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

Emoticons screen method

A screening method and emoticon package technology, applied in the field of image recognition based on deep learning, to reduce costs, facilitate classification and use, and increase work efficiency.

Inactive Publication Date: 2019-01-04
上海宝尊电子商务有限公司
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is no report on a screening method that can identify facial expressions and non-human facial expressions for emoticons and classify them.

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
  • Emoticons screen method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The specific embodiments provided by the present invention will be described in detail below in conjunction with the accompanying drawings.

[0030] The reference signs and components involved in the accompanying drawings are as follows:

[0031] Please refer to figure 1 , figure 1 It is a flow chart of an emoticon bag screening method of the present invention. The process 1 is to acquire the salient area of ​​the input target image after receiving the screening request for the target image. The salient area is the area in the image that can arouse the most interest and express the content of the image. Computer algorithms can calculate the visual features and information-intensive areas in the image by simulating the human attention mechanism to select areas that are more in line with human subjective evaluation.

[0032] The process 2 is to perform image algorithm preprocessing on the salient area. Since the input image is subject to conditional constraints and r...

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 an expression pack screening method, which comprises the following steps of: 1,obtaining a significant area of an input target image; 2, preprocessing the salient region imagealgorithm; 3, extracting picture features and text information; 4, matching the picture features and text information through a pre-designed classifier; 5, judging whether that input picture is an emoji or not by calculate a matching probability; 6, marking images that have been identified as emoticons. The invention has the advantages that the picture information is classified by using a plurality of algorithms, the number of recognized pictures per second is far more than that of manual operation, the input picture can be judged whether it is an emoji pack or not efficiently, and the multi-dimensional marked emoji pack can be conveniently used for subsequent classification, the cost of manual recognition is reduced, and the work efficiency is increased.

Description

technical field [0001] The invention relates to the technical field of image recognition based on deep learning, in particular to a method for screening emoticons. Background technique [0002] With the development of various social applications, such as WeChat, Weibo, QQ and other communication software, and new media technologies, the use of emoticons is becoming more and more extensive. At the beginning, emoticons were just simple symbols and emoticons. Due to the popularity and development of Internet culture, the content of emoticons has become diverse, including but not limited to popular stars, photos, film and television stills, animation, dynamic pictures, etc., and Often accompanied by matching words or symbols to express a specific emotion. [0003] At present, most of the emoticons used by users come from social software providers and third-party emoticon creators. The creators use screenshot tools, drawing tools, animation tools, etc. The complexity of package...

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 Applications(China)
IPC IPC(8): G06K9/62G06K9/46G06K9/20
CPCG06V10/22G06V10/462G06F18/22G06F18/2415
Inventor 章俊黄博胡玉琛
Owner 上海宝尊电子商务有限公司
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