Vector enhances OCR with text extraction for trucking documents

by Vector | Apr 27, 2020 12:00:00 AM

Vector enhances OCR with text extraction for trucking documents

April 27, 2020
Vector enhances OCR with text extraction for trucking documents

Let’s all admit, who likes paper? It’s a necessary evil in trucking. 

However, it is the most common form of communication because it is the easiest. Whether that paper is printed out and scanned back in or whether it is emailed in digital format, everyone understands paper.

However, systems don’t understand paper. And for many customers, they need to.

Some common use cases for customers include:

  • Documents that need to be indexed
  • Documents that need to be translated for downstream systems
  • Documents that need to be searchable and filterable

In order to do that, you need machines to be capable of recognizing text on paper, in a structured way, and extracting it into an accessible format to translate.

Paper now becomes like an API call. 

This is why Vector is excited to announce our new product line: Vector Text Extraction. Vector already provides OCR capabilities for searching as part of our standard document capture solution, now we are taking this one step further with structured text extraction.  

What is OCR?

Optical character recognition (OCR) software works with various scanners and/or image capturing solutions to convert characters into digital text, allowing us to search, edit or feed the information into other systems. Traditionally, OCR was limited to only recognize characters printed in pre-set font styles. Today, OCR is capable of recognizing individual, printed hand-written characters. 

Many of our customers benefit from this capability to pull information off of proof of deliveries, bill of ladings, trip sheets, and many more types of documents to search and filter documents in Vector. 

What is text extraction?

Text extraction automatically extracts text and data from scanned documents, going beyond optical character recognition (OCR) to also identify the contents of fields in forms and information stored in tables in a structured way.  OCR can recognize text within documents, but not where to extract the data.  

With Vector Text Extraction, customers can now create and edit their own templates and extract areas of text relative to the labels around it, into a structured field or set of fields. This approach greatly reduces the need to create multiple templates for every variation of text.  In addition, customers can then use Vector’s APIs to extract the information for conversion into whatever format they wish for whatever purpose they wish.

Vector Text Extraction

Text Extraction can be extremely useful in recognizing Rate Confirmations from your customers to transform into Orders in your TMS system.  You can create your own templates for the Rate Confirmations you receive, and then extract that data using Vector’s APIs to create downstream Orders, greatly accelerating what was previously a manual process and reducing costly errors. This is just one of many examples for how Text Extraction may benefit you.

We are excited to offer this as part of our early access program and encourage customers to reach out to your AE or CSM to be a part of this great initiative!

Subscribe Now

Additional Reading