Week 1 with Freshly Built has completed. I am so curious about this project. It is so interesting to make own python library and let others use this. This is my first project with image processing.
At the beginning, project was explained very briefly and everyone was giving their idea. Every team member was given their task and mentor are helping them in their work. As, we are dealing with extraction of text from images so there are different kind of text present like documents, clicked image or any pdf files.
So, we had to test different OCR model and decided to go with “Pytessaract” to use.
During testing, we saw this model gives bad result when image’s quality is bad so we have decided to do image processing before extracting text from this.
As, I was new to image processing. So, I decided to learnt about it first and I have learnt about different python libraries like cv2, PIL. I also tried to learn pytesseract to extract text.
I just take an simple image to remove skewness for testing myself.
After removing the skewness of the above image and I used pytessaract to extract text from the given image.