Bounding boxes are not correctly extracted.
Budget: $250 – $750 USD
We have smaller errors that must be solved in our python main script .
- Bounding box:
The template is locating the boxes correctly when we create the template, but the extraction is not positioning them correctly for some reason.
I suspect this is a scaling problem since the page must have exactly the same size as the template has.
It could be that the export to an image from PDF is making this scale wrong and it can be that the export function is saving it wrongly.
We had this working before 2 weeks ago, but now it is not working any longer.
Please note: you must be experienced in Tesseract. This means, Amazon, Google and Azure experience in API calls are not sufficient in this job.
Python
- 10+ years (yes and more)
- Python Flask
- Virtual environment
- You work on a Linux machine
- Bounding box:
The template is locating the boxes correctly when we create the template, but the extraction is not positioning them correctly for some reason.
I suspect this is a scaling problem since the page must have exactly the same size as the template has.
It could be that the export to an image from PDF is making this scale wrong and it can be that the export function is saving it wrongly.
We had this working before 2 weeks ago, but now it is not working any longer.
Please note: you must be experienced in Tesseract. This means, Amazon, Google and Azure experience in API calls are not sufficient in this job.
Python
- 10+ years (yes and more)
- Python Flask
- Virtual environment
- You work on a Linux machine