Over the course of time, it has become a very common activity digitize documents or writings who are previously in physical form. A clear example of this are the notes or notes that you have on paper
Do you know how to digitize your documents or writings?. Really many people are unaware about the subject, but the good news is that there are tools like google vision that allow you to do it easily. In this way, you will have at hand all the information you need in digital format.
In this post we will talk in depth about How to convert your notes and notes on paper to digital format with Google Vision?, through a useful step-by-step guide. In addition, we will explain what it is for.
What is Google Vision and what is this tool from the Internet giant for?
google vision it’s a image recognition system ideal for all developers who want to automate the analysis of the content of a large number of images. This tool has the ability to detect each of the elements present in the photographs, apart from knowing everything about all those that are in .
The Google Cloud Vision API It offers users different machine learning models with which to assign labels to images and quickly classify them into a wide number of previously defined categories. Consequently, it can detect objects and faces, as well as read printed and handwritten text.
When it comes to converting notes and notes to digital format, working with Google Vision is an excellent idea because it allows you to extract the text present in images to be able to digitize it, without the need to do it manually. In this sense, you can use it to extract text in images and also to detect and extract handwriting on . If you want to learn how to do it, you have to keep reading.
Learn step by step how to convert your notes and notes on paper to digital format with Google Vision
The procedure to convert your notes and notes on paper to digital format it is a bit long and you may find it complicated at first. But, once you become familiar with how it works, you will be able to get the most out of this tool.
Let’s see next:
Sign up for Google Cloud
The first step to enjoy any Google service is be registered. In this case, you must create your Google Cloud account In the following link “https://cloud.google.com” and then enter “Start free.” The next step to take is login with your namely, in your account . Choose the country and accept the terms of service.
Then set up your account with customer information, which includes:
- Account type (commercial or individual).
- Name and direction.
- Payment method (Credit or debit card).
when you come in Google Cloudyou must select in the option of “Create new project”. Once you do, it’s time to enable Google Vision API for your project.
Enable Google Vision API
For enable Google Vision APIclick on the menu located at the top left from the screen. There a list with the services it provides is displayed Google Cloud. You must go down in said list until you find the vision option. Likewise, we recommend you follow the link: “https://console.cloud.google.com/apis/api/vision.googleapis.com/overview” to enable the API corresponding to Google Vision. Later, click on “Enable API”.
When you have done that, you must proceed with the authentication, the procedure to follow is:
- go to menu top left.
- In IAM & Admintap on “Service Accounts”.
- click in “Create service account”.
- Fill in at least the required field of “Service Account Name”.
in the option of “Service Account Name” type the name you want for your project.
Create a key for credentials
Once the previous section has been configured, it is time to create a private key for credentials that are requested of you. To get it, you must go to list of service accounts (go to IAM and Admin/ Service Accounts). In there, create the key you want. Afterwards, you must download key as JSON.
Now it’s time to set the environment variable GOOGLE_APPLICATION_CREDENTIALS in the file path JSON containing the password for your service account. Note that this variable only applies to the current shell session. This means that if you open a new session, you have to set the variable again.
So, the way to do it is the following:
- On Linux or macOS: replaces PATH by the path of the JSON file that has the service account key. For example (export GOOGLE_APPLICATION_CREDENTIALS=”/home/user/Downloads/service-account-file.json”).
- On Windows: you have to replace PATH by file path JSON containing the password for your service account. For example with PowerShell ($env:GOOGLE_APPLICATION_CREDENTIALS=”C:\Users\username\Downloads\my-key.json”).
Installing the Google Cloud SDK
The Google Cloud SDKs is nothing more than a set of tools you can use to manage resources hosted on Google Cloud and the applications. All of this includes the command line tools of gcloud, gsutil and bq. Note that the gcloud command line tool is downloaded along with the SDKs of cloud.
Installation instructions depend on the computer you are accessing from:
- Download the Cloud SDK Installer. Similarly, you can open a terminal PowerShell and run the following commands:
- (New-Object Net.WebClient).DownloadFile(“https://dl.google.com/dl/cloudsdk/channels/rapid/GoogleCloudSDKInstaller.exe”, “$env:Temp\GoogleCloudSDKInstaller.exe”)
& $env:Temp\GoogleCloudSDKInstaller.exe - Start the installer and follow all the instructions. One thing you should know is that the Cloud SDK requires Python.
- The versions that are compatible are: those from 3.5 to 3.7, and 2.7.9 or later.
- Immediately afterwards, all the necessary dependencies will be installed, including the version of python correspondent. Although it is true that currently SDKs of clouds uses Python 3 By default, you can uncheck the option of “Install Python Package” to use an existing installation.
- When the installation is complete, it’s time to accept the installation options. Start the Cloud Shell SDK and of Run gcloud init. The installer will then launch a termination window and run the “gcloud init” command.
- Finally, the default installation does not include App Engine extensions necessary to be able to deploy an app with the gcloud commands. These components can be installed with the component manager of the SDKs of cloud.
Write the actual code
- The next step is write real code. But, before doing so, you have to install Node.js “https://nodejs.org/en/download”.
- Then you must create a folder:
- mkdir google vision
cd google vision /
npm init –yes - Import the Google Vision library:npm install @google-cloud/vision.
- Create the Node application entry point: Tap googlevision.js.
- In the same folder, add the photo that contains the text you want.
- If you want to make sure you’re on the right track, try get the plain text of your image by adding the following code in googlevision.js:
- const vision = require(‘@google -cloud/vision’);
async function app() {
constant client = new view.ImageAnnotatorClient();
const fileName=”pic2.jpg”;
const = await client.documentTextDetection(filename);
const fullTextAnnotation = result.fullTextAnnotation;
console.log(`Result: ${fullTextAnnotation.text}`);
}
app (); - When running it, you should get the following: googlevision.js node.
- Now you can start generating the HTML. To achieve this, you need to create a helper function (convertToHtml). You have to replace the console.log line in your application method with this: convertToHtml (fullTextAnnotation.text);.
- Below the apply() method, create the method:
- function convertToHtml(text) {
}
Finally, it is necessary that you take into consideration that, before generating the HTML, you must clean up the code generated by the Google Vision API. Once you’ve done that, you’ll have clean, digitized text. Undoubtedly, the use of a OCR library (optical character recognition) coupled with the creativity of the person, it can give amazing results. Go ahead and try and convert your notes and notes to digital format!.
Facebook Comments
Disqus