Keras OCR - Reading Text from Images and Custom Models using Python

Подписаться 76 тыс.

Просмотров 46 тыс.

50% 1

#datascience #OCR #Keras
Optical character recognition or optical character reader (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo
In this video we will see how we can use Keras OCR to scan report and we will also see how we can extend it to build custom OCR models

Наука

Опубликовано:

20 авг 2020

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 105

@Behindthewheelwithsyed 4 года назад

Thank you for sharing. Everyday I am watching atleast a video from your library and great learning.

@AIEngineeringLife 4 года назад

Thanks Syed and glad if it is useful :)

@zaheerbeg4810 3 года назад

Srivatsan Sir Nice , Kindly keep it up

@yashdeepkumar2495 2 года назад

Hi srivatsan I have a doubt. How did you train the 'captcha.hdf5' model that you are using here

@hareshr1986 3 года назад

Thanks a lot bro Englightening Keep it going

@sharanbabu2001 4 года назад

Awesome as usual :)

@AIEngineeringLife 4 года назад

Thank you :)

@kusamuzukashi3825 2 года назад

cool tutorial bro, thanks for your good video

@talhayousuf4599 3 года назад

Thanks for this video, Can you please make a video to train custom detector and recognizer?

@viveksuresh7178 4 года назад

thank you Srivatsan - was trying to do something similar with EAST but was running into issues with multi oriented and arbitary shapes for text content , will try with CRAFT and see if this will give better result

@tanmaygupta638 3 года назад

have you tried? How was the result?

@nisarggandhewar8242 3 года назад

Its very nice video, thanks for sharing. Kindly prepare video to prepare Custom Models.

@AIEngineeringLife 3 года назад

Sure will do it 👍

@machinelearning9197 4 года назад

very helpful,, thank you for the video,one question--> going back and forth and seeing the bounding box is the only way to evaluate how accurate it is or there is any evaluation metrics for this pretrained CRNN. please post a video on how to train custom keras ocr model and to evaluate its performance

@AIEngineeringLife 4 года назад

CRNN metrics is typically per character precision or full sequence precision. This is close to how character error rate or word error rate works. For CRAFT bounding box can be a measure.. Yes on custom model

@siddarthbali12 3 года назад

Can u please make a video demonstrating, the method to train the recognizer on custom data images.

@AIEngineeringLife 3 года назад

I have it in plans and will do it in coming month

@santhoshmanoharan8969 3 года назад

@@AIEngineeringLife waiting for custom models recognizer training tutorial

@santhoshmanoharan8969 3 года назад

@@AIEngineeringLife waiting for that video

@abhilasht6471 3 года назад

@@AIEngineeringLife thank you for such a wonderful tutorial, could you please share video on how retrain on custom images

@shouryanagpal5813 Год назад

@@AIEngineeringLife sir please tell how to train the model , either provide some links or blogs or a video (best)

@fahadhassan8749 3 года назад

Hey Sir ! are there weights for handwritten recognition that we can use in Recognizer() method for handwritten recogntion ? please reply !

@AIEngineeringLife 3 года назад

Fahad.. Nope it cannot be used for handwritten test. Weights have to be fine tuned based on handwritten dataset for it to work

@hamzakhanniazaee224 3 года назад

Sir when i gave more than 10 imagea to keras.recognize() function. My session got crashed every time.

@hemantchauhan6437 4 месяца назад

NEED HELP! I am making a website where user can upload a pdf but I want that pdf to upload only if that pdf has images of only HANDWRITTEN text. Thank you for reading.

@abhinavraja650 3 года назад

I'm having trouble with importing the keras-ocr library, can someone help

@fredweb1997 3 года назад

Thanks for sharing. I think it is a very useful guide. just a question. I have to extract the text for a .pdf in the right order. I convert the single pages in image format (.jpg) and now I would like to obtain a proper .txt file in the same text order from the original. (something like pytesseract). is it possible?

@AIEngineeringLife 3 года назад

Yes you might be able to do it by customizing detector module to identify each line as single object

@user-pj3ku7jj5j 6 месяцев назад

@@AIEngineeringLife how to do that sir.

@tariqulislam7926 3 года назад

please send me the link that, how to train the custom model ?

@ouardafenek3765 3 года назад

Thanks a lot for sharing. May I ask how can I fine tune the model on custom data images please ? Thanks in advance.

@AIEngineeringLife 3 года назад

Have you seen this link - keras-ocr.readthedocs.io/en/latest/examples/fine_tuning_recognizer.html This shows how recognizer can be customized. Even the detector component can be done in similar way

@sainikhila1193 3 года назад

🙏🙏👌

@NaveenKumar-zo2rz 3 года назад

Hi Sir !! Great content. Can you help on how to train the model ?

@gauravranchi 3 года назад

I was trying to find a software like this which can translate doctors prescription...do you know where to find it or can you help me develop one .

@AIEngineeringLife 3 года назад

I am not sure such software exists but if you have lot of data and examples of it then you can label it and train using keras-ocr

@gauravranchi 3 года назад

@@AIEngineeringLife Yes I have data and example to label... please guide me how to... right from first step. Should I download keras ocr?

@rhiothelab5251 3 года назад

Eagerly waiting for HTR

@AIEngineeringLife 3 года назад

Yes Gaurav.. Have dataset but need to prepare it which might take time. Will try to get it done

@radhakrishnanrayaprolu 3 года назад

@@AIEngineeringLife use IAM offline dataset

@alsgusdl 3 года назад

Thank youfor sharing. but i can't find model weights='captcha'. how could I get captcha model?

@AIEngineeringLife 3 года назад

If you have installed it from my git repo i have modified version of keras-ocr. Else you can use this to download the captcha 'weights': { 'notop': { 'url': 'drive.google.com/uc?export=download&id=1drJ9rlIb6WtnW8ysoWU9kTp3TBAS-q6v', 'filename': 'captcha.hdf5', 'sha256': '701e0947beab802624ba562200da7b7684b87fd516a7d720c6a7453d0e3db805' },

@alsgusdl 3 года назад

@@AIEngineeringLife Thank you!

@ipvikas 4 года назад

Thanks a lot!!! Can you please make a seperate video for 'How to use "github", illustrating any End to End Data Science Project? Thanks a lot in Advance :)

@AIEngineeringLife 4 года назад

Sure Vikas.. I have a plan to start ML from scratch where I plan to cover git and best practices. This will be towards Nov this year

@binvantbajwa9101 3 года назад

Awesome tutorial! Is there any way to count the number of boxes created?

@AIEngineeringLife 3 года назад

Yes.. The pipeline recognize methods just gives a list of recognized objects with boxes. You can check length of list

@binvantbajwa9101 3 года назад

@@AIEngineeringLife If I use 3 images to perform ocr and then i use the len() function to find the length of the list on which I ran the pipeline.recognize method, it outputs 3 (the number of input images) instead of the number of bounding boxes. Any reason? As far as i know, number of boxes should have been the output. Please help

@ridhazaghdoud6208 Год назад

Hi sir thanks for this work,how to evaluate my model in order to display the iou score

@anuradhab1043 3 года назад

sir..I have a ledger image[which is a table] and want to extract the table into excel..can u please put a video reg the same

@AIEngineeringLife 3 года назад

Anuradha... Can you show me some sample.. It is very difficult to read table as it is but if some sample is there I can try it out

@paavanshah855 5 месяцев назад

Good tutorial. Is there a video on how to train custom model?

@atharvajadhav8598 3 года назад

Hello, first of all thank you for a great video. I wanted to know how did you custom train the recognizer model. I do want to train my own model based on custom dataset for number plates as inputs. I tried looking for fine tuning the model with dataset but I was confused with the dataset they have used. Kindly provide any link for the same. Reply from you will help me a lot.

@AIEngineeringLife 3 года назад

Atharva, Custom training is basically creating a tuple object with file name and ground truth. It is documented in keras-ocr git repo. I will try to make one video on it later this year

@atharvajadhav8598 3 года назад

@@AIEngineeringLife Thank you for replying. I will try doing the same. It would be very kind of you if you upload a tutorial, as a beginner into NN it would be a great help. Also I did see that you have forked and added the model file. I would like to do a similar thing since i have a dataset of number plates instead of captcha.

@AIEngineeringLife 3 года назад

@@atharvajadhav8598 Will do that early next year

@atharvajadhav8598 3 года назад

@@AIEngineeringLife thanks a lot, I'll be waiting for the same.

@althobhanialaa8268 3 года назад

@@AIEngineeringLife We still waiting for the tutorial, thanks a lot for your help

@shivampurbia6169 3 года назад

Sir any package for handwritten text ? For computer generated text I am using tesseract but for hand written I need you help .

@AIEngineeringLife 3 года назад

Have you tried Nephi.. You can search for Nephi crnn in github

@shouryanagpal5813 Год назад

hello sir can u provide the video in which you have trained the model with different captcha images , I am thinking a simillar thing for my final year project and I really want to train a model with different kind of images , Please help

@rishirajsinghrathorepgi19c56 Год назад

hey mate u got anything i am working on something same for final year

@Wanderlust1342 3 года назад

how can i print out the text that i have detected onto the console

@AIEngineeringLife 3 года назад

Prediction object is an array. You can print the text by iteration the array of text and printing 0 index

@mithunktmrc5934 3 года назад

Hello sir How can I contact u have some doubts to ask Thank you

@shreyaputhran7646 2 года назад

how to print the text as output. Pls help

@nsnilesh604 3 года назад

How to create that custom model sir

@abhishek_maity 3 года назад

Sir Please show us how to do the custom training for the handwritten text and use it in keras OCR or at least share some blog/resources to follow and achieve this please.

@AIEngineeringLife 3 года назад

Abhishek.. Currently I am focusing on Cloud and MLOps will get back to this one once I am done with that. But have you tried keras-ocr fine tuning that is mentioned in their document?

@abhishek_maity 3 года назад

Thanks Srinivasan sir for replying . I have not tried keras ocr fine tuning. but i wanted to explore offline ocr for handwritten texts. Because Google vision api is giving better results in hand written text. but wanted to explore more on offline ocrs. I also tried EasyOCR but its giving poor results on handwritten text.

@AIEngineeringLife 3 года назад

@@abhishek_maity Beating accuracy of Google API will be difficult as they have lot of data but have you checked this session on custom training handwritten OCR - ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-QnPZZb9D2Ss.html

@abhishek_maity 3 года назад

this seems to be very very helpful thanks a lot Srinivasan sir for sharing this .... I will now look this 😊

@nithinreddy2299 3 года назад

Can you please post the code link with your custom models, please?

@AIEngineeringLife 3 года назад

Nithin, Code link for the vieo is here - github.com/srivatsan88/RU-vidLI/blob/master/Keras_OCR_Demo.ipynb

@nithinreddy2299 3 года назад

@@AIEngineeringLife thankss

@nithinreddy2299 3 года назад

@@AIEngineeringLife and please make a video on how to train custom model. It will be great. Thank you man in advance.

@charud1874 29 дней назад

Where can I get the code

@muralir3551 3 года назад

Hai How to read text and formulas by capturing the image (Image contains text and formulas question paper with high accuracy

@AIEngineeringLife 3 года назад

Murali... Sorry I have never worked on that except for some research papers I have seen

@muralir3551 3 года назад

@@AIEngineeringLife Thank you for your reply

@nigamaveena4211 3 года назад

Please share your github repo of this project

@mridul6019 3 года назад

but how to get this output from here ???????

@AIEngineeringLife 3 года назад

Which output ?

@mridul6019 3 года назад

@@AIEngineeringLife like the text you get from caption will be the final output with most precision

@pycodesmachinelearning5096 4 года назад

amazing, thanks a lot for such kinds of quality videos. I have completed my be.tech CSE in 2020. I am from up. Tell me In which city, I apply for data science job or internship. and please tell me some companies name.

@bilel255b 3 года назад

hi, i got this erreur import keras_ocr OSError: [WinError 126] Le module spécifié est introuvable

@AIEngineeringLife 3 года назад

I think you did not install keras-ocr. Here is the step - !pip install git+github.com/srivatsan88/keras-ocr.git#egg=keras-ocr If you are not planning to use custom model then you can directly install from keras-ocr git

@bilel255b 3 года назад

@@AIEngineeringLife thank you

@AjitKumar-wm5cl 3 года назад

@@AIEngineeringLife I tried on windows it gives error keras_ocr the specified module could not be found. It works on colab

@mridul6019 3 года назад

you must share the git link of all codes you use in a video in description

@AIEngineeringLife 3 года назад

Mridul.. all codes is in my git repo. My channel homepage has link to repo or you can search for username srivatsan88 in git to get code I will try to update on future videos

@mridul6019 3 года назад

@@AIEngineeringLife thanks 😊

@arpanghosh3801 4 года назад

please share the github link for the code

@AIEngineeringLife 4 года назад

Here you go - github.com/srivatsan88/RU-vidLI/blob/master/Keras_OCR_Demo.ipynb

@RAJATSINGH-hk6xi 3 года назад

Thanku soo much ..can you please share this code link sir it will be helpful for me

@AIEngineeringLife 3 года назад

You can find all video codes in my repo here - github.com/srivatsan88/RU-vidLI

@devman1546 3 года назад

where is source code

@AIEngineeringLife 3 года назад

github.com/srivatsan88/RU-vidLI/blob/master/Keras_OCR_Demo.ipynb

@ntchindagiscard3870 3 месяца назад

I am just asking my selve what i really learned from this video ?

@AregGhazaryan 2 года назад

WOw you USe COLLaB? WoW Soo InforMAtiVE I can DO ThaT TooO. You MusST WorK At NaSA

@manuelcan Год назад

This video does not contain the subtitles that help people with disabilities to understand it. I request the author to complete this deficiency, improving his excellent work.Thank you