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

Image processing method and apparatus, image recognition apparatus, and storage medium

An image processing device and image processing technology, which are applied in the field of image processing, can solve problems such as large amount of base image data, limitation of recognition function of image recognition equipment, and inability of image recognition equipment to store base image, so as to achieve the effect of improving the recognition function

Inactive Publication Date: 2019-02-22
BEIJING KUANGSHI TECH
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in order to ensure the accuracy of the recognition of the object to be recognized, the image quality of the bottom library image needs to be relatively good, so the data volume of the bottom library image is also relatively large
In this way, when the storage space of the image recognition device is limited, the image recognition device cannot store more bottom library images, which in turn causes the recognition function of the image recognition device to be greatly limited.

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
  • Image processing method and apparatus, image recognition apparatus, and storage medium
  • Image processing method and apparatus, image recognition apparatus, and storage medium
  • Image processing method and apparatus, image recognition apparatus, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0050] see figure 1, the embodiment of the present application provides an image recognition device 10, the image recognition device 10 includes: camera 11, memory 12, flash memory 13, communication interface 14, main chip 15 and FPGA16 (Field-Programmable GateArray, field programmable gate array ). Wherein, the main chip 15 is respectively connected with the camera 11 , the flash memory 13 , the communication interface 14 and the FPGA 16 , and the FPGA 16 is connected with the memory 12 and the flash memory 13 respectively. certainly, figure 1 The shown components and structure of the image recognition device 10 are only exemplary, not limiting, and the image recognition device 10 may also have other components and structures as required.

[0051] The camera 11 can be a conventional high-definition camera. When the image recognition device 10 is in a power-on working state, the camera 11 can photograph the object to be recognized under the control of the main chip 15 and o...

no. 2 example

[0059] see image 3 , this embodiment provides an image processing method, the image processing method is applied to an image recognition device, and the image processing method includes: step S100, step S200 and step S300.

[0060] Step S100: Obtain a standard feature library containing standard features of each object in at least one object, wherein the standard features of each object are obtained based on the bottom library image of each object, and the data volume of the standard features of each object is less than each The data volume of the base library image for each object.

[0061] Step S200: Obtain an image containing an object to be identified, and obtain features of the object to be identified based on the image.

[0062] Step S300: Based on the standard feature library and the features of the object to be identified, determine whether the object to be identified belongs to the at least one object.

[0063] The method flow of the present application will be des...

no. 3 example

[0104] see Figure 4 , the embodiment of the present application provides an image processing device 100, which is applied to image recognition equipment, and the image processing device 100 includes:

[0105] The feature obtaining module 110 is configured to obtain a standard feature library containing standard features of each object in at least one object, wherein the standard feature of each object is obtained based on the bottom library image of each object, and the standard feature of each object is The amount of data is less than the amount of data of the bottom library image of each object;

[0106] A feature extraction module 120, configured to obtain an image containing an object to be identified, and obtain features of the object to be identified based on the image;

[0107] The feature identification module 130 is configured to determine whether the object to be identified belongs to the at least one object based on the standard feature library and the features of...

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

Embodiments of the present application provide an image processing method and apparatus, an image recognition apparatus, and a storage medium, which relate to the technical field of image processing.The method includes obtaining a standard feature library containing at least one standard feature of each object, wherein the standard feature of each object is obtained based on a base image of eachobject, and the amount of data of the standard feature of each object is smaller than the amount of data of the base image of each object; obtaining an image containing an object to be identified andobtaining features of the object to be identified based on the image; based on the standard feature library and the features of the object to be recognized, whether the object to be recognized belongsto at least one object is judged. In a case where the storage space of the image recognition apparatus is limited, the image recognition apparatus acquires and stores a standard feature library containing standard features of more objects. In this way, the image recognition apparatus can use more standard features of the object to recognize the object to be recognized, thereby effectively improving the recognition function of the image recognition device.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, relates to an image processing method, device, image recognition device, and storage medium. Background technique [0002] In the current image recognition technology, the image recognition device needs to store the base image of the object. Then, during the recognition process, the image recognition device can identify the object to be recognized by performing feature matching between the stored bottom library image and the image of the object to be recognized. [0003] However, in order to ensure the accuracy of the recognition of the object to be recognized, the image quality of the bottom library image needs to be relatively good, so the data volume of the bottom library image is also relatively large. In this way, under the condition that the storage space of the image recognition device is limited, the image recognition device cannot store more images ...

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): G06K9/46G06F16/583
CPCG06V10/462
Inventor 梁喆潘宇超张一山朱雨
Owner BEIJING KUANGSHI TECH
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