A binarization method for low-quality document images based on background estimation and energy minimization

Abstract

The invention discloses a low-quality document image binarization method based on background estimation and energy minimization. First, grayscale preprocessing is performed on the color document image, and bilateral filtering is used to perform noise reduction processing on the image, image background estimation, and background reduction. Divide and enhance the image, construct the energy function, construct the network graph, and finally use the graph cut algorithm based on the augmented path to minimize the energy function. The invention significantly improves the binarization effect of document images under complex backgrounds, and can be applied to binary document images with complex backgrounds such as multi-color writing, stroke gradients, ink infiltration, stains or textures on the page, uneven lighting, low contrast, etc. chemical treatment.

Description

technical field [0001] The invention belongs to the technical fields of digital image processing, pattern recognition and machine learning, and in particular relates to a low-quality document image binarization method based on background estimation and energy minimization. Background technique [0002] Document Analysis and Recognition (DAR) technology has been widely used in the digitization of ancient books, layout analysis and text recognition, video subtitle extraction, text information retrieval and other fields, mainly including image acquisition, binarization, skew correction, character segmentation and recognition and other processes . Image binarization is one of the key preprocessing links, which converts grayscale images into binary images, so as to realize the separation of character foreground and document background. The effect of the binarization algorithm directly affects the performance of the entire DAR system, so many scholars have studied it in recent ye...

AI Technical Summary

Problems solved by technology

The effect of the binarization algorithm directly affects the performance of the entire DAR system, so many scholars have studied it in recent years and proposed many algorithms; however, it is affected by factors such as poor image contrast, ink infiltration, page stains, or uneven illumination. , binarizing low-quality document images remains a challenge

However, none of the above methods can well solve image binarization under complex document backgrounds such as low contrast, ink soaking, gradient lighting, smudges and textures.

Images