Image recognition method and system

An image recognition and image technology, which is applied in the field of recognition methods and recognition systems, can solve the problems of cumbersome operations and the inability to judge whether the images are normal or not.

Pending Publication Date: 2022-01-28
TUL CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the number of images of the object under test increases with time, many abnormal images that are not stored in the database may be generated, resulting in the inability to judge whether the images are normal, so this identification method needs to be constantly updated The image type in the abnormal state in the database makes the operation very cumbersome

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 recognition method and system
  • Image recognition method and system
  • Image recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

no. 1 Embodiment

[0066] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0067] figure 1 It is a schematic diagram for illustrating the architecture of an image recognition system according to an embodiment of the present invention. Please refer to figure 1 , in an embodiment of the present invention, the image recognition system includes a database 10 , a computer device 20 and at least one camera device 30 . The database 10 stores at least one normal state image of at least one object under test 40, such as normal state images 401-403; the photography device 30 captures at least one state image of the object under test 40; the computer device 20 is electrically connected to the database 10 and photographs device 30, and the computer device 20 includes an automatic codec 201, the automatic codec 201 receives at leas...

no. 2 Embodiment

[0073] image 3 It is a schematic diagram for illustrating the image comparison of the image recognition system according to another embodiment of the present invention. Please refer to figure 1 and image 3 , in another embodiment of the present invention, similarly, the feature 400 is included in the state image 301, and the feature 400 has a displacement d compared with the normal position, but it should be understood that the feature 400 with the displacement d will not The object under test 40 is affected, so it can be regarded as a normal state. Furthermore, when the trained automatic codec receives the state image 301, the trained automatic codec will compare whether the feature 400 in the state image 301 matches the normal state image, and only match the normal state image Image features 400 are extracted and reconstructed into a reconstructed state image 303 .

[0074] Wherein, because the trained autocoder has received information that the feature 400 with the d...

no. 3 Embodiment

[0076] Figure 4 It is a schematic diagram for illustrating the image comparison of the image recognition system according to another embodiment of the present invention. Please refer to figure 1 and Figure 4 , in another embodiment of the present invention, similarly, the feature 400 is included in the state image 301, and the feature 400 has a rotation value compared with the normal position, but it should be understood that the feature 400 with the rotation value does not It will not affect the object under test 40, so it can be regarded as a normal state. Furthermore, when the trained automatic codec receives the state image 301, the trained automatic codec will compare whether the feature 400 in the state image 301 matches the normal state image, and only match the normal state image Image features 400 are extracted and reconstructed into a reconstructed state image 303 .

[0077] Wherein, because the trained automatic codec has received information that the feature...

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 provides an image recognition method and a system thereof. The image recognition method comprises the following steps: storing at least one normal state image of at least one object to be detected; an automatic codec receiving the at least one normal state image to become a trained automatic codec; capturing at least one state image of the at least one object to be detected by at least one photographing device; a computer device receives the at least one state image, and the trained automatic codec performs feature extraction and reconstruction on the at least one state image to generate at least one reconstructed state image; and the computer device compares the at least one state image with the at least one reconstructed state image and determines whether the at least one state image is a normal state image.

Description

technical field [0001] The present invention relates to an identification method and an identification system, in particular to an image identification method and an image identification system for performing a new identification method on images. Background technique [0002] In the prior art, if image recognition is used to capture defects in an image frame, or to determine whether the image frame is in a normal state, it is usually to compare the acquired image frame with a standard image (GoldenFrame) Yes, as long as there is a difference between the two, it will be determined that the acquired image is abnormal, and there may be defects or other abnormalities. However, there may be a situation of misjudgment in the above-mentioned prior art, and the situation of misjudgment will be described below. [0003] Figure 10 It is a schematic diagram used to illustrate one of the frame comparison misjudgment situations in the prior art. Please refer to Figure 10 , in the pr...

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): G06V10/774G06V10/74G06K9/62G06N3/04G06T7/00G06F16/51
CPCG06T7/0002G06F16/51G06N3/045G06F18/22G06F18/214
Inventor 黄文吉陈建华陈纬仁裴德雄贾博渊
Owner TUL CORP
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap