No account yet ?

In object detection using R-CNN, RPN is the only real backbone and has proven to be very effective so far.

Its purpose is to offer several identifiable objects within a particular image.

It is a very popular algorithm that has caught the attention of many data scientists, deep learning and artificial intelligence engineers.

RPN takes all anchor boxes as input, then generates the objectivity score for each box and performs regression to find a more accurate bounding box.

It is used in many object detection applications.