Road-Sign Text Recognition Architecture for Intelligent Transportation Systems
Bibliographic record
Abstract
Text recognition in the automotive context is a crucial task for Intelligent Transportation Systems. Its objective is to supply the driver with important information found on traffic signs. This information could be speed limits, traffic orders (Stop, for example) or texts that describe the nature of the road ahead. In this paper, a four-stage text recognition strategy is investigated. The first stage uses Histogram of Oriented gradients (HOG) features in combination with a trained suppervector machine (SVM) to detect traffic signs, specifically text-based signs such as speed-limit signs or informative-signs describing traffic situations. The detection stage is followed by a filtering stage. This stage aims to 'clean' the detected traffic sign using some filters. The filters tested in this paper are the Grayscale filter, Bilateral filter, Median filtered, and the Gaussian filler. The filtered image is then fed into the third stage, the recognition stage. An open-source Optical Character Recognition tool (OCR) "Tesseract" is used to read the texts found on the detected traffic signs. The strategy concludes with a fourth stage, i.e., post- processing, in order to add a layer of immunity to false positive and false readings. Finally, we compare our work to the standard HOG-SVM scheme. The results show that our scheme exhibits a higher accuracy over the HOG-SVM scheme.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.014 | 0.010 |
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".