OCR is one of the new and highest trending technology by which you can extract the data from any image. Image can be car number plate, any pdf file, etc. There are certain task which can be proceed by using OCR. With help of few libraries of Python you can easily use them. The libraries used are- OpenCV and Python Tesseract.
Here IDE used was PyCharm from where you can easily download the packages without getting any pip issue while using CMD.
-
OpenCV - It is one of the common libraries in which you can easily solve the computer vision problems and used for numerical computations basically for the image purpose. You can read the image and do certain pre-pocessing of the image like removal of noise, shaping the edges, etc.
-
Python Tesseract - Whereas Python tesseract is the common tool for the OCR purpose only. With help of these you can do multiple functions such as read the embedded digits, characters, string, etc. from any image. But make sure that image should be well pre-processed if there is any kind of noise or distortion is present than the output may vary. You can have more look at the github repo - https://github.com/tesseract-ocr/tessdoc
-
Install the packages in PyCharm by navigating in following manner- Settings-> Python Interpreter-> Click on + -> Choose the package that you want to intsall -> Click on download package
-
Refer to downlaoded path to tesseract.exe
-
Import image and convert into RGB
-
Do the fuctionalities which you want to perform. Some of them will be given in form of py file.
