Object detection is a computer vision technique that is used to identify and locate objects in an image. An image can be considered as a 2D array containing PPP rows and QQQ columns. Each element at position (i,j)(i, j)(i,j) in the image is called a ‘picture element’ or pixel. In this problem, we will only consider Grayscale Images, which means, each pixel can be described by a single value denoting the intensity (amount of light) of that pixel. Let’s denote a N×MN\times MN×M sub-image (where 1≤N≤P1\leq N \leq P1≤N≤P and 1≤M≤Q1 \leq M \leq Q1≤M≤Q) of the image to be a rectangle in the image containing NNN rows and MMM columns.

This is a companion discussion topic for the original entry at https://toph.co/p/object-detection