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

Object identification method and device, data set updating method and device and data processing method and device

An object recognition and object technology, applied in the field of object recognition, can solve the problems of limited manual input of pictures by users, limited number of face picture collection pictures, etc.

Active Publication Date: 2019-06-28
ALIBABA GRP HLDG LTD
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The applicant's research found that due to the limited number of pictures manually entered by the user in the face registration stage, and the face recognition is affected by factors such as illumination, expression, posture, aging, etc., it is necessary to add more face pictures in the face verification stage to improve recognition rate, but subject to various conditions, the number of pictures in the face picture collection that can be used for face recognition is limited, so the number of face pictures needs to be controlled

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
  • Object identification method and device, data set updating method and device and data processing method and device
  • Object identification method and device, data set updating method and device and data processing method and device
  • Object identification method and device, data set updating method and device and data processing method and device

Examples

Experimental program
Comparison scheme
Effect test

example 2

[0250] Example 2 may include the method described in Example 1, wherein the deleting the object picture corresponding to at least one difference data sorted first from high to low includes:

[0251] According to the quantity requirement of the object pictures in the object picture set, delete the object picture corresponding to at least one difference data that is sorted first from high to low.

example 3

[0252] Example 3 may include the methods described in Example 1 and / or Example 2, wherein the determining the difference data between the remaining target pictures after the target pictures are extracted from the target picture set includes:

[0253] For the remaining object pictures after the object pictures are extracted from the object picture set, determine the difference data between any pair of object pictures;

[0254] Determine the difference data between the remaining object pictures according to the difference data between the pairwise object pictures.

example 4

[0255] Example 4 may include one or more of the methods described in Example 1-Example 3, wherein the determining the difference data between the remaining object pictures according to the difference data between the pairwise object pictures includes:

[0256] The mean or sum of the difference data between the pairwise object pictures is used as the difference data between the remaining object pictures.

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 object recognition method and device. The method comprises the following steps of: determining difference data among the rest object pictures after the object pictures are extracted from the object picture set, and deleting the object pictures from the object picture set according to the difference data, including deleting the object picture corresponding to at least onepiece of difference data which are ranked from high to low and are the most front, and carrying out object recognition by adopting the object picture set with the object pictures deleted. According to the method and the device, the difference between the remaining object pictures can be maximized, the complementarity between the object pictures is optimal, the object picture set with the object pictures deleted is adopted for object recognition, then the diversification of the object pictures in the object picture set with the set picture number is best, and the recognition rate during objectrecognition is increased.

Description

technical field [0001] The present application relates to the technical field of object recognition, and specifically relates to an object recognition method and its device, a data set updating method and its device, a data processing method and its device, a computer device and a computer-readable storage medium. Background technique [0002] Face recognition is a kind of biometric recognition technology based on human facial feature information, which can be applied to authentication scenarios such as user login and access control. The usual face recognition system consists of two stages. In the face registration stage, it is responsible for collecting face pictures, entering face names and other related information, extracting face features and saving them to the database; in the face verification stage, collecting face pictures , extract face features, compare with the user’s face in the database, if the comparison result is greater than the preset score, confirm the ide...

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): G06F16/53G06F16/54G06K9/00G06K9/62
Inventor 于鲲
Owner ALIBABA GRP HLDG LTD
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