Region proposal layer for Faster R-CNN
A region proposal layer outputs bounding boxes around potential objects in an image as part of the region proposal network (RPN) within Faster R-CNN. These outputs are further refined by additional layers within Faster R-CNN to produce the final object detection results.
There are two inputs to this layer:
'scores' — The classification scores produced by the RPN
'boxDeltas' — The bounding box deltas produced by the RPN
Use the input names when connecting or disconnecting the region proposal layer to other
connectLayers (Deep Learning Toolbox) or
disconnectLayers (Deep Learning Toolbox)
(requires Deep Learning Toolbox™).
AnchorBoxes— Anchor boxes
Anchor boxes, specified as an M-by-2 matrix defining the [height width] of M anchor boxes.
Anchor boxes are predefined bounding box templates of fixed size. The size of each anchor box is typically determined based on a priori knowledge of the scale and aspect ratio of objects in the training dataset. An RPN network is trained to predict the translation and rescaling needed to align the anchor boxes with the ground truth bounding boxes. 
NumInputs— Number of inputs
Number of inputs of the layer. This layer has two inputs.
InputNames— Input names
Input names of the layer. This layer has two inputs, named
NumOutputs— Number of outputs
Number of outputs of the layer. This layer has a single output only.
OutputNames— Output names
Output names of the layer. This layer has a single output only.
Define three square anchor boxes for the region proposal layer.
anchorBoxes = [ 16 16 64 64 128 128 ];
Create a region proposal layer with the name
regionProposal = regionProposalLayer(anchorBoxes,'Name','region_proposal');
 Ren, S., K. He, R. Girshick, and J. Sun. "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks." Advances in Neural Information Processing Systems. Vol. 28, 2015.