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

Target element content measurement method, training method, related device and storage medium

A target element and measurement method technology, applied in the field of image processing, can solve the problems of sorbite content error, difficult to perfectly identify sorbite structure, etc.

Pending Publication Date: 2021-12-10
ALIBABA GRP HLDG LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the existing grain boundary extraction methods are difficult to perfectly identify the sorbite structure, resulting in errors in the sorbite content during the measurement process

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
  • Target element content measurement method, training method, related device and storage medium
  • Target element content measurement method, training method, related device and storage medium
  • Target element content measurement method, training method, related device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0185] Example 1: Extract the metallographic image from top to bottom and from left to right according to a preset step size, and extract an image block whose size is the preset cutting size as the image block to be trained.

example 2

[0186] Example 2: The metallographic image is processed by up- and down-sampling, and the metallographic image obtained after sampling is cut according to the preset cutting size to obtain the image block to be trained.

example 3

[0187] Example 3: Perform image enhancement processing on the metallographic image, and cut the enhanced metallographic image according to the preset cutting size to obtain the image block to be trained

[0188] Targeted emphasis on the overall or local features of the image, making the original unclear image clear or emphasizing some interesting features, expanding the difference between different object features in the image, suppressing uninteresting features, can improve the image High quality, rich information, and enhanced image interpretation and recognition effects.

[0189] In a specific implementation, image enhancement may be performed by frequency domain methods such as low-pass filtering or high-pass filtering, or image enhancement may be performed by spatial domain methods such as local averaging or median filtering.

[0190] The noise in the image can be removed or weakened by low-pass filtering, local averaging or median filtering, and high-frequency signals su...

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

A target element content measuring method, a training method, a related device and a storage medium are provided, the target element content measuring method comprises the following steps: obtaining a target object metallographic image collected by a metallographic microscope; cutting the metallographic image into a plurality of image blocks according to a preset cutting size; inputting the plurality of image blocks into a trained deep regression network model to extract features of the plurality of image blocks, and mapping the features of the plurality of image blocks into a real number grading to obtain real number measurement results of the plurality of image blocks; and weighting the real number measurement results of the plurality of image blocks to obtain the target element content of the metallographic image. By adopting the method provided by the embodiment of the invention, the content of the target element can be quickly and effectively measured.

Description

technical field [0001] The embodiments of this specification relate to the technical field of image processing, and in particular to a method for measuring the content of target elements, a training method, a related device, and a storage medium. Background technique [0002] The traditional measurement of target element content, such as the measurement of sorbite content, adopts a manual method and uses a metallographic microscope to observe with the naked eye, which is labor-intensive and inefficient. In addition, using a metallographic microscope for a long time has a great impact on the eyes of testers harm. In recent years, with the development of image processing technology, different image processing methods have been proposed, and corresponding software systems have been designed to realize the automatic identification of sorbite structure, and the measurement of sorbite content has been completed on this basis. [0003] However, the existing grain boundary extracti...

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): G06T7/11G06T5/00G06K9/46G06K9/32G06K9/62
CPCG06T7/11G06T2207/10061G06T2207/20081G06T2207/20084G06F18/213G06T5/73
Inventor 林柏洪
Owner ALIBABA GRP HLDG LTD