In the last post we discussed how to extract the *sudoku* region from the captured frame of a live stream and then we applied *perspective transform* to the extracted region and then we *slide* a window through each cell and *recognized* the digits in the cells. Now in this post we discuss how to **solve** the *sudoku* puzzle using Backtracking algorithm. There are several approaches to solve the sudoku puzzle. For example, you can find some of them in this paper.

Though there are several approaches to solve it, let’s stick to the traditional *backtracking* algorithm to solve the puzzle. For our understanding, just have a look at how the *sudoku* is presented below.