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

Image processing method and device thereof

An image processing device and image storage technology, which is applied in image data processing, image analysis, instruments, etc., can solve problems such as inability to inspect, difficult to improve inspection reliability, and affect the accuracy of judgment results, so as to achieve the effect of fast and accurate comparison

Active Publication Date: 2018-07-06
大强视觉科技(湖州)有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, there are many technologies that capture the captured image by capturing the appearance of the object such as the bottle mouth, and check whether there are any defects such as foreign matter mixed in, breakage, gaps, and dirt based on the captured image, but these only use the captured image data Perform binarization with a certain threshold, and test the black or white area (area ratio) of the binarized data to check for defects. This simple binarization method is sometimes difficult to improve the reliability of the inspection; Some image processing equipment can determine whether a specific part with obvious local shape features such as the mouth of a glass bottle is qualified, and can quickly and accurately inspect it, but objects other than glass bottles cannot be inspected because they do not have such obvious local features; some Although advanced image processing equipment can automatically judge the attributes of the object based on various parameters such as color, shape, structure, and size displayed in the image information, it cannot judge the state displayed in each cut part, which is Seriously affect the accuracy of judgment 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
  • Image processing method and device thereof
  • Image processing method and device thereof
  • Image processing method and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Next, an image processing apparatus related to a first embodiment of the present embodiment will be described with reference to the drawings.

[0035] Such as figure 1 As shown, the image processing device related to the present invention includes a photographing device 1 , a reference image storage unit 2 , a confidence calculation unit 3 and a state judgment unit 4 . After the state judging unit receives the input instruction, it reads out the specified program and data from the reference image storage unit, and then performs various corresponding processing according to these programs and data.

[0036] Specifically, on the basis of the image data of the object (the object whose state needs to be judged) and the image information captured by the photographing device, the state judging unit pre-stores whether the state of the object is good or not in the reference image storage unit. The image data are compared to make a judgment and output the judgment result. For ...

Embodiment 2

[0068] The following will pass Figure 5 etc., the image processing apparatus related to the second embodiment of the present invention will be described.

[0069] Figure 5 , is a description of creating a reference image template used as a judgment criterion in this embodiment. As shown in the figure, reference image templates related to various defective products are added.

[0070] For example, it is generally believed that qualified products have a typical style, and by preparing multiple or single samples, that is, collecting average standard data, a reference image template that can accurately judge the similarity of qualified products can be generated. However, depending on the properties of the object, etc., there are many reasons for the occurrence of defective products. The shape, etc. expressed as a defective product differs greatly depending on the cause. The causes of defective products include various causes such as misalignment, contamination of foreign mat...

Embodiment 3

[0089] The following will pass Figure 9A etc., the image processing apparatus related to the third embodiment of the present invention will be described.

[0090] Figure 9A , Figure 9B Image processing in this embodiment is described. As shown in the figure, the shooting device (refer to figure 1 ) obtained by Figure 9A All images shown in PH, by automatic segmentation, such as Figure 9B As shown, the segments are divided into P 1-P m, and a template (hereinafter referred to as a reference segmented image template) is created using each segmented image as a criterion for use. Figure 9A , Figure 9B In the example, m bottles B T 1-B T m stored in a box etc. are photographed (6 rows and 8 columns in the figure, that is, m=6×8=48), and the image is as shown in the schematic diagram. In this case, the arrangement of m bottles is pre-determined. According to this arrangement, the division line LL of the demarcated area is uniformly reflected from all previous images PH...

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 image processing method and its equipment. Through a confidence degree calculation unit, the confidence degree reflecting the degree of approximation of unqualified products or qualified products is specified based on a pre-prepared reference image template, and based on the relevant confidence degree, the The status of the object is judged as good or bad. In this way, even for an object with an abstract fuzzy concept area, it is possible to perform a preparatory and rapid judgment like processing an image of the object.

Description

technical field [0001] The invention relates to an image processing method and equipment thereof. Background technique [0002] At present, there are many technologies that capture the captured image by capturing the appearance of the object such as the bottle mouth, and check whether there are any defects such as foreign matter mixed in, breakage, gaps, and dirt based on the captured image, but these only use the captured image data Perform binarization with a certain threshold, and test the black or white area (area ratio) of the binarized data to check for defects. This simple binarization method is sometimes difficult to improve the reliability of the inspection; Some image processing equipment can determine whether a specific part with obvious local shape features such as the mouth of a glass bottle is qualified, and can quickly and accurately inspect it, but objects other than glass bottles cannot be inspected because they do not have such obvious local features; some ...

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 Patents(China)
IPC IPC(8): G06T7/00
Inventor 门洪涛
Owner 大强视觉科技(湖州)有限公司
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