Show Tag: object-recognition

Select Other Tags

Viola and Jones presented a fast and robust object detection system based on

  1. a computationally fast way to extract features from images,
  2. the AdaBoost machine learning algorithm,
  3. cascades of weak classifiers with increasing complexities.

Greene and Fei-Fei show in a Stroop-like task that scene categorization is automatic and obligatory for simple (`entry-level') categories but not for more complex categories.

The complexity of features (or combinations of features) neurons in the ventral pathway react to increases to object level. Most neurons react to feature combinations which are below object level, however.