Packing List OCR
This article walks you through the building process of an OCR API that extracts data from Packing List forms using our deep learning engine.
- You’ll need a free beta account. Sign up and confirm your email to login.
- You’ll need at least 20 Packing List images or pdfs to train your OCR.
Define your Packing List use case
First, we’re going to define what fields we want to extract from your Packing List.
- Exporter: The name of the exporter
- Exporter address: The exporter's address
- Consignee: The consignee's name
- Consignee Address: The consignee's address where the package must be delivered
- Consignee Phone Number: The consignee's phone number
- Method of dispatch: how the package is carried (sea)
- Export Invoice Date: Issue date of the export invoice
- Export Invoice Number: Identification number of the export invoice
- Country of Origin: where the package comes from
- Country of Final Destination: the package final destination
- Total Weight: total weight of package carried
That’s it for our use case. Feel free to add any other relevant data to fit your requirements.
Deploy your API
Once you have defined the list of fields you want to extract, head over to the platform and press the ‘build a new endpoint’ button.
You land now on the setup page. Here is the image you can use for setting up the API, and my setup looks like this:
Once you’re ready, click on the “next step” button. We are going to specify the data types for each of the fields we want our API to extract.
To go further, you can download this json config to set up your data model or do it manually.
Exporter Name: type String that never contains numeric characters.
Exporter Address: type String without specifications.
Consignee Name: type String that never contains alpha characters.
Consignee Address: type String without specifications.
Consignee phone number: type Phone Number.
Method of Dispatch: type String that never contains alpha characters.
Export Invoice Date: type Date with US format.
Export Invoice Number: type Number without specifications
Country of Origin: type String that never contains numeric characters.
Country of Final Destination: type String that never contains numeric characters.
Total Weight: type Number without specifications.
Once you’re done setting up your data model, press the Data model ready? start training button at the top of the screen.
Train your Packing List OCR
You’re all set!
Now is the time to train your Packing List deep learning model in the Training section of our API.
In a few hours (minutes if you're fast), you’ll get your first model trained and will be able to use your custom OCR API for parsing Packing List in your application.
To get more information about the training phase, please refer to the getting started tutorial. If you have any questions regarding your use case, feel free to reach out!