Tibetan ancient book document image binarization method and system

Abstract

The invention relates to a Tibetan ancient book document image binarization method and system. The method comprises the following steps: acquiring a Tibetan ancient book document image, and carrying out binarization processing on the Tibetan ancient book document image to determine a preliminary binarization image; determining an estimated binary image according to the preliminary binary image, labeling the estimated binary image, and determining a Tibetan ancient book document image labeling image; training an improved U-Net network model by using the Tibetan and ancient book document image annotation graph and the Tibetan and ancient book document image to generate a trained U-Net network model, and storing network model parameters; and slicing a to-be-processed Tibetan and ancient book document image, amplifying the sliced Tibetan and ancient book document image and the to-be-processed Tibetan and ancient book document image, inputting the amplified Tibetan and ancient book document image and the to-be-processed Tibetan and ancient book document image into the trained U-Net network model, and determining a final binarization result image. According to the invention, the generation of false adhesion is effectively inhibited.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a binarization method and system for Tibetan ancient book document images. Background technique [0002] Existing image binarization methods can be divided into two categories. One is the global binarization method represented by the Otsu method. Its main idea is to determine a fixed threshold and divide the image into two parts, the background and the foreground. Because the variance is a measure of the uniformity of the gray distribution, the greater the inter-class variance between the background and the foreground, the greater the difference between the two parts that make up the image. When part of the foreground is wrongly divided into background or part of the background is wrongly divided into foreground will result in a smaller difference between the two parts. Therefore, the split that maximizes the between-class variance means the smallest probability of misclassifica...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method and system for binarizing Tibetan ancient book document images, so as to solve the problem that the existing binarization method based on full convolutional network is likely to cause false adhesion between strokes in the document image

Images