How to recognize text from image with Python OpenCv OCR ?

Tutorial about how to convert image to text using Python+ OpenCv + OCR. Help you install opencv for python, install and config tesseract ocr for windows.
Please SUBSCRIBE my channel to support me for free working.
Relative videos:
1. Recognize digital screen display
3. Recognize answer sheet with mobile phone:
4. Recognize marked grid with USB camera:
5. Recognize answers sheet with mobile phone:

Technologies using:
Tesseract is an optical character recognition engine for various operating systems. It is free software, released under the Apache License, Version 2.0, and development has been sponsored by Google since 2006. Tesseract is considered one of the most accurate open source OCR engines currently available.

OpenCV was built to provide a common infrastructure for computer vision applications and to accelerate the use of machine perception in the commercial products. Being a BSD-licensed product, OpenCV makes it easy for businesses to utilize and modify the code.
The library has more than 2500 optimized algorithms, which includes a comprehensive set of both classic and state-of-the-art computer vision and machine learning algorithms. These algorithms can be used to detect and recognize faces, identify objects, classify human actions in videos, track camera movements, track moving objects, extract 3D models of objects, produce 3D point clouds from stereo cameras, stitch images together to produce a high resolution image of an entire scene, find similar images from an image database, remove red eyes from images taken using flash, follow eye movements, recognize scenery and establish markers to overlay it with augmented reality, etc. OpenCV has more than 47 thousand people in their user community and an estimated number of downloads exceeding 7 million. The library is used extensively in companies, research groups and by governmental bodies.

[MrSea]

Leave the sample image link, I will tell you if It can be recognized using OpenCV.
Or suggest what should I do next?
*** Please do not dislike my video, I spend hours to make it for FREE ***

[jonusbrothers]

one doubt..please help


this is only working with normal images with black or white background and images having normal text font...
but, with images with different contrast and when font is not normal..like memes, etc..its giving wrong output..which no one can understand

[abhaysantra]

Is it possible to extract text like IFSC, date, pay, amount, name from bank check using this code?

[sahil]

OpenCV Error: Assertion failed (scn == 3 || scn == 4) in cv::cvtColor, file C:\build\master_winpack-bindings-win64-vc14-static\opencv\modules\imgproc\src\color.cpp, line


geting this error can u help

[rashmipandey]

No. For e.g I hv image which contains some text like roll number, subject like wise
How can I find specific text and draw bounding box

[ankitakulkarni]

can you please help? I am getting wrong output i.e texts are not displayed as they are in the image.

[MJFernandoIII]

please help me I got this error:
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

[thegunners]

I instaled tesseract-ocr but still get error: raise TesseractNotFoundError()
tesseract is not installed or it's not in your path
Python 3.7 64 bit, windows 7
Can you help? Thanks

[emilyhuang]

I am using a Windows so my src_path would have backward slashes. And this results in EOL error. Using the escape character does not work. How do I know the image object is a supported image object?

[riseupforrevival]

Traceback (most recent call last):
File "E:/opencv tutorial/car2.py", line 19, in <module>
print get_string(src_path + 'car1.jpg')
File "E:/opencv tutorial/car2.py", line 10, in get_string
kernel=np.ones((1, 1), np.unint8)
AttributeError: 'module' object has no attribute 'unint8'



HI, Iam getting this error can you please help me

[prathameshmule]

try to ocr the handwritten invoice see the confidence level of ocr or else try ocr invoice to extract particular data from invoice

[ArpitAJain-gbut]

Is it Possible to extract handwritten characters ? can you suggest which algorithm to choose for the same.

[TechTubic]

hey bro can i extract any language text ? from the image?

[reymarkgubat]

hello can you help me ? I have a problem in reading two columns because of ocr read straight

[ThePlayMakerClub]

How did you do digital screen display can i get that code please

[atharvajadhav]

can this be implemented to recognise number plates?

[ashasahrial]

Hi I have an error for this line " from resizeimage import resizeimage " from ehat package can I find this module ?
Thank you

[educationisyours]

Is there is any way to recogonize hand written notes and extracting data from them and classify them. i am searching for code. can u help me forward.

[wijatera]

I wanna ask with you.

Whether this method can be used for OCR that has a colored or pictorial background?

[similarsprachen]

hey, thanks much for the tutorial. I was just wondering if it´s possible to recognize marked/highlighted text only...?