Object recognition

I represent my one of closed projects.
This projects is to study simple object recognition to use significant concept.

Here is the procedure to recognize object.

  1. Take informations (covariance matrix including average and variance of pixel) of a background.

  2. Take information of objects in front of the same background.

  3. Get Mahalanobis distance of the covariance matrix of the background

  4. Classify between background and object using SVD

  5. Reduce noise using blob coloring

  6. Get histogram of each classified informations

  7. Recognize object to use bhattacharyya coefficient

You can watch register three different objects and detect it.



that’s very different approach which i haven’t find it anywhere,well if you find time i request you to have a look over how i did object detection using tensorflow

thank you