How to Extract Text from Images

Published in

NanoNets

4 min readApr 19, 2021

Originally published at https://nanonets.com on September 19, 2020, this article has been updated regularly.

Check out Nanonets’ free image to text OCR tool or read on to learn more about methods to extract text from images.

Extracting text from an image can be a cumbersome process. Most people just retype the text or data from the image; but this is both time-consuming and inefficient when you have a lot of images to deal with.

Image to text converters, often in-built as a sub-feature in image/document processing programs, offer a neat way to extract text from images. (Check out Nanonets’ free image to text and image to Excel tools)

Tools like Snagit & OneNote among others, leverage basic OCR (Optical Character Recognition) capabilities to extract text from images. While such tools do a good job, the extracted text/data is often presented in an unstructured manner that results in a lot of post processing effort.

An AI-driven OCR like Nanonets can extract text from images and present the extracted data in a neat, organized & structured manner. (What is OCR? — here’s a detailed explainer on OCR.)

Nanonets’ free online OCR allows you to extract text from images accurately, at scale, and in multiple languages.

Nanonets is the only text recognition OCR that presents extracted text in neatly structured & organized formats that are entirely customizable. Captured data can be presented as tables, line items, or any other format.

Find out why Nanonets is better than other OCR APIs.

Extracting text from an image using Nanonets

Here are three ways in which you can use Nanonets OCR to detect and extract text from images, parse PDFs, extract text from PDFs, extract data from websites or extract data from PDFs and other document types:

How to extract text from images using Nanonets pre-trained OCR models

Nanonets has pre-trained OCR models for the specific image types listed below. Each pre-trained OCR model is trained to accurately relate text in the image type to an appropriate field like name, address, date, expiry etc. and present the extracted text in a neat and organized manner.

Invoices
Receipts
Driver’s license (US)
Passports
Menu cards
Resumes
License plates
Meter readings
Shipping containers

Nanonets pre-trained OCR model in action

Step 1: Select an appropriate OCR model

Step 2: Add files

Step 3: Test

Step 4: Verify

Step 5: Export

How to extract text from images by building a custom Nanonets OCR model

Building a custom OCR model with Nanonets is easy. You can typically build, train and deploy a model for any image type, in any language, all in under 25 minutes (depending on the number of files used to train the model).

Watch the video below to follow the first 4 steps in this method:

Step 1: Create your own OCR model

Step 2: Upload training files/images

Step 3: Annotate text on the files/images

Step 4: Train the custom OCR model

Step 5: Test & verify data

How to train your own models for an OCR software or OCR application using Nanonets API

If you have an OCR software or application, here’s a detailed guide to train your own OCR models using the Nanonets API.

Step 1: Clone the Repo

git clone https://github.com/NanoNets/nanonets-ocr-sample-python cd nanonets-ocr-sample-python sudo pip install requests sudo pip install tqdm

Step 2: Get your free API Key

Get your free API Key from https://app.nanonets.com/#/keys

Step 3: Set the API key as an Environment Variable

export NANONETS_API_KEY=YOUR_API_KEY_GOES_HERE

Step 4: Create a New Model

python ./code/create-model.py

Note: This generates a MODEL_ID that you need for the next step

Step 5: Add Model Id as Environment Variable

export NANONETS_MODEL_ID=YOUR_MODEL_ID

Step 6: Upload the Training Data

Collect a dataset of training images from which you would like to recognize & extract text. Once you have dataset ready in the folder images (image files), start uploading the dataset.

python ./code/upload-training.py

Step 7: Train Model

Once the Images have been uploaded, begin training the Model

python ./code/train-model.py

Step 8: Get Model State

The model takes ~30 minutes to train. You will get an email once the model is trained. In the meanwhile you can check the state of the model

watch -n 100 python ./code/model-state.py

Step 9: Make Prediction

Once the model is trained. You can make predictions using the model

python ./code/prediction.py PATH_TO_YOUR_IMAGE.jpg

Originally published at https://nanonets.com on September 19, 2020.

Here’s a slide summarizing this article.