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

An image processing method, device, image processing device, and storage medium

An image processing and image technology, applied in the field of image processing, can solve the problems of high hardware cost, occupation of computing resources, complex algorithms, etc., to achieve the effect of improving processing efficiency and processing effect, saving hardware cost and computing resource consumption

Active Publication Date: 2020-03-17
SHENZHEN INST OF ADVANCED TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an image processing method, device, image processing equipment and storage medium, aiming to solve the problem of high hardware cost and computing resource occupation due to the dependence on hardware equipment and complex algorithms of existing medical tomography image processing methods more questions

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
  • An image processing method, device, image processing device, and storage medium
  • An image processing method, device, image processing device, and storage medium
  • An image processing method, device, image processing device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 The implementation flow of an image processing method provided by Embodiment 1 of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0026] In step S101, when a tomographic image to be processed is received, the tomographic image is divided into tomographic image blocks, and image features of the tomographic image blocks are extracted.

[0027] In an embodiment of the present invention, when a tomographic image to be processed is received, the tomographic image may be divided into multiple image blocks, and image features of these image blocks may be extracted. Wherein, the tomographic image may be a low-resolution PET image or a CT image, and overlapping parts may exist between different image blocks, and these image blocks are referred to as tomographic image blocks for easy distinction.

[0028] As an example, the tomographic image...

Embodiment 2

[0035] figure 2 It shows the implementation flow of the sparse coding network training process in an image processing method provided by Embodiment 2 of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0036] In step S201, a high-resolution dictionary and a low-resolution dictionary are obtained through training according to a preset training image set, and the training image set is composed of a training image pair formed by a low-resolution training image and a corresponding high-resolution training image.

[0037] In the embodiment of the present invention, high-resolution tomographic images are collected in advance. For the convenience of distinction, these high-resolution tomographic images are called high-resolution training images. Sampling, difference amplification and other operations to obtain corresponding low-resolution tomographic images, and t...

Embodiment 3

[0064] image 3 The structure of an image processing device provided by the third embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, including:

[0065] The image segmentation unit 31 is configured to, when receiving a tomographic image to be processed, segment the tomographic image into tomographic image blocks, and extract image features of the tomographic image blocks.

[0066] In the embodiment of the present invention, when a tomographic image to be processed is received, the tomographic image may be divided into multiple tomographic image blocks, and there may be overlapping parts between different tomographic image blocks. As an example, the tomographic image may be divided into tomographic image blocks by performing a convolution operation with a Haar filter (Harr), and features of the tomographic image blocks may be extracted.

[0067] The image processing unit...

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 is applicable to the technical field of image processing, and provides an image processing method, an image processing device, image processing equipment and a storage medium. The methodcomprises steps: a to-be-processed tomography image is segmented to tomography image blocks; image features of the tomography image blocks are extracted; according to a pre-trained sparse coding network, a high-resolution dictionary and a low-resolution dictionary, the image features of the tomography image blocks are processed to generate a high-resolution image block corresponding to each tomography image block; and the high-resolution image blocks corresponding to all tomography image blocks are combined, and a high-resolution reconstructed image corresponding to the tomography image is acquired and outputted. Thus, through combination of deep learning and sparse coding, artifact reduction and detail compensation are carried out on a low-resolution tomography image, the computation andthe hardware cost of tomography image processing are reduced, and the tomography image processing efficiency and the processing effects are effectively improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image processing method, device, image processing equipment and storage medium. Background technique [0002] Current medical imaging mainly includes Positron Emission Tomography (PET) images, Computed Tomography (CT) images, and PET / CT fusion images. Among them, PET can study the physiology of the body from the cellular and molecular levels. Or pathological information has become a particularly important medical examination method for brain functional imaging and early cancer diagnosis. CT is a technology that continuously collects information around the scanning target through X-rays, and converts the collected information into tomographic images by computer. It can directly provide doctors with the physiological and pathological changes of the patient's body tissues or organs. [0003] At present, PET and CT image the collected low-count and under-samp...

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): G06T7/00G06T7/10G06T11/00
CPCG06T7/0012G06T7/10G06T11/008G06T2207/10081G06T2207/10104
Inventor 胡战利蒋昌辉梁栋杨永峰刘新郑海荣
Owner SHENZHEN INST OF ADVANCED TECH