Unlock instant, AI-driven research and patent intelligence for your innovation.

Abnormality detection method and system and computer readable storage medium

An anomaly detection and anomaly technology, which is applied in the fields of image processing and artificial intelligence, can solve problems such as high cost, low efficiency, and poor precision, and achieve the effect of improving detection accuracy and detection efficiency

Pending Publication Date: 2021-06-01
吴俊
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the technical problems of low efficiency, high cost or poor precision existing in the existing cloth quality detection technology, the present invention provides an anomaly detection method, which can efficiently detect the abnormality of cloth images with complex patterns in non-fixed postures

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
  • Abnormality detection method and system and computer readable storage medium
  • Abnormality detection method and system and computer readable storage medium
  • Abnormality detection method and system and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] Compared with the technical problems such as low efficiency and poor precision in the traditional cloth quality detection technology, this embodiment proposes an abnormal detection method. The method of this embodiment adopts a hierarchical detection method (large-size abnormal area detection + small-size abnormal area Detection) can detect abnormal cloth images with complex patterns in non-fixed postures, which improves the detection efficiency and detection accuracy.

[0073] Specific as figure 1 As shown, the detection method of the present embodiment comprises the following steps:

[0074] Step S1, acquiring an image to be inspected; the image to be inspected in this embodiment is an image of the cloth to be inspected collected by an image acquisition device.

[0075] Step S2, detecting whether there is an abnormality in the image to be detected, and if so, directly output the detection result; otherwise, continue to execute step S3.

[0076] Step S2 of this embod...

Embodiment 2

[0152] This embodiment proposes an anomaly detection system 1, specifically as Figure 11 As shown, the system 1 of this embodiment includes a first-level detection module 10 and a second-level detection module 20;

[0153] The first-level detection module 10 of this embodiment is used to obtain the image to be detected and detect whether there is an abnormality in the image to be detected, and if so, output the detection result, otherwise the image to be detected is transmitted to the second-level detection module; this embodiment The first-level detection module 10 is used to realize the detection of large-size abnormal regions of the cloth image to be detected.

[0154] The image to be detected in this embodiment adopts, but is not limited to, the image of the cloth to be detected collected by an image acquisition device.

[0155] The second-level detection module 20 of this embodiment is used to divide the image to be detected into a single style graphic; wherein, the sin...

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 anomaly detection method and system and a computer readable storage medium. The method comprises the steps of S1, acquiring a to-be-detected image; s2, detecting whether the to-be-detected image is abnormal or not, If yes, directly outputting a detection result; otherwise, continuing to execute the step S3; s3, segmenting the to-be-detected image into a single-style graph; wherein the single-style graph refers to an image area with a consistent characteristic on the to-be-detected image; step S4, performing rectangular dicing processing on each single-style pattern; and S5, judging whether each to-be-detected rectangular block obtained by the block cutting processing is abnormal or not. According to the method, a grading detection method is adopted, the large-size abnormal area of the image can be detected. Meanwhile, the small-size abnormal area of the image can be detected, and the detection precision and the detection efficiency are improved.

Description

technical field [0001] The invention belongs to the technical fields of artificial intelligence and image processing, and in particular relates to an abnormality detection method, system and computer-readable storage medium. Background technique [0002] In cloth production, cloth image anomaly detection has always been a very important link. With the development of technology and the upgrading of product functions, users have put forward higher requirements for product quality, which requires enterprises to have stricter quality inspection standards and more effective quality inspection methods, which mainly rely on visual cloth quality inspection It is a difficult and high-cost point in the entire quality inspection system. At present, there are four common detection methods for cloth image anomalies: one is that quality inspectors detect anomalies with the naked eye; the other is to detect anomalies through visual image template matching; Sparse representation of differ...

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): G06T7/00G06K9/46G06K9/62G06N3/04G06N3/08G06T7/11G06T7/143
CPCG06T7/0004G06T7/11G06T7/143G06N3/08G06T2207/10004G06V10/40G06N3/045G06F18/22G06F18/214
Inventor 吴俊
Owner 吴俊