Text Spotting for Low-Resolution Price Tag Images
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Text spotting on low-resolution images is a challenging as well as a popular subject for computer vision researchers. Detecting and also recognizing small characters with a singular system has several difficulties. We have devised a system with multiple simplistic neural networks to overcome the text spotting of product prices on the price tag images taken from the market shelf images. We have acquired our own dataset of market shelf images with 40252 price tag crop images with corresponding price tag text labels. We have focused on detecting the price area on the tags instead of detecting the whole tag with product name, barcode, date, etc. This setup lets us design the sub-networks with relatively well-known and simple architectures. Our architecture consists of one feature extractor backbone ResNet-18, one convolutional network for detecting text area, and one convolutional recurrent network for recognizing characters. As a result, we obtained around 0.80 full-text accuracy and 0.91 character similarity.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it