Hi <<Full Name>>,

The BigML Team is thrilled to release Image Processing! The new and greatly enhanced version of the BigML platform allows you to generate valuable business insights from your image data with as little as a few clicks: No coding is necessary!

With BigML Image Processing, you can easily label your image data, train and evaluate supervised and unsupervised models, make predictions, and automate end-to-end Machine Learning workflows: All on a single platform.

Yesterday, we presented the details of this milestone release in a live webinar. You can watch it at your leisure by clicking on the video recording below. The video recording is also available on BigML's Youtube Channel. 
 

Real-world Image Processing applications can deliver great business outcomes by reducing costs and increasing profits in many industries, and BigML's unique implementation can get you there faster thanks to the differentiating features explained below.

Because BigML treats images as any other data type, you can easily use image data alongside text, categorical, numeric, date-time, and items data types as input to create any Machine Learning model available in our platform, both supervised and unsupervised. No need to spend countless hours mastering new libraries or installing various plug-ins.

BigML lets you solve a wide variety of computer vision and image classification and regression problems, including use cases in medical image analysis, visual product search, security surveillance, and vehicle damage detection, among many other industries. All in a single platform with remarkable ease of use!

A composite source supports multiple data types including individual images. Composite sources save time and prevent errors because users can incrementally add more data to them and use the built-in image labeling while preserving immutability along the way.

Through multiple feature extraction configuration options, BigML gives you fine control over what the algorithm “sees” in your image data. As part of pre-processing, a collection of images are automatically transformed into rows of tabular data that any model type can handle with ease. 

BigML allows the user to pick from five different pre-trained Convolutional Neural Nets to build better models faster by leveraging Transfer Learning. These pre-trained models are based on industry-standard datasets containing millions of images and thousands of classes.

Here are some useful resources to the material covered during the webinar:
 

We hope to see you again at future webinar releases and other BigML events!