multi-object-tracker VS EasyOCR

You may find this useful: https://adipandas.github.io/multi-object-tracker/

As you can see, in Frame 43, the tracker assigns the ID 10 to a metal post, but a few frames later when the tracker tracks the same metal post, it provides an ID of 11. This shows that the tracker is assigning new IDs to the same detected object. I cannot seem to find out why this happens, and how to fix it. I am using the motrackers module from this repo. I have not made any changes as such in the mot_yolov3.py file, I have just added the line to print the frame counter.

I have a simple python project which has gone through at least 5 iterations since I began working on it. Please see this link: adipandas/multi-object-tracker.

I have tried a bunch of things. This is what worked best for me: Surya [0]. It can run fully local on your laptop. I also tried EasyOCR [1], which is also quite good. I haven't tried this myself, but I will look at Paddle [2] if the previous two don't float your boat.

All of these are OSS, and you don't need to pay a dime to anyone.

[0]: https://github.com/VikParuchuri/surya

[1]: https://github.com/JaidedAI/EasyOCR

[2]: https://github.com/PaddlePaddle/Paddle

https://github.com/JaidedAI/EasyOCR

Ok on cleaned aligned data, but there are a few newer ones like EasyOCR [0] that can deal with much less organized text (albeit more slowly)

[0] https://github.com/JaidedAI/EasyOCR

PyTesseract Module [ Github ] EasyOCR Module [ Github ] PaddlePaddle OCR [ Github ]

I just uploaded my C++ implementation of EasyOCR, a well known ocr library for python. Also dusted some cobwebbs from some audio related projects as well, feel free to leave feedback or contribute! I only implemented the most salient parts, so certainly could use some community help! Cheers!

EasyOCR is a popular project if you are in an environment where you can use run Python and PyTorch (https://github.com/JaidedAI/EasyOCR). Other open source projects of note are PaddleOCR (https://github.com/PaddlePaddle/PaddleOCR) and docTR (https://github.com/mindee/doctr).

The main one was https://github.com/JaidedAI/EasyOCR, mostly because, as promised, it was pretty easy to use, and uses pytorch (which I preferred in case I wanted to tweak it). It has been updated since, but at the time it was using CRNN, which is a solid model, especially for the time - it wasn't (academic) SOTA but not far behind that. I'm sure I could've coaxed better performance than I got out of it with some retraining and hyperparameter tuning.