Model determination, image recognition and industrial quality inspection method and device, and storage medium
A technology for image recognition and determination methods, applied in the field of vision, can solve problems such as low recognition accuracy, achieve the effect of improving recognition performance and improving overall recognition performance
Pending Publication Date: 2022-05-13
ALIBABA (CHINA) CO LTD
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, using the existing machine vision quality inspection scheme for quality inspection has the problem of low recognition accuracy
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] In the field of industrial quality inspection, artificial intelligence solutions based on deep learning usually need to collect or collect pictures of defective (or defective) products on the industrial production line, and then label the pictures containing defective products with different types of defects. In the initial stage of the project, the number of pictures containing defective products that can be collected is very small, and all the pictures collected need to be marked with all defect categories. After the data labeling work, a single deep learning model is trained on the labeled data, and the trained deep learning model is used to detect or identify all categories of defects. Such as figure 1 As shown, the picture to be inspected is input to the trained deep learning model, and the deep learning model is used to identify all defect categories. All defect categories include: defect category 1, defect category 2, category 3, ..., category n .
[0050] With...
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
Login to View More Abstract
The embodiment of the invention provides a model determination method, an image recognition method, an industrial quality inspection method, equipment and a storage medium. The method comprises the following steps: determining a trained first image recognition model; the first image recognition model can recognize a plurality of preset foreground categories; determining a plurality of different target image recognition models according to the first image recognition model; the plurality of different target image recognition models can recognize different preset foreground categories; the plurality of preset foreground categories comprise the preset foreground categories which can be recognized by a plurality of different target image recognition models; according to the training samples, a plurality of different target image recognition models are trained; wherein the plurality of different target image recognition models are used for recognizing the to-be-recognized image. According to the technical scheme provided by the embodiment of the invention, the overall recognition performance of the model can be improved, and particularly in the field of industrial quality inspection, the recognition accuracy of the defect category of the defective product can be improved.
Description
technical field [0001] The present application relates to the field of visual technology, in particular to a method, device and storage medium for model determination, image recognition and industrial quality inspection. Background technique [0002] At present, industrial intelligence is the future development trend. Industrial quality inspection is one of the most important links in industrial production, and it is also an important breakthrough in industrial transformation and upgrading. Traditional industrial quality inspection relies on manpower, which not only has low efficiency and high error rate, but also has high labor cost and easy loss of personnel. [0003] In the prior art, there are some machine vision quality inspection schemes to replace manual quality inspection and realize the identification and classification of product defects or flaws. However, using the existing machine vision quality inspection scheme for quality inspection has the problem of low 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
Login to View More IPC IPC(8): G06T7/00G06V10/764G06K9/62G06Q10/06G06Q50/04
CPCG06T7/0008G06Q10/06395G06Q50/04G06F18/2431Y02P90/30
Inventor 刘伟周静辉陈汉苑李晨阳赵亮罗斌
Owner ALIBABA (CHINA) CO LTD