What are the kinds of models Nanonets offers

Nanonets supports multiple types of Machine Learning models below is a list of the types of models we support.

Nanonets offers multiple kinds of models:

  1. Optical Character Recognition (OCR)
  2. Object Detection
  3. Image Classification
  4. Image Similarity


Optical Character Recognition (OCR)

Our OCR models are able to extract key pieces of information from Images and Documents and categorise them. As an example a model for Invoices can detect fields like Invoice Number, Buyer's Name, Buyer's Address etc. as well as the location of the field and the text. You can define your own fields that you would like to extract from a document.

Here is what the model looks like:


You can start building your OCR Model here

Image Classification

Our Image Classification models can tell what category an image belongs to. You can define your own categories and the model will bucket a given into one of those categories.

Here is what the model looks like:



You can start building your Classification Model here

Object Detection

Our Object Detection models can find an object of interest in an Image. You can define your own object of interest and given an new image we will find the object of interest.

Here is what the model looks like:

You can start building your Detection Model here

Image Similarity

Our Similarity models can find similar images from a given set of images it's already seen. When you give new image it will return the closest matching image it has already seen.

Here is what the model looks like:

You can start building your Similarity Model here

Was this article helpful?