IBM Developer Day | Bengaluru | March 14th Register now
Get the code
By Scott D'Angelo | Published July 23, 2018
The Windows on Earth project features images taken by astronauts on the International Space Station. The image galleries include clouds, sunsets, farms, and various world cities at night. This code pattern combines the city images and Watson Visual Recognition to show you how to create a custom classifier that will identify various cities based on their images at night.
The International Space Station (ISS), launched in 1998, serves as a microgravity and space environment research laboratory in which crew members conduct experiments in biology, human biology, physics, astronomy, meteorology, and other fields. These experiments have produced copious amounts of data and experimental results, many of which are available to the public. The Windows on Earth project showcases images taken by astronauts for science research, education, and public outreach. This code pattern uses images of various cities at night to build a visual recognition custom classifier with IBM Watson Visual Recognition, demonstrating how you can use AI to categorize and organize the thousands of images taken from the ISS.
When you have completed this code pattern, you should understand how to:
Find the detailed steps for this pattern in the README. The steps show you how to:
Use computer vision, TensorFlow, and Keras for image classification and processing.
Artificial IntelligenceData Science+
Improve your neural network model by using some well-known machine learning techniques.
November 12, 2018
Back to top