Document image binarization method based on support vector machine

Abstract

The invention discloses a document image binarization method based on a support vector machine, comprising the following eight steps: color image graying, dividing a document image into blocks, improving the local contrast of image blocks, feature parameter extraction, SVM threshold classification, image block splicing, stroke width estimation, and local binarization. A color image is grayed using a minimum mean method, and the obtained gray image is of color independence. The defined local contrast not only can compensate for the influence generated by the change in image brightness, but also takes into consideration the normalized contribution of all the pixels in the neighborhood of the image to the local contrast of the image. Through use of an SVM threshold classification method, the accuracy and reliability are high. Stroke width estimation using a line-by-line scanning method is of high robustness to the resolution change of the document image. Through the method, character stroke details can be better retained, and phenomena such as ink infiltration, page stain, texture background and uneven illumination can be well suppressed while effective character foreground segmentation is achieved.

Description

technical field [0001] The invention belongs to the technical fields of digital image processing, pattern recognition and machine learning, and relates to a document image binarization method, in particular to a support vector machine (SVM)-based low-quality document image binarization method. Background technique [0002] Document Analysis and Recognition (DAR) technology has been widely used in printed characters and formula recognition, handwritten character recognition, document image segmentation, video subtitle extraction, text information retrieval and other fields, mainly including image acquisition, preprocessing, binarization, layout Analysis, character recognition, indexing, etc. Image binarization is one of the key processing steps, which directly affects the performance of the DAR system. However, binarization of such low-quality document images is extremely challenging due to factors such as image contrast, ink smearing, page stains, or uneven lighting. [00...

AI Technical Summary

Problems solved by technology

[0005] Researchers at home and abroad have also proposed many other methods, such as background estimation method, local contrast method, stroke edge detection method, gradient normalization and saliency map method, texture analysis method, Laplace energy method, error diffusion method, spectral Clustering methods and hybrid algorithms, etc., most of which have relatively high computational complexity, and cannot well solve the problem of binarization of low-quality document images affected by degradation factors such as ink infiltration, page stains, and background textures, or Can only be applied to some specific scenes (such as uneven lighting conditions)

Images