Tesseract OpenCV Versus CNN: A Comparative Study on the Recognition of Unified Modern Iraqi License Plates
Bibliographic record
Abstract
Various applications central to societal functioning, such as traffic control and parking management, are fundamentally rooted in License Plate Recognition (LPR). The type of license plate significantly impacts the effectiveness of these processes. This study focuses on the 2022 Unified Modern Iraqi license plates, which pose a unique challenge due to their recent design that incorporates the representation of governorate names with symbols. This new design introduces difficulties in accurately recognizing characters, leading to potential misinformation and unreliable applications. Furthermore, there is a dearth of recognition systems specifically tailored for these newly designed plates. In an attempt to surmount these hurdles, this paper introduces a comparative analysis of two models based on stateof-the-art machine and deep learning methods. The first model employs Tesseract by OpenCV for the recognition of characters on the detected plate, while the second model utilizes a nine-layer Convolutional Neural Network (CNN). The research contributes to the field by collating the plates into a dataset and recognizing them for the first time using these models. The results indicate a significant disparity in the performance of the two models, with the CNN model exhibiting superior accuracy in character recognition, surpassing 95.5%, while the Tesseract OpenCV model achieved a rate of merely 36%. This study underscores the potential of deep learning methods in augmenting license plate recognition systems, especially for novel designs like the 2022 Unified Modern Iraqi license plates.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".