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

Multi-energy X-ray image fusion method and device based on deep learning

An image fusion and deep learning technology, which is applied in neural learning methods, image analysis, image data processing, etc., can solve the problems that the depth range of the image exceeds the display capability, and cannot fully display the structural information of the workpiece, so as to enrich the edge details and overcome the excessive Effect of exposure and underexposure, strong robustness

Pending Publication Date: 2022-07-05
ZHONGBEI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most X-ray-based workpiece detection methods obtain transillumination subimages of different thickness ranges by increasing the X-tube voltage, and obtain fusion results through weighted fusion of subimages, but the weighted fusion process may cause the image depth range to far exceed the display capability of the device , cannot fully display the structural information of the workpiece

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
  • Multi-energy X-ray image fusion method and device based on deep learning
  • Multi-energy X-ray image fusion method and device based on deep learning
  • Multi-energy X-ray image fusion method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Multi-energy X-ray image fusion method based on deep learning

[0033] like figure 1 , figure 2 As shown, the deep learning-based multi-energy X-ray image fusion method of the present invention includes the following steps:

[0034] Step 1: Collect different energy X-ray images of different workpieces as a training data set.

[0035] The hyperparameters of the network are set, and the dataset image is scaled to a size suitable for the network input. In this embodiment, the input image is scaled to a size of 256×256.

[0036] Step 2: Input the X-ray image of the training data set into the encoder, train the encoder and decoder, and obtain the trained encoder and decoder after the training network is stable.

[0037] The encoder consists of a main branch and an auxiliary branch. The main branch first uses a 1×1 convolution layer to increase the number of feature channels of the input image, and then uses 4 layers of multi-scale convolution blocks to extract the global...

Embodiment 2

[0067] Multi-energy X-ray image fusion device based on deep learning

[0068] The deep learning-based multi-energy X-ray image fusion apparatus is used to perform the above-mentioned deep learning-based multi-energy X-ray image fusion method.

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 relates to a multi-energy X-ray image fusion method and device based on deep learning. The method comprises the following steps: acquiring different energy X-ray diagrams of different workpieces as a training data set; inputting the X-ray graph of the training data set into an encoder, training the encoder and a decoder, and obtaining the trained encoder and decoder after the training network is stable; a fusion strategy combining channel attention and space attention based on fuzzy entropy is added between the trained encoder and decoder; and inputting X-ray diagrams with different energies into the trained encoder to extract features, fusing the feature diagrams by using a fusion strategy combining channel attention and space attention based on fuzzy entropy, and inputting the fused feature diagrams into the trained decoder to output a fusion result. When the method and the device are used for processing the image, the workpiece information can be effectively reflected, and the detection accuracy is improved.

Description

technical field [0001] The invention relates to a multi-energy X-ray image fusion method and device based on deep learning. Background technique [0002] Important components with complex structures play an irreplaceable role in aerospace, defense and industrial applications. Manufacturers need to strictly control the quality when manufacturing these workpieces. X-rays are often regarded as a quality inspection tool. Digital X-ray imaging technology can complete a series of tasks such as defect detection and internal structure analysis. However, due to the constraints of workpiece structure and material, the detection object with large thickness ratio has the phenomenon of over-exposure and under-exposure under the single-energy system, which is difficult to achieve. Reflect comprehensive structural information. Specifically: in the X-ray image, when the thicker area in the workpiece is displayed well, only a small part of the X-ray is absorbed in the thinner area, and over...

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
IPC IPC(8): G06T7/00G06T7/13G06N3/08G06N3/04G06K9/62G06V10/82G06V10/80
CPCG06T7/0002G06T7/13G06N3/08G06T2207/10116G06T2207/20221G06T2207/20081G06N3/045G06F18/2415
Inventor 刘祎刘宇航桂志国张权颜溶標
Owner ZHONGBEI UNIV