EnigmaScan: Streamlining Matrix Puzzle Solving through Image Recognition

3. Aditya Chaudhary, Student, Computer Science Engineering and Technology, Bennett University, Noida, Uttar Pradesh, India (E21CSEU0137@bennett.edu.in)

4. Aditya Mishra, Student, Computer Science Engineering and Technology, Bennett University, Noida, Uttar Pradesh, India (E21CSEU0140@bennett.edu.in)

5. Vaibhav Saini, Student, Computer Science Engineering and Technology, Bennett University, Noida, Uttar Pradesh, India (E21CSEU0106@bennett.edu.in)

6. * Shiv Naresh Shivhare, Assistant Professor, Computer Science Engineering and Technology, Bennett University, Noida, Uttar Pradesh, India (shiv827@gmail.com)

In an era increasingly shaped by technology, the enduring allure of word puzzles, such as word searches, crosswords, and Sudoku, remains steadfast. Yet, manually tackling these puzzles can prove to be a time-intensive and frequently exasperating endeavor. To meet this challenge, we suggest employing image recognition-based algorithms designed for puzzle-solving, specifically targeting Sudoku, word searches, and crossword puzzles. EnigmaScan is publicly accessible at https://github.com/theNewtonCode/EnigmaScan, allowing users to promptly solve their puzzles in real-time by uploading snapshots of unsolved Sudoku, word searches, or crosswords. This ground-breaking tool is designed to streamline and hasten the puzzle-solving process for users of all proficiency levels, thereby promoting a more enjoyable and accessible interaction with these timeless pastimes. The proposed algorithms exhibit remarkable efficiency, solving these puzzles within seconds and achieving an accuracy of 100%.

Keywords

Sudoku; Word Search; Crossword; Puzzle Solving; Dancing Links Algorithm; Optical Character Recognition

Berg, B., Høgskar, D., & Torbjørnsen, Ø. (2003). A fast parallel algorithm for solving sudoku puzzles. In Proceedings of the Fourth International Symposium on Artificial Intelligence and Mathematics.
Bradski, G., & Kaehler, A. (2000). Opencv: A general-purpose computer vision library. Dr. Dobb’s Journal of Software Tools, 25(11), 120-123.
Chen, H., Tsai, S.S., Schroth, G., Chen, D.M., Grzeszczuk, R., & Girod, B. (2011). Robust text detection in natural images with edge-enhanced maximally stable extremal regions. In 2011 18^th IEEE International Conference on Image Processing, 2609-2612. IEEE.
Colton, S., Bacardit, J., & Ross, P. (2007). An efficient and flexible algorithm for solving crossword puzzles. AI Communications, 20(3), 181-189.
Crawford, B., Castro, C., & Monfroy, E. (2009). Solving sudoku with constraint programming. In 20^th International Conference, MCDM 2009, Chengdu/ Jiuzhaigou, China, June 21-26, 2009. Proceedings (pp. 345-348). Springer.
Damas, F.B.V., & Oliveira, M.H.M.B. (2004). A survey of constraint programming techniques for the sudoku puzzle. In European Conference on Artificial Intelligence (pp. 735-739).
Haythorpe, M. (2016). Reducing the generalised sudoku problem to the hamiltonian cycle problem. AKCE International Journal of Graphs and Combinatorics, 13(3), 272-282.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385.
Hutchings, R.A., & Pothen, A. (2019). Solving large sudoku puzzles faster. arXiv preprint arXiv:1905.12965.
Jaderberg, M., Simonyan, K., & Zisserman, A. (2014). Reading scene text in deep convolutional sequences. In Proceedings of the International Conference on Learning Representations (ICLR).
Knuth, D.E. (2000). Dancing links. arXiv:cs.DS/0011047 v1.
Kusakari, K., & Hashimoto, J. (2010). Solving and rating large-scale sudoku problems via partitioning. In International Conference on Integration of Artificial Intelligence (AI) and Operations Research (OR) Techniques in Constraint Programming (pp. 297-310).
Littman, M.L., Keim, G.A., & Shazeer, N. (2002). A probabilistic approach to solving crossword puzzles. Artificial Intelligence, 134(1-2), 23-55.
Jam Soft LLC (n.d.): Asolver>let’s solve the puzzle. Retrieved from https://apps.apple.com/us/app/asolver-lets-solve-the-puzzle/id1505663005
Mishra, A., Alahari, K., & Jawahar, C.V. (2013). Robust text detection in natural images with edge-enhanced maximally stable extremal regions. arXiv preprint arXiv:1312.4894.
Nguyen, A.D., Do, T.T., Nguyen, T., & Cheung, N.M. (2017). Sudokuvision: Solving and explaining sudoku puzzles using vision. arXiv preprint arXiv:1704.03004.
Prosser, P. (1998). Solving crossword puzzles as a constraint satisfaction problem. In Proceedings of the European Conference on Artificial Intelligence (ECAI), (vol. 98, pp. 429-433).
Rosebrock, A. (2020): Opencv sudoku solver and ocr. Retrieved from https://pyimagesearch.com/2020/08/10/opencv-sudoku-solver-and-ocr
Shazeer, N.M., Littman, M.L., & Keim, G.A. (1999). Solving crossword puzzles as probabilistic constraint satisfaction. AAAI Press, Palo Alto: California USA.
Abto Software (2019). Computer vision powers automatic jigsaw puzzle solver. Retrieved from https://www.abtosoftware.com/blog/computer-vision-powers-automatic-jigsaw-puzzle-solver
Vezina, M. (2017). On project estimation or how long does it take to solve a sudoku. Retrieved from https://medium.com/@m_vezina/on-project-estimation-or-how-long-does-it-take-to-solve-a-sudoku-881dc41d341e