In this blog we will use AWS Textract to scan and extract the texts of a document from a picture and get a JSON output response. We will also use AWS lambda function with Node.js to build a backend.
1. Setting up Backend with Serverless using Node
Assuming you already know how serverless works, we can continue with AWS Textract and the flow it follows. If you're not familiar with serverless with node please don't jump the gun, go checkout some tuts here.
Okay. Let's quickly setup our serverless
sls create --template aws-nodejs --path myService
Make sure you have the dependencies in your package.json file as well. Then run
npm install
{
"name": "Document Scanner",
"version": "1.0.0",
"description": "",
"main": "handler.js",
"scripts": {
"test": "mocha src/test/**"
},
"author": "",
"license": "ISC",
"devDependencies": {
"aws-sdk": "^2.860.0",
"aws-sdk-mock": "^4.5.0",
"dirty-chai": "^2.0.1",
"generator-serverless-policy": "^2.0.0",
"mocha": "^8.3.1",
"serverless": "^1.43.0",
"serverless-iam-roles-per-function": "^1.0.4",
"serverless-mocha": "^1.12.0",
"serverless-mocha-plugin": "^1.12.0",
"serverless-pseudo-parameters": "^2.4.0",
"serverless-tag-api-gateway": "^1.0.0",
"standard": "^11.0.1"
},
"dependencies": {
"chai": "^4.3.3",
"fs-extra": "^9.1.0",
"serverless-secrets-plugin": "^0.1.0",
"sharp": "^0.27.2"
}
}
NOTE
Some things to keep in mind before continuing
- Make sure you have proper authorization for this task.
- Check your region.
- Make sure the bucket url is accurate.
2. Now once AWS SDK is configured, we can write code for Textract
'use strict';
const AWS = require('aws-sdk');
AWS.config.update({region:'YOUR_REGION'});
const textract = new AWS.Textract();
module.exports.textractAnalyinzer = async (event) => {
let { fileKey } = JSON.parse(event.body)
const ttparams = {
DocumentLocation: { S3Object: { Bucket: 'BUCKET_NAME', Name: fileKey } },
FeatureTypes: [
"TABLES" ,
// "FORMS"
],
};
const analysis = await textract.startDocumentAnalysis(ttparams).promise();
console.log(analysis);
const JobId = analysis.JobId
console.log('Waiting for processing');
let response = {};
do {
await sleep(1000);
response = await textract.getDocumentAnalysis({
JobId,
MaxResults : 1
}).promise();
//console.log(response.JobStatus)
} while (response.JobStatus=="IN_PROGRESS");
console.log(response);
let Blocks = [...response.Blocks];
do {
response = await textract.getDocumentAnalysis({
JobId,
NextToken : response.NextToken
}).promise();
Blocks = Blocks.concat(response.Blocks);
} while( response.NextToken );
# All Text By Line
let textByLine = purifyAnalyzedDataToAllLines(Blocks)
return {
statusCode: 200,
body: JSON.stringify(
{
message: 'Go Serverless v1.0! Your function executed successfully!',
"fileKey": document,
"textByLine": textByLine,
"texTractblocks" : blocks ## Full response from textract
},
null,
2
),
};
};
function sleep(ms) {
return new Promise(resolve => setTimeout(resolve, ms));
}
function purifyAnalyzedDataToAllLines(data) {
return data.filter(item => item.BlockType === "LINE")
}
The following code finds a file with the specific key in s3/public/** and then runs Textract analysis on it.
3. Deploy the Code
sls deploy
Find the endpoint, for me it looks like this
4. For our next step, we will drop a file manually on the bucket so we can use it for testing.
- Go to S3,
- the navigate to /public
- and then upload a img file
Im using this old receipt
5. Finally, Test it on post man.
payload:
"fileKey" : "public/demo.jpeg"
- If it gives you timeout error, change the function time out to 30s on .yml file.
- You can see the type of data we get back. For this demo I'm gonna take every line and add them together in an array.
Your response should look somethig like this
{
"fileKey": "public/demo.jpeg",
"textByLine": [
{
"line": "01/027 APPROVED - THANK YOU",
"confidence": 99.5232162475586
},
.
.
.
.
],
"texTractblocks": [
{
"BlockType": "PAGE",
"Geometry": {
"BoundingBox": {
"Width": 0.8844140768051147,
"Height": 0.8354079723358154,
"Left": 0.048781704157590866,
"Top": 0.15526676177978516
},
"Polygon": [
{
"X": 0.07131516188383102,
"Y": 0.1597394049167633
},
{
"X": 0.9331957697868347,
"Y": 0.15526676177978516
},
{
"X": 0.9245083928108215,
"Y": 0.9906747341156006
},
{
"X": 0.048781704157590866,
"Y": 0.9588059782981873
}
]
},
"Id": "9b384b8d-dcb8-4596-8511-af18659a9787",
"Relationships": [
{
"Type": "CHILD",
"Ids": [
"250a9339-d1ed-4c21-ad50-5a2154cd89da",
"aac798f2-3c05-41a2-979c-869509b53d58",
"eb878ad4-8b37-415d-b6ac-8cc909dab0a3",
"376c375f-94d1-47b7-9f4e-a9fb203043f2",
"628dbdd6-1225-43c9-867c-9a83ea91e1ae",
"aecacbf9-8727-4334-a904-6795df9c455b",
"c8e51b32-d010-4300-8e98-6002d6e5eee3",
"20e6422a-16c0-41b6-be2d-6c0c9d09ed44",
"82bfdb0d-20bd-407f-bc3b-33aef24fc097",
"aa3125fd-2e2d-48a5-9416-84ef7a987976",
"10ec162e-a937-4cd2-87d5-6d6b9205d719",
"b05a2ece-0a7f-4e65-87e5-fe4e49277f25",
"561f5c75-bbb4-4dc6-8660-fbc3f7386f9c",
"665bb6fe-8ac9-44b3-af49-189ac3ea7757",
"5d42a676-0621-42ad-89ff-7a16873290c4",
"bdb02d6e-3b80-4913-8359-ef7e70068582",
"28691f75-aef5-418d-8519-1d05bb991fda",
"8c4b9208-c2c5-4ad8-96a6-35e962043fbd"
]
}
]
},
.
.
.
}
That's it!
Next Step
Next week I will continue on with this app and build a front end for it using Flutter and AWS Amplify.
- We will setup AWS Amplify suing Flutter,
- Setup our camera to take pictures.
- Once that's done we will confirm and send the picture to the S3 store,
- Which will trigger our lambda function and send us the response back to our front-end.
Top comments (2)
Thanks for taking the time to read it (: