Document image binarization method based on stroke structural symmetry

A document image, symmetry technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of unclear printing, noise, etc., to achieve enhanced adaptability, strong local adaptability, and excellent binarization Effect
CN106203434AActive Publication Date: 2016-12-07INST OF AUTOMATION CHINESE ACAD OF SCI
5 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Current Assignee / Owner
INST OF AUTOMATION CHINESE ACAD OF SCI
Publication Date
2016-12-07

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a document image binarization method based on stroke structural symmetry. The method includes the following steps: determining the gradient image of a document image, wherein the document image is a grayscale image; utilizing the OTSU method to conduct global binarization processing on the gradient image; based on the width of character strokes and the regional gradient symmetry, removing non-stroke gradient noise of the image which undergoes the global binarization processing, and determining a gradient image being regional gradient symmetrical; based on the gradient image being regional gradient symmetrical, determining a structural symmetry element image; based on the local intensity of foreground elements of the structural symmetry element image, filtering noise, and conducting local binarization processing based on voting strategy in combination with the document image. According to the invention, the embodiments increase the adaptability of character extraction from document image.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The embodiment of the present invention relates to the technical fields of pattern recognition and optical character recognition, and specifically relates to a document image binarization method based on stroke structure symmetry, but is by no means limited thereto. Background technique

[0002] In recent years, with the rapid development of network technology, human beings have entered the information age. Traditional information acquisition methods, such as books, newspapers, and periodicals, are inconvenient to carry and require a lot of space for storage, which is not easy to edit and organize. and spread. People are more and more inclined to use electronic devices such as disks for storage. Therefore, it is of great significance to quickly input the text information of paper materials into the computer. OCR (Optical Character Recognition, Optical Character Recognition) technology was born from this. OCR technology can realize high-speed and aut...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More