Non-max suppression

Imagine a scenario where multiple region proposals are generated and significantly overlap one another. Essentially, all the predicted bounding-box coordinates (offsets to region proposals) significantly overlap one another. For example, let’s consider the following image, where multiple region proposals are generated for the person in the image:

Figure 7.8: Image and the possible bounding boxes

How do we identify the box, among the many region proposals, that we will consider as the one containing an object and the boxes that we will discard? Non-max suppression comes in handy in such a scenario. Let’s unpack that term.

Non-max refers to the boxes that don’t have the highest probability of containing an object, and suppression refers to us discarding those boxes. In non-max suppression, we identify the bounding box that has the highest probability of containing the object and discard all the other bounding boxes that have...