A new web-based galaxy classification tool using deep learning

Classifying galaxies is a key task in astronomy. A new automated galaxy classification method based on deep learning (AI) has been implemented by astronomers at UWA. In order for the new AI-based method to be used by other astronomers, a new web-based platform needs to be developed so that other astronomers can classify galaxies online automatically. In this project, students will develop a new web-based tool for astronomical image analysis (mainly galaxy classification) so that users can quickly analyze galaxy images through "drag and drop" online.

In this web-based platform, when users input a galaxy image, then the AI (i.e., python code using Keras/tensorflow) in the platform will automatically classify the image into a morphological category (e.g., spiral or elliptical galaxy) and show the result online. Therefore, the platform needs to be connected to a server where the classification task by AI can be done very quickly. Also, the input/output image transfer between the server and the web should be done quickly. Students will implement the python codes for AI-based galaxy image classification online. Other image analysis (e.g., super-resolution etc) will be implemented too.

Many images of galaxies can be found at https://apod.nasa.gov/apod/astropix.html .

Client


Contact: Kenji Bekki
Phone: 6488 7730
Email[email protected]
Preferred contact: Email
Location: Perth (UWA)

IP Exploitation Model


The IP exploitation model requested by the Client is: Creative Commons (open source) http://creativecommons.org.au/



Department of Computer Science & Software Engineering
The University of Western Australia
Last modified: 10 June 2020
Modified By: Michael Wise
UWA