Bayesian optimization-based image table character segmentation method

Abstract

The invention belongs to the image recognition field and relates to a Bayesian optimization-based image table character segmentation method. The method includes the following steps that: cells in an image table to be recognized are detected; information content in each cell is segmented out wholly; spare segmentation points of characters are found for character information in each cell through using a projection method; a Bayesian classifier is utilized to judge the spare segmentation points, so that accurate segmentation points of the character information can be found out; and segmented character sub images are classified. With the Bayesian optimization-based image table character segmentation method adopted, favorable conditions are created for the accurate recognition of the character information; the completeness and accuracy of single segmented characters can be ensured; the problem of difficulty in image table segmentation in the image and character recognition field which has been difficult to be solved can be solved. The Bayesian optimization-based image table character segmentation method has very high accuracy in image table character segmentation and has a bright application prospect in the image and character recognition, information mining and information analysis field.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to an image table text segmentation method based on Bayesian optimization. Background technique [0002] Image recognition technology is a very important development direction in the field of intelligent recognition technology. The development of image recognition has gone through three stages: character recognition, digital image processing and recognition, and object recognition. The recognition technology is particularly important because image text often contains more important usable information than simple images. Text recognition generally recognizes letters, numbers and symbols, and is widely used from printed text recognition to handwritten text recognition. The mathematical nature of the image recognition problem belongs to the mapping problem from pattern space to category space. At present, in the development of image recognition, there are mainly three recognition meth...

AI Technical Summary

Problems solved by technology

Due to the existence of the frame line of the table, it is not realistic to directly use the traditional projection method to achieve text segmentation and recognition.

At the same time, due to the complex and changeable structure of the form itself, the complex and changeable outline frame makes it difficult for the projection method to segment the text information of the form.

At the same time, due to the complexity of the text information in the picture text information (such as Chinese characters with left and right structures), when using the projection method for segmentation, the left and right structural components are easily divided into two independent parts due to the gap between them , which is not conducive to the accurate recognition of image text information. Facing the rapid analysis of a large number of image table data, a fast, complete and accurate image table text segmentation method is urgently needed

Images