Drawing a rectangle/bounding box on display and getting image bytes within it

Upon a voice command (e.g. "bounding box") or maybe a gesture, I want to create a bounding box around a portion of the HoloLens display. Perhaps this would require a gesture where I set the location and size of the rectangle. Then, I'd like to grab the bytes of the image contained within the rectangle - essentially crop the image. Can anyone point me to some good tutorials/code for this? I will report back on my progress.