RCNN

Photo by Avi Theret on Unsplash

From a high level:

• It takes an input image.
• Apply selective search on it and get region proposals.
• Pass them into CNN architecture (for feature extraction).
• The SVM is used for classification.

Details:

• It uses selective serach to get search 2000 region proposals.
• It uses SVM for classificaion and non-max supression.
• linear regression to get bounding boxes
• The regions are wrapped into the input shape of alexnet (used to extract features).

Architecture:

HIgh level architecture

It uses the concepts we talked about above.

Con’s:

• Extracting 2000 region proposals is hard, and after that if we pass them into cnn then we have a bottle neck.
• Extracting feature for every region proposal
• Takes 40–50 seconds for prediction.