Camera-based Sudoku recognition with deep belief network

In this paper, we propose a method to detect and recognize a Sudoku puzzle on images taken from a mobile camera. The lines of the grid are detected with a Hough transform. The grid is then recomposed from the lines. The digits position are extracted from the grid and finally, each character is recognized using a Deep Belief Network (DBN). To test our implementation, we collected and made public a dataset of Sudoku images coming from cell phones. Our method proved successful on our dataset, achieving 87.5% of correct detection on the testing set. Only 0.37% of the cells were incorrectly guessed. The algorithm is capable of handling some alterations of the images, often present on phone-based images, such as distortion, perspective, shadows, illumination gradients or scaling. On average, our solution is able to produce a result from a Sudoku in less than 100ms.

[1]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[2]  J. Shewchuk.  An Introduction to the Conjugate Gradient Method Without the Agonizing Pain , 1994 .

[3]  S. Impedovo,et al.  Optical Character Recognition - a Survey , 1991, Int. J. Pattern Recognit. Artif. Intell..

[4]  Keiichi Abe,et al.  Topological structural analysis of digitized binary images by border following , 1985, Comput. Vis. Graph. Image Process..

[5]  Jean Hennebert,et al.  Content-Based Image Retrieval with LIRe and SURF on a Smartphone-Based Product Image Database , 2014, MCPR.

[6]  P. J. Simha,et al.  Recognition of numbers and position using image processing techniques for solving Sudoku Puzzles , 2012, IEEE-International Conference On Advances In Engineering, Science And Management (ICAESM -2012).

[7]  Jiri Matas,et al.  Robust Detection of Lines Using the Progressive Probabilistic Hough Transform , 2000, Comput. Vis. Image Underst..

[8]  C. M. Reeves,et al.  Function minimization by conjugate gradients , 1964, Comput. J..

[9]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[10]  David S. Doermann,et al.  Camera-based analysis of text and documents: a survey , 2005, International Journal of Document Analysis and Recognition (IJDAR).

[11]  Marc'Aurelio Ranzato,et al.  Sparse Feature Learning for Deep Belief Networks , 2007, NIPS.

[12]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.

[14]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[15]  Quoc V. Le,et al.  On optimization methods for deep learning , 2011, ICML.