges, we present a digit recognition algorithm that is designed to be fast, easy to use, and highly adaptable.Unlike a single fit-all solution, our system can be easily modified to fit different use cases and applications, incorporating additional layers of flexibility and adaptability.This is desirable since different types of displayed digits may have unique features or characteristics that traditional digit recognition libraries do not capture well.To further demonstrate the efficacy of the proposed system, we tested it on a unique pump-flowmeter digits format, which poses significant challenges for digit recognition algorithms due to the complicated shape and layout of the digits.This paper provides a detailed step-by-step account of our system's development and its performance on this challenging dataset.The presented system achieved an accuracy of 80% on test data, is simple and can be used by researchers, developers, and practitioners working in fields such as handwriting recognition, computer vision, machine learning, image processing, pattern recognition, and neural networks.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".