Development of a character recognition software to solve a Sudoku puzzle

Abstract: 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.

Abstract: The Tesseract OCR engine, as was the HP Research Prototype in the UNLV Fourth Annual Test of OCR Accuracy, is described in a comprehensive overview. Emphasis is placed on aspects that are novel or at least unusual in an OCR engine, including in particular the line finding, features/classification methods, and the adaptive classifier.

Abstract: A new hybrid page layout analysis algorithm is proposed, which uses bottom-up methods to form an initial data-type hypothesis and locate the tab-stops that were used when the page was formatted. The detected tab-stops, are used to deduce the column layout of the page. The column layout is then applied in a top-down manner to impose structure and reading-order on the detected regions. The complete C++ source code implementation is available as part of the Tesseract open source OCR engine at http://code.google.com/p/tesseract-ocr.

Abstract: Almost all the current commercial OCR machines employ matrix matching, resulting in high speed and accuracy, but a severely restrictive range of recognized fonts. Published algorithms conversely, concentrate on feature extraction for font independence, yet they have previously been too slow for commercial use. Current algorithms also fail to distinguish between text and non-text images. This thesis presents a new approach to the automatic extraction of text from multimedia printed documents. An edge detection algorithm, which is capable of extracting the outlines of text from a grey level image, is used to obtain a high level of discrimination between text and non-text. An additional benefit is that text of any colour can be read from almost any background, provided that the contrast is reasonable. The outlines are approximated by polygons using a fast two-stage algorithm. A feature extraction approach to font independent character recognition is described, which uses these outline polygons. It is shown that highly accurate and fast recognition can be achieved using a remarkably small number of carefully chosen features. The results show that after training on only seven quite similar fonts, the recognition algorithm provides greater than 95% accuracy on fonts different to the training set. A more complex edge extraction algorithm is also described. This is capable of extracting text and line graphics from an arbitrary page. Although not essential for character recognition, this algorithm is useful for the interpretation of engineering drawings. As a further contribution to this problem, a thinning algorithm is defined, which is non-iterative and uses the polygonal approximated outlines from the edge extractor.