The Active Segmentation platform for ImageJ (ASP/IJ) was developed in the scope of GSoC 2016 - 2019. The plugin provides a general-purpose environment that allows biologists and other domain experts to use transparently state-of-the-art techniques in machine learning to achieve excellent image segmentation and classification. ImageJ is a public domain Java image processing program extensively used in life and material sciences. The program was designed with an open architecture that provides extensibility via plugins.
The project idea: The existing machine learning model of Active Segmentation is based on the Weka library. However, this is limited to traditional machine learning approaches. The objective of the project will be to incorporate deep-learning functionality into the platform. Deep neural nets are capable of record-breaking accuracy.
The project is a continuation of GSOC 2020. The project will start from an already available codebase implemented using Deeplearning4j. At present, there are 2 implemented architectures U-Net — an architecture for biomedical image segmentation, and SegNet — a deep learning semantic segmentation architecture. The candidate will work out the GUI integration with the rest of the ASP/IJ platform.
Tasks:
Fix existing issues and bugs
Get familiar with Deeplearning4j
GUI implementation and integration of the Deeplearning4j functionality
Minimal set of deliverables:
Requirement specification - Prepared by the candidate after understanding the functionality.
System Design - Detailed plan for the development of the plugin and test cases.
Implementation and testing - Details of implementation and testing of the platform.
Hi ma’am,
I am Purva Chaudhari, third year undergraduate in Computer Science. I have worked on Object Oriented Python, c++,java, ML, DL, Tensorflow, Pytorch, and data science algorithms. (My introduction) . I am keenly interested in working on this project. Have the desired skill set and have done major projects in my curriculum in them.
Got an outline of the project from the summary and I have started going and learning through the references to get in depth idea about the project. Can you help me with moving forward in it. And are there any pre-requite tasks or contributions that I can make to be eligible to apply for GSOC 2021. Would be really helpful if you could guide me to move ahead in proper direction.
You can get familiar with ImageJ. Next, you can download and the current stable distribution of Active Segmentation and try some segmentation tasks.
Can you post links to samples of your work?
Hello mam,
I am Soyel Akter Habib first year student in cse.
By going through your project i just love the concept of the project and i would love to work on this if i may. My skills are:
∆ Java
∆ C
∆ C++
∆ Android beginner
∆ Unity beginner
∆ Python Beginner
Currently I am in first year but i am a tech enthusiasts and i love to work. But i dont know wheather i am eligible for this project or not as this project include machine learning and i didn’t have knowledge for this.
Hi @malin, I would like to contribute to this project. I am specialized in Java and deep learning and currently working on deep learning for text and images. I am currently working on capsule networks. Hope to apply that knowledge to this project. Thanks.
Please find the link of another project and shares some goals with this project. I would recommend student to have a look and can even apply for this project.