What is Zegami?

Zegami is an easy to use visual data exploration tool for viewing large collections of images.  The solution allows for the inclusion of associated meta data (structured and unstructured) from multiple sources to provide a single true view.  This easy to use solution presents image rich data in a way that makes it easily accessible to everyone.

By presenting vast quantities of images within a single field of view, Zegami allows users to search, sort, filter and group information which allows quick identification of patterns, correlations, outliers and relationships within the data. Zegami’s plugin API allows developers to create their own visualisations.

Zegami has been built as a platform to allow it to integrate with a wide variety of data and image sources. Out of the box flat files and most relational data bases are supported, however other data sources can also be supported by leveraging Zegami’s API’s.  This ability to connect to a variety of data sources and generate collections which can be viewer within a browser makes Zegami a natural platform for publishing data.

What problem does Zegami Solve?

Everyday we generate billions of images each containing unique information. Zegami is a powerful solution that presents image rich data in a way that makes it easily accessible to everyone.

Zegami allows users to combine images and their associated data from various sources and provides the means to search, sort, filter and group them in a meaningful and dynamic way.

On the surface Zegami looks interesting, however it seems that it’s not until you have your own images within the solution does the true value of the solution become evident.

Zegami allows you to rapidly survey all images in your data set through our easy to use web interface Zegami allows you to:

  • Identify anomalies in your data set quicklyCombine images, categorical and numerical data to allow rapid querying and integration of disparate data
  • Tag interesting images for further analysis or remove poor quality of outliers from your data set
  • Use scatterplots and boxplots or your own plugins to allow anyone to analyse their image collections based on extracted image features
  • Quickly collate images using our unique lasso and tag feature to build training sets for machine learning
  • Publish your results easily on the web

Who uses Zegami?

Image and data management is a growing requirement in research, academia and all commercial endeavours. While there is no limit to where Zegami can be applied, there are several notable industries where the platform has made significant contributions. These include Heating, ventilation and air conditioning (HVAC) management, Microscopy, Genomics, Plant Phenotyping Digital and Cultural Heritage Galleries, Libraries, Archives, and Museums, Human resources, competitive analysis.

How do organisations use Zegami?

New ways to incorporate Zegami in companies, museums and research institutions are being discovered constantly. As our clients use the platform for visualising and analysing data, they can drill deeper into the data presented. Zegami enables people to ask questions of their data that they did not know they needed to ask, as a result.

How do you process and create collections?

Zegami supports multiple data sources. Out of the box it comes with support for flat files (like CSV and TSV) and ODBC. Zegami has a plugin API for data and image sources, which means that any type of data source can be implemented.

A tab delimited file is the simplest data structure, the only requirement is that the first row contains the headers.

What is Zegami’s Pricing Structure?

The Zegami pricing model is charged out at a per user licensing model and ensures that our customers benefit from the enhanced features released as version updates.

There are two basic cost structures one for commercial and a second for academic and non-profit organisations. For the pricing structure for your organisation, please contact the Zegami team who will be able to help you get started.

How is Zegami hosted?

It can be hosted on your own hardware and be completely hosted within a private network. It does require access to the internet for installation/updates and error logging.

A fully outsourced cloud version is due for release in Q2 2018.

How does Zegami receive data?

As mentioned Zegami can retrieve data from any type of data source. Image are typically located on the file system or file share. The images are processed and stored in a local cache, this cache needs to have enough space to store the processed collections (dependant on source file sizes).  Zegami uses MongoDB to store collection information and snapshots.

Multiple data sources are not yet supported via the user interface, however this could be done with an SQL query or SSIS package.

Any ‘back of house’ components not visible in the publicly-consumable app.

Zegami has a web based user interface for creating and managing collections. This includes user management and security. Our support site has some documentation on its functionality – https://support.zegami.com/

We have various authentication plugins including LDAP.

What are Zegami’s Deployment technologies?

Zegami is written in Python and can be deployed on either Linux or Windows. It also requires MongoDB.

Does Zegami allow you to create multiple data sets or collections?

The management portal supports creating multiple collections, depending on the software licence you have will determine the number, size and accessibility of your collections.

See how Zegami works