Article identification method and system, and electronic device

A recognition method and article technology, applied in the field of image recognition, can solve the problems of inaccurate recognition results, inaccurate recognition effects, and similar furniture shapes.

Active Publication Date: 2018-03-23
深圳码隆智能科技有限公司
View PDF12 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to provide an item identification method, system and electronic equipment to solve the problem in the prior art that the current identification effect of identifying items in pictures is not accurate enough, for example, when using image recognition technology When identifying furniture, some furniture with different functions will be easily confused due to their similar appearance, such as kitchen cabinets and bathroom storage cabinets, which will lead to inaccurate technical problems in the identification results

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
  • Article identification method and system, and electronic device
  • Article identification method and system, and electronic device
  • Article identification method and system, and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] An item identification method provided by an embodiment of the present invention can be used for identification and search of items such as furniture, and can be applied to scene identification, for example, to identify more accurate items according to the scene. Such as figure 1 As shown, the item identification method may include:

[0062] S11: Identify the object in the image where the target item is located, and obtain object information; wherein, the object information includes: first object information and second object information.

[0063] As a preferred solution, objects other than the target item in the image where the target item is located are identified. The target item can be a commodity such as furniture that needs to be identified, and the object in the image can be other objects in the image where the furniture is located, such as electrical appliances, ornaments, other furniture, etc.

[0064] S12: Setting multiple space types; wherein, the space typ...

Embodiment 2

[0083] An item identification method provided by an embodiment of the present invention can be used for identification and search of items such as furniture, and can be applied to scene identification, for example, to identify more accurate items according to the scene. Such as figure 2 As shown, the item identification method may include:

[0084] S31: Identify the object in the image where the target item is located, and obtain object information; wherein, the object information includes: first object information and second object information.

[0085] In this step, objects other than the target item in the image where the target item is located are identified. The target item can be a commodity such as furniture that needs to be identified, and the object in the image can be other objects in the image where the furniture is located, such as electrical appliances, ornaments, other furniture, etc.

[0086] S32: Setting multiple space types; wherein, the space types include...

Embodiment 3

[0111] An article identification system provided by an embodiment of the present invention, such as image 3 As shown, the article recognition system 4 can include: an object recognition module 41, a space setting module 42, a probability calculation module 43, a probability statistics module 44, a probability comparison module 45, a space judgment module 46, an article type judgment module 47, and an initial recognition module 48 and an item determination module 49 .

[0112] For the object identification module 41, it can be used to identify the object in the image where the target item is located, and obtain object information, wherein the object information includes: first object information and second object information; the space setting module 42 can be used to set multiple space types , where the space type includes: the first space type and the second space type.

[0113] In practical applications, the probability calculation module 43 can be used to calculate the pr...

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 present invention provides an article identification method and system, and an electronic device, and relates to the field of image identification technology. The method comprises the steps of: identifying an object in an image where a target article is located, calculating probabilities of a first object belonging to a first space type and a second space type according to first object information to obtain a first probability and a second probability; calculating probabilities of a second object belonging to a first space type and a second space type to obtain a third probability and a fourth probability according to second object information; adding the first probability and the third probability to obtain a first space total probability, and adding the second probability and the fourth probability to obtain a second space total probability; comparing the first space total probability to the second space total probability, determining a space type where the target article belongsto, and determining an article type where the target article belongs to; and determining accurate information of the target article according to the article type and initial information. The technical problems are solved that different pieces of furniture are similar in shape to be easily confused when the pieces of furniture are performed by employing the image identification technology to causean inaccurate identification result.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an object recognition method, system and electronic equipment. Background technique [0002] Image recognition refers to the technology of using computers to process, analyze and understand images to identify targets and objects in various patterns. [0003] In the process of general image recognition, a camera is used to take pictures, and then the software is used for further recognition processing according to the gray scale difference of the pictures. In addition, in geography, it refers to the technology of classifying remote sensing images. [0004] However, the current recognition effect of identifying items in pictures is not accurate enough. For example, when using image recognition technology to identify furniture, some furniture with different functions will be easily confused due to similar shapes, such as kitchen cabinets and bathroom storage. cabinet, re...

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): G06K9/62
CPCG06F18/2415
Inventor 马修·罗伯特·斯科特黄鼎隆傅恺
Owner 深圳码隆智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products