PROJECT FILM / ZONGO MAQUTU
C++ image segmentation across thresholds
Compare a grayscale portrait with actual C++ segmentation outputs as the threshold rises from 32 to 224.
What the film shows
- The original grayscale specimen stays on the left.
- The right-hand image shows output from the C++ connected-components application.
- Increasing the threshold changes which pixels and connected regions remain.
Behind the demonstration
The input photograph is AI-generated. The segmentation images are actual C++ outputs. The project page includes more realistic specimens and a display-inversion control.
Built and documented by Zongo Maqutu. Read the Field Note for the implementation, architecture and limitations.