Classify Through ESP Feature Collection

Grooper’s ESP engine finds the different features of each page in order to group images together as classified documents. ESP uses three key methods to find page features:


Natural language processing looks at the text of the complete document to understand context.

Lexical Classification image


Find unique key words or phrases that positively identify a document, like a title or section heading.

Rules-based document classification


Computer vision finds structured forms based on what they look like without having to read from OCR.

Computer vision-based document classification

How Machines Classify Documents Like Humans

Why is it so hard for machines to understand documents, and to classify them?

In this infographic, you will learn how Grooper overcomes the limits of machines to understand documents like humans, and why it does such a great job at classification tasks.

Download Grooper Infographic

What is ESP Separation?

Train document examples and see how the ESP separation engine interprets the content of each page. It then groups pages into documents, and simulates page breaking and classification.

Grooper page classification
  • First, a simple “train-by-example” interface lets you quickly teach ESP how to identify each document.
  • Next, real-time confidence scores show you both the document type and assumed page number for each page in a batch.
  • Finally, estimated Page Index (EPI) finds page numbers on your documents. This data is used by ESP to decide if an unknown page is likely part of a larger document.

Sit Back and Watch the Classification

Provide document examples and watch as Grooper learns the right document type for each one provided.

When batch testing, unclassified documents (those with low confidence scores) can be flagged and sent to a queue for someone to analyze and train further.

Grooper document classification

Photo Classification

You can also classify photos now through Grooper and the best AI cloud services. Leverage the Azure Cognitive Services Computer Vision API to return words (or tags) that describe the content of a photo.

These tags can be used to classify photos or photos in documents, or to add to metadata. Also, adult or racy content can be moved to a separate location if it is detected.

Image Classification Animation

Give it a Try

The Grooper Experience Will Change You

Imagine With Us