Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for image type identification

A picture type, picture technology, applied in the field of social applications, can solve the problems of multi-traffic, slow loading of long text and pictures, large storage space, etc., to reduce the consumption of traffic, improve the probability of being read, and expand the effect of communication.

Active Publication Date: 2019-05-28
新浪技术(中国)有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of long picture takes up a lot of storage space, and viewing text and pictures on a mobile terminal in a non-WIFI environment will consume more traffic
In addition, the slow loading of long text images will also affect the user's reading experience

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 device for image type identification
  • Method and device for image type identification
  • Method and device for image type identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Embodiment one, figure 2 It is a flow chart of picture type identification shown according to an exemplary embodiment 1, see figure 2 , the process of picture type identification in this embodiment includes:

[0075] Step 201: Perform binarization on the released picture, and scan the binarized picture line by line, determine the sum of the row pixel values ​​of each row of pixels, and select the pixel row whose sum of row pixel values ​​in the picture is greater than the first preset value It is determined as a candidate text line, and all adjacent candidate text lines are connected to form a corresponding adjacent region of the candidate text line.

[0076] Similarly, the Otsu algorithm can be used to binarize the picture, the background pixel value is 0, and the foreground pixel value is 1. Then, the binarized picture is scanned line by line, and the pixel values ​​of each row of the binarized picture are respectively accumulated to obtain the sum of the row pixe...

Embodiment 2

[0091] Embodiment two, image 3 It is a flow chart of picture type identification shown according to a second exemplary embodiment. see image 3 , the process of picture type identification in this embodiment includes:

[0092] Step 301: Perform binarization on the released picture, and scan the binarized picture line by line, determine the sum of the row pixel values ​​of each row of pixels, and select the pixel rows whose sum of row pixel values ​​in the picture is greater than the first preset value It is determined as a candidate text line, and all adjacent candidate text lines are connected to form a corresponding adjacent region of the candidate text line.

[0093] Similarly, the Otsu algorithm can be used to binarize the picture, the background pixel value is 0, and the foreground pixel value is 1. Then, the binarized picture is scanned line by line, and the pixel values ​​of each row of the binarized picture are respectively accumulated to obtain the sum of the row ...

Embodiment 3

[0125] Embodiment three, Figure 5 It is a structural diagram of a device for identifying picture types according to an exemplary embodiment 3, see Figure 5 In this embodiment, the device includes: a scan processing unit 410 , a connection unit 420 , a determination unit 430 , and an identification unit 440 , and also includes a reminder unit 450 and a down-frequency processing unit 460 .

[0126] Specifically, the scan processing unit 410 performs binarization on the released picture, and scans the binarized picture row by row to determine the sum of row pixel values ​​of each row of pixels.

[0127]The connecting unit 450 determines a pixel row in the picture whose sum of row pixel values ​​is greater than a first preset value as a candidate text row, and connects all adjacent candidate text rows to form a corresponding candidate text row adjacent region. In this way, the determining unit 430 determines, according to the height of each candidate text line adjacent area, th...

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 method and a device for identifying a picture type, which are used to increase the transmission amount of information in the picture. The method includes: performing binarization on the released picture, and scanning the binarized picture row by row to determine the sum of row pixel values ​​of each row of pixels; making the sum of row pixel values ​​in the photo larger than a first preset value The pixel row is determined as a candidate text row, and all adjacent candidate text rows are connected to form a corresponding candidate text row adjacent region; according to the height of each of the candidate text row adjacent regions, the height is first The adjacent regions of candidate text lines within the preset range are determined as adjacent regions of valid text lines; if the height of the adjacent regions of effective text lines satisfies the set condition, the picture is identified as a long text image. In this way, the user can be reminded to determine the way to publish information according to the type of information, so as to reduce the consumption of traffic, increase the probability of the published content being read, and further expand the dissemination of information.

Description

technical field [0001] The present invention relates to the technical field of social applications, in particular to a method and device for identifying picture types. Background technique [0002] With the development of Internet technology, some social applications are increasingly widely used. Users can publish some articles, such as blog posts, comments, etc., through social applications. The dissemination of these articles through the Internet can enable more users to obtain the required information. [0003] Among them, when a user publishes an article with a lot of text through a social application, it will be converted into a corresponding image for publication. For example, when a user publishes a blog post with a lot of text, he usually writes a long article with a long Weibo tool, and then generates a text Long pictures to publish content. Such long pictures take up a lot of storage space, and viewing text pictures on mobile terminals in a non-WIFI environment ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V30/40G06V10/56G06V10/758
Inventor 刘洁
Owner 新浪技术(中国)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com