Extract Text from image OCR using Google Vision API in Python

In this video, I'll show you how you can extract text from images using Google Cloud Vision API's OCR (Optical Character Recognition) solution.

If you do have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer those.

If you enjoy these tutorials & would like to support them then the easiest way is to simply like the video & give it a thumbs up & also it's a huge help to share these videos with anyone who you think would find them useful.

Please consider clicking the SUBSCRIBE button to be notified for future videos & thank you all for watching.

You can find me on:

#OCR #GoogleVision

[manirathnam]

Instead of boxing the text in image. How to get output as text ?

[sachinkaushal]

Thank you so much Bhavesh Sir for this awesome support. this video really helpful.

[AnuRadha-fgry]

hi Bhavesh..I am not able to understand where u get the ENDPOINT URL from and in the Json file, I cant find any key named api_key..instead I find private_key...Iam getting stuck in that part..plz help

[VidyeshKumarJain]

how can we check the confident score of our ocr prediction

[souvikroy]

hello sir,
can you guide me on how to put text for the bounding boxes like what they have predicted and it displays with the bounding box...

[kapilchauhan]

Hey, Is it compulsory to enable billing to use it, as in India it is not accepting rupay card, so is there any alternative for this or there is any alternative APIs like this which doesn't require billing to access their services. Aws rekgnition also needs billing via visa which I don't have😭

[solitairegeek]

Please can you make video how to use it in android app? I have been looking for days but almost every tutorial is of python. I need a tutorial on how to do it using java, how to create box around the detected and most of all how to use OBJECT_LOCALIZATION feature in android

[abdulladmohammadsakib]

I am getting an error in finding the API key please help @Bhavesh

[dhirendrakumar]

Hi Bhavesh, you described it really well and in simple manner. I followed the steps but while calling the requestOCR(ENDPOINT_URL, api_key, img_loc), the result is showing error. Could you please suggest some checkpoints steps at the earliest.

[pavankumar]

Hi am trying to achieve the ocr functionality using custom cnn model but for few characters model is not able to detect properly for ex for 9 it is detecting 3 like that can you suggest any way to improve the cnn model or is there any other api which can be used to achieve this functionality, as Google vision needs some payment am looking for alternatives. Can you please provide your valuable suggestions

[gytry]

Team,

Please help how to download vision_api.json file from GCP i am try but not getting the download option.

[attamuhammad]

I am looking for OCR which could read blank spaces as well, can google vision api do this ?

[ishaquenizamani]

how can I use URL images for text detection plz help

[arsalanwasim]

how to filter weak detections from google vision api python

[MEDIATIPS]

can we do the translation with that also? I mean your hindi text is shown as english also.

[coderunner]

Sir please do this same thing for java .

[knbk]

Api key is not generated in json file. What to do now?

[aakashpatwa]

Hi I love your every video.. Please suggest an online course that will also provides Project and Placement too..

[PrakashDars]

Hi bhavesh do you do projects, i have requirement using ocr

[maverick]

Hey Bhavesh, in one of the hackathon I required ocr and I used easy ocr. But the images were so low resolution that the results were usually incorrect. How is the performance of Google's vision API? I mean till what resolution or level of blur does the API produce good results?