Areas of Expertise

  • Business Process Automation

Industries

  • Transportation

Technology Used

Challenge

Six Feet Up was approached by a major corporation in the transportation and moving industry to assist with the automation of PDF document processing. The goal was to move away from a time-consuming and ineffective manual process.

One of the key challenges to figure out consisted in correctly identifying and tagging documents with various states of quality as many were warped, blurry, upside down, and out of order. 

Implementation Details

Six Feet Up began with the review of a single type of document within a PDF bundle. Consistent page elements that occurred across multiple variations of the same document type were able to be identified.

For example, the team was able to leverage pre-processed QR codes on specific pages that were relatively dense of information and, when legible, contained enough data to identify document type and order. Six Feet Up successfully used Google Cloud Vision's powerful machine-learning models to process the QR codes. This was a low risk, high reward entry point into document identification.

Beyond QR code processing, Six Feet Up leveraged Optical Character Recognition (OCR) for document content categorization. Google Cloud Vision's OCR capabilities allowed for a comprehensive analysis of the documents. Six Feet Up was able to combine both the QR and OCR analysis along with custom coded Python scripts to generate a simple proof of concept application for quickly processing a large group of bundled documents. 

Results

Leveraging Google Cloud Vision for reading QR codes and document content, Six Feet Up was able to consistently grab one specific document type along with identifying information, so long as the document was in relatively good condition. Though there were a few outliers, a promising rate of return was achieved for this to be considered a successful first document pass.

Are you ready to start your next project?

Let's Talk