Abstract
Historical documents are important sources of information. With the information revolution and the advancement of science and technology, the digitalization of historical documents will change the protection, collection, transmission, and utilization of historical documents. However, historical documents often suffer from varying degrees of degradation, such as stains, creases, uneven illumination, and seepage of ink. Compared with the general image, the document image has many characteristics. For example, the background pixels are more concentrated than the foreground pixels, and the foreground and background pixels are relatively concentrated. Based on these problems and characteristics, this paper introduces three commonly used historical document image enhancement algorithms, and improves the Sauvola algorithm for a new historical document image enhancement algorithm that does not have to calculate a special threshold for each pixel, but uses the same threshold within a fixed area to reduce the cost of time while maintaining image quality. Experimental results prove that the improved algorithm can significantly reduce the time required while ensuring the quality of the image.