CogniSight engines

AI 4Vision powered by NeuroMem silicon neural networks


Pass/Fail, grade quality, locate defects, etc.


Locate people, measure cell density, detect obstacles, etc


Airplane, cars, people, cells under a microscope, etc.


Semi conductor inspection, QC of printed materials, etc


A CogniSight engine can be trained
  • Off-line on collected images and video
  • In real-time on live video
A CogniSight engine can learn under supervision
  • From annotations made by domain experts on collection of reference images
  • From live interrupts triggered by an operator
A CogniSight engine can learn no supervision
  • To re-inforce a knowledge getting less confident
  • To synchronize knowledge between stereoscopic engines
  • To build a dictionnary of viewlets describing reference images for compression or segmentation
  • To build a reactive image memory frame
A CogniSight engine can rely on single or multiple visual experts to made a decision
  • Experts can be trained to be redundant to minimize false positive
  • Experts can be trained to be complementary to waive uncertainties wisely