In small-scale industries, the conventional practice of assigning serial numbers to manufactured parts by physically punching them poses challenges in efficient data retrieval. To overcome this, there is a critical need to leverage Optical Character Recognition (OCR) technology for automating the process of serial number extraction from part images. The existing manual methods are not only time-consuming but also susceptible to errors, especially under adverse environmental conditions.
Download the Project as zip file
cd OCR_SOLUTION
pip install -r requirement.txt- Download the trained models
| Model name | Used datasets | Languages | Purpose | Model Link |
|---|---|---|---|---|
| General | SynthText, IC13, IC17 | Eng + MLT | For general purpose | Click |
| IC15 | SynthText, IC15 | Eng | For IC15 only | Click |
| LinkRefiner | CTW1500 | - | Used with the General Model | Click |
- Run with pretrained model
python test.py --trained_model=[weightfile] --test_folder=[folder path to test images] --char True
The result image and score maps will be saved to ./result by default.
--trained_model: pretrained model--text_threshold: text confidence threshold--low_text: text low-bound score--link_threshold: link confidence threshold--cuda: use cuda for inference (default:True)--canvas_size: max image size for inference--mag_ratio: image magnification ratio--poly: enable polygon type result--show_time: show processing time--test_folder: folder path to input images--refine: use link refiner for sentense-level dataset--refiner_model: pretrained refiner model--char: Character level split (default:False). If True, means Each character is got identified used for Model Deployment
- Download the Datasets
| Used datasets | Dataset Link |
|---|---|
| DATASET | Click |
| EMNIST | Click |
| NIST | Click |
| SVHN | Click |
| Custom Dataset | Cannot disclose Internship Dataset |
- Bounding Box of the Image
- Region Score shows Heatmap of the probability of a pixel being at the center of a character
- Affinity Score shows Heatmap of the probability of the space between adjacent characters
- Recognised Text shows above the bounding box
