Study Of Nv Shu Character Image Segmentation And Skew Correction Algorithms Under Complex Background

Nv shu is the most gender-conscious language in the world, which is created and used only by women. Its italic writing system reflects women's collective wisdom at the cultural level. As the exclusive female language in the world, Nv shu is divided by gender, which neither belong to any nationality nor rely on any religion. Because the images of Nv shu have been saved for a long time, some of them are difficult to be extracted and separated because of the complex background. And the images tend to be inevitably skewing during scanning. Therefore, the two problems seriously affect the quality and the efficiency of the information processing.The thesis firstly discusses the common algorithms of image segmentation and tilt correction, analyzing the advantage and disadvantage of the algorithms in dealing with the images. Then it focuses on the classical algorithm called LLT algorithm, investigates the parameters involved in the algorithm, demonstrating the shortcomings of the algorithm.In order to deal with the problem of image segmentation of Nv shu character from the complex background, the thesis presents an revised method of the LLT altorithm. The revised algorithm extends the pixel points of the image edge so as to reduce the error caused by segmentation firstly. Then combined with the distribution of the image gray level in each area,this paper presents an algorithm of adaptive local threshold based on the characters of areas. Experiments indicate that compared with the original LLT altorithm and OTSU algorithm, the revised algorithm is better in noise elimination,with higher segmentation accurary and stronger adaptability in image segmentation.In order to deal with the skew Nv shu character images, the thesis put forward an algorithm called Improved Least Square Method based on Pixel. The algorithm not only takes account of the error value of the x-coordinate and y-coordinate, but also processes character adhesion, and improves the accuracy of correction. Experimental results show that the ILSMP algorithm is an effective model to the correction of skewing images such as Nv shu character images.