Color text image binarization method and system based on image complexity

A technology of image complexity and text image, applied in the field of image processing, can solve the problems of failing to achieve the binarization effect, increasing the amount of calculation, and singleness

Inactive Publication Date: 2020-08-28
SHANDONG UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Clustering-based methods generally use color information to divide text block images into several categories, and then aggregate the clusters that meet the rules according to a certain clustering algorithm and a set threshold value. The text pixels correspond to one of the categories, and the rest of the categories as the background; but when the background contains components with the same or similar color as the text, this method will generate a large amount of residual background, which will affect OCR recognition
[0006] The method based on the statistical model establishes a probability model for all pixels in the text block, then sets reasonable parameters in the probability model, and determines whether each pixel belongs to the text pixel according to the maximum likelihood rule; but the model parameters in the probability model method generally require Statistical learning requires a large number of learning samples
[0007] In summary, the inventor believes that the above-mentioned various text image binarization methods do not consider the complexity of the image, and a single binarization method is used for both low-complexity images and high-complexity images; and for low-complexity images If the image adopts a complex method, the amount of calculation will be increased; for a complex image, a simple method will not achieve the desired binarization effect

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Color text image binarization method and system based on image complexity
  • Color text image binarization method and system based on image complexity
  • Color text image binarization method and system based on image complexity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Such as figure 1 As shown, this embodiment provides a color text image binarization method based on image complexity, which can be applied to image understanding, video content analysis, intelligent transportation, machine vision, intelligent control and other fields, specifically including:

[0030] S1: Extract color features and geometric features from the acquired color text image, calculate color complexity and geometric complexity respectively, and calculate image complexity according to color complexity and geometric complexity;

[0031] S2: Classify the color text image according to the complexity of the image, and perform binarization respectively to obtain an initial binarized image;

[0032] S3: After performing double filtering and polarity determination on the initial binarized image, the text area and the background area are obtained, and the binarized image is output.

[0033] In the step S1, the extracted color features include color category features an...

Embodiment 2

[0101] This embodiment provides a color text image binarization system based on image complexity, including:

[0102] The complexity calculation module is used to extract color features and geometric features from the acquired color text image, calculate color complexity and geometric complexity respectively, and calculate image complexity according to the color complexity and geometric complexity;

[0103]The binarization module is used to binarize the color text image according to the complexity of the image to obtain an initial binarized image;

[0104] The segmentation module is used to perform double filtering and polarity determination on the initial binary image to obtain the text area and the background area, and output the binary image.

[0105] It should be noted here that the above-mentioned modules correspond to steps S1 to S3 in Embodiment 1, and the examples and application scenarios implemented by the above-mentioned modules and corresponding steps are the same,...

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

PUM

No PUM Login to View More

Abstract

The invention discloses a color text image binarization method and system based on image complexity, and the color text image binarization method comprises the steps: extracting color features and geometric features of an obtained color text image, respectively calculating the color complexity and geometric complexity, and calculating the image complexity according to the color complexity and geometric complexity; classifying the color text images according to the image complexity, and performing binarization to obtain initial binarized images; and performing dual filtering and polarity judgment on the initial binary image to obtain a text region and a background region, and outputting the binary image. The color text image binarization method calculates the image complexity according to the color and geometric complexity of the color text image, classifies the images, adopts different binarization methods for the classified images, outputs a binarized image result after carrying out dual-filtering and polarity judgment on the binarized initial binarized image, considers the complexity degree of the images, and considers the binarization time and the binarization effect.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a color text image binarization method and system based on image complexity. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] The text information in the image or video plays a role in explaining and interpreting the image or video. Extracting and recognizing this text information is of great significance to image understanding, video content analysis, intelligent transportation, machine vision, intelligent control and other aspects. However, such text information is usually in a colorful and complicated background, and it is difficult for a general-purpose OCR system to recognize the text information. [0004] Existing binarization methods generally include threshold-based methods, cluster-based methods, and statistical learning-based...

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

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/34G06K9/46
CPCG06V30/413G06V10/267G06V10/56G06V30/10
Inventor李敏花柏猛吕英俊张恒毛文杰
OwnerSHANDONG UNIV OF SCI & TECH