Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and system for detecting definition of document image

A document image and detection method technology, applied in the field of image processing, can solve the problems of inability to evaluate document image definition, less image definition evaluation, and large information entropy, etc., achieve quantifiable data, reduce processing steps, and lower software and hardware requirements Effect

Pending Publication Date: 2022-03-25
南京商集智能科技有限公司 +1
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods are mainly aimed at the objective evaluation of the defocus blur of general images, while document images have significant texture features, and there are few evaluations for the clarity of such images. From the perspective of information entropy, the information entropy of blurred images may also be large. It may also be very small, and these methods cannot be directly used to evaluate the clarity of document images

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
  • Method and system for detecting definition of document image
  • Method and system for detecting definition of document image
  • Method and system for detecting definition of document image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] see figure 1 , a method for detecting the sharpness of a document image, comprising the following steps:

[0054] S1: Get the target document image. Such as figure 2 , the image collected by the camera device is generally an RGB three-color image, which contains a variety of color information. In this method, such color information is not needed.

[0055] S2: Perform grayscale processing on the target document image to obtain a grayscale target document image, such as image 3 shown.

[0056] S3: Binarize the grayscaled target document image to obtain a binarized target document image, such as Figure 4 As shown, binarization turns the grayscale image into a black and white image with grayscale values ​​of only 0 or 255. Intuitively, a document image is an image containing text information, such as various characters and numbers. It can be seen that the black pixels after the binary image of the document image are generally text information, and the clarity of these...

Embodiment 2

[0078] A document image sharpness detection system includes a memory and a processor, the memory stores instructions, and the instructions are adapted to be loaded by the processor and perform the following steps:

[0079] S1: Acquiring the target document image;

[0080] S2: Perform grayscale processing on the target document image to obtain a grayscale target document image;

[0081] S3: Perform binarization processing on the grayscaled target document image to obtain a binarized target document image;

[0082] S4: Perform the operation of calculating connected domains on the binarized target document image, divide the binarized target document image into mutually independent connected domains, and divide the records in the connected domains identified as black pixels is a character point, and those identified as white pixels are recorded as non-character points;

[0083] S5: Find a connected domain grayscale image corresponding to the connected domain and character points...

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 relates to a document image definition detection method and system, and the method comprises the steps: obtaining a target document image, carrying out the graying and binarization of the target document image, carrying out the connected domain calculation of a binarized image, obtaining mutually independent connected domains, and carrying out the detection of the definition of a document image according to the coordinates of each pixel of the binarized connected domain image. And obtaining a grayscale image and character points and non-character points corresponding to the connected domain. The method comprises the following steps: respectively carrying out gray value histogram statistics on character points and non-character points of a connected domain grey-scale map, calculating a data discrete proportion of the connected domain grey-scale map, judging whether a current connected domain is a clear connected domain or not according to a relationship between the data discrete proportion and a threshold value, and finally determining the definition of a current image according to a clear connected domain proportion. The definition detection method needs fewer image parameters, is simple and quick, and has low requirements on software and hardware of equipment.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and system for detecting the definition of document images. Background technique [0002] In daily life, it is often necessary to enter paper documents into the system, that is, to digitize documents, such as the electronic processing of ancient books in libraries, the recognition and entry of inspection sheets in hospitals, and the image recognition and entry of bills in financial systems. etc. Among them, the most important thing for the recognition result is whether the image is clear. The evaluation method of image clarity is not only an important link to measure the quality of digital images, but also the basis for realizing automatic focusing of digital imaging systems, and an important means of judging the imaging quality of a digital imaging device. [0003] Existing image sharpness evaluation methods are generally judged based on image edge gradient descent, ent...

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): G06T7/00G06T7/11G06T7/136G06V30/148G06V10/28G06V10/50
CPCG06T7/0002G06T7/11G06T7/136G06T2207/10004G06T2207/30168
Inventor 庄国金陈昊郝占龙吴胜杰黄文英方恒凯
Owner 南京商集智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com