EasyOCR | OCR recognition component | Computer Vision library

The new version of OpenCV has some issues. Uninstall the newer version of OpenCV and install the older one using:

This is the answer:

I was able successfully to read this image with tesseract by doing the following:

• cropping out the pink border
• reducing to grayscale (binarising)
• running tesseract with --psm 8 (see this question )

I don't know if the cropping is necessary, but I couldn't get any output at all with any page segregation mode before binarising.

I did the processing manually here, but you will likely want to automate it. A good trick for setting thresholds is to look at the standard deviation of the image in question and use that to scale your thresholds, rather than picking some absolute value and having it fail on you.

Here's the image I got working:

And the run:

You are not reading the image. Please use opencv to read the image. Ensure that the image is in the current directory or provide the absolute path of the image.

I would start with image enhancement. It's hard to tell what exactly is applicable but here are some possible manuevers:

1. As usual recognition algorithms are not invariant to rotation. And every image seems to be geometically distorted similarly. You can try to normalize the geometry by warpPerspective function from Opencv with appropriate transformation matrix. Rotation is a subset of all possible transformations covered by perspective transform.
2. You can try to use advanced deblurring techniques like wiener filter or deeplearning. It seems like point spread function is different from image to image that complecates the recovery.
3. There is some periodic signal in your images (vertical blue-white-blue stripes). That can possibly can be enhanced by doing FFT -> removing components of the specific wavelength -> iFFT.

Anyway looking on your images, I am not sure if it will be easy to achieve the desired result without diving into the OCR pipeline.

Solved downgrading to the nov 2021 version of opencv

First you could use print() to see what you have in variables - it helps to see what is needed in code.

Using for-loops (without range()) you get lists, not indexes, so results_[i][j][0] is wrong.

If you have empty list then you should skip them - ie. if i: .... to run code only when i is not empty.

You can have a look at AWS EC2 Instances with GPU Support. There are 3 or 4 classes available (p3, g3, p4 and g4). They should be sufficient for your usecase. Make sure to use the AWS Deep Learning AMI, to get out of the Box NVIDIA Drivers and CUDA Support.

Edit: Ref- https://docs.aws.amazon.com/dlami/latest/devguide/gpu.html

Use this code to achive the result in single line