GSOC 2026 Project #25 : ImageJ Active Segmentation platform: Parallel Engine for ASP/IJ

The Active Segmentation platform for ImageJ (ASP/IJ)[2] was developed in the scope of GSOC 2016 - 2025. 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 [1] is a public-domain Java image processing program extensively used in life and material sciences. Recent years have experienced explosive development in the GPU-accelerated computing. The project will explore the existing parallel filtering framework and extend it towards TornadoVM framework [4]. TornadoVM is an open-source software technology that automatically accelerates Java programs on multi-core CPUs, GPUs, and FPGAs.

The project will explore some of established Java-based GPU computing frameworks [4,5,6,7] and port the convolution engine used by the ASP/IJ to parallel implementation.

The project idea: The project will extend the convolution engine used by the ASP/IJ to the TornadoVM framework.

Tasks

• Fix existing issues and bugs

• GPU computing frameworks evaluation and testing

• Implementation and profiling of selected convolution filters

Minimal set of deliverables

• Requirement specification – Prepared by the candidate after understanding the functionality.

• System Design – Detailed plan for development of the plugin and test cases.

• Implementation and testing – Details of implementation and testing of the platform.

Desired skills: Java, Machine learning

Mentors: Dimiter Prodanov (dimiterpp@gmail.com) IICT-BAS; Teodor Minev IICT -BAS (teodorminev98@gmail.com); Rikas Ilamdeen (rikasilamdeen@gmail.com)

References

  1. ImageJ: https://imagej.nih.gov/

  2. Active Segmentation: GitHub - sumit3203/ACTIVESEGMENTATION: Active Segmentation Project · GitHub

  3. Eclipse IDE https://www.eclipse.org/

  4. TornadoVM https://www.tornadovm.org/