Axis Transformation Object Recognition

BAI Axis Transformation Object Recognition technology includes the following features


  • High level Rotation Invariance (± 45° minimum all axes)
  • High level Translation and Scale Invariance (only limited by image resolution)
  • High level Lighting Invariance (intensity, saturation, and hue)
  • High level Occlusion Invariance
  • Supports 2D data (image data only)
  • Supports 3D data (requires parallax or laser generated distance information)
  • Accepts image data in all formats
  • Operating system independent development - ISO C++ (currently available on Linux EL5/EL6/EL7/EL8/UB14/UB16/UB20 and Microsoft Windows XP/7/8/10)
  • Conforms to WIPO 2011/088497

For information regarding BAI object recognition technology, please view the Introduction to Optimised Geometric Hashing. This technology is not currently being maintained and it is recommended to use a modern vectorised and hardware accelerated implementation (e.g. TensorFlow/PyTorch).

Technology Name Support Source License Source Documentation
Axis Transformation Object Recognition (ATOR) LinuxRed Hat LinuxUbuntu LinuxWin AGPLv3 (view source online) Auto Documentation