CogniSight engines

powered by NeuroMem NN Presentation


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


Parts, faces, silhouettes, etc.


People, cars, cells under a microscope, etc.


Wafer inspection, QC of printed materials, etc.


Our CogniSight SDKs let you deploy NeuroMem neural networks to learn and recognize your images and videos. You have a choice between our standard SDK or the ones specifically targeted for MatLab and LabVIEW.

Buy now

Our CogniPat SDKs are more generic and let you deploy NeuroMem neural networks to learn and recognize patterns extrcated from any data sources, including images.

Buy now

  • Identification
  • Classification
  • Novelty detection
  • Anomaly detection
  • Image contextual segmentation
  • Tracking with reinforced learning as the target changes
  • Stereoscopic distance evaluation
  • Edge detection
  • Noise removal
  • Image compression


Supervised training
  • From annotations made by domain experts on collection of reference images
  • From live interrupts triggered by an operator
Non supervision training
  • 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
Train multiple networks to make more robust decision
  • Experts can be trained to be redundant to minimize false positive
  • Experts can be trained to be complementary to waive uncertainties wisely
Multiplicity of outputs
  • List of identified objects (location, recognized categories, confidence levels)
  • Transform images (maps of categories and confidence)