This paper attempts to explore the solving of Sudoku puzzles (as commonly found in newspapers and mobile games) using image processing, machine learning algorithms for OCR, and an efficient solving algorithm to compute the correct answer. We use various image processing techniques, such as Image Thresholding, Erosion and Dilation, etc. to convert a high-resolution and colored camera-generated image of the physical Sudoku puzzle into a format that can be digitally operated upon, in order to isolate the contents of the 9 × 9 puzzle grid correctly. We then use our custom Optical Character Reader (OCR), which is based on the k-NN machine learning algorithm, in order to correctly identify the digits contained in the grid and place them in the respective positions in a digital copy of the Sudoku grid, which is then processed by an efficient Sudoku solving algorithm, to compute the correct solution.

A Novel Automated Solver for Sudoku Images

An Image is a visual representation of any object, place, person etc. In the field of Computer Science a Digital Image is a numeric representation of a two-dimensional image. Often images may contain texts, which are a sequence of human-readable characters. Our general conundrum is extraction of texts from an image for processing and editing. In an image texts are defined by set of pixels just like any other object and thus cannot be processed or edited. In this work we have strived to develop a system which can extract texts from a digital image of a Sudoku puzzle, solve the puzzle, and then provide a solution. Our approach is specific but its application are varied.

Arunabha Ghosh

Papers

Development of a character recognition software to solve a Sudoku puzzle