Image segmentation method and image similarity calculation method and device
A similarity calculation and image similarity technology, applied in the field of image processing, can solve problems such as slow running speed, complicated calculation process, and difficult solution
Active Publication Date: 2021-04-27
SHANGHAI UNITED IMAGING INTELLIGENT MEDICAL TECH CO LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Based on this, it is necessary to focus on the Dice function. Currently, the parameters used in the calculation are binary parameters, that is, parameters that are either 0 or 1. This calculation method makes the calculation process more complicated and the solution is more difficult, resulting in image segmentation, etc. For the problem of slower running speed during operation, an image segmentation method and an image similarity calculation method, device, computer equipment and storage medium are provided
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
[0043] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.
[0044] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. It is a key step from image processing to image analysis. The existing image segmentation methods are mainly divided into the following categories: threshold-based segmentation methods, region-based segmentation methods, edge-based segmentation methods, and segmentation methods based on specific theories. From a mathematical point of view, image segmentation is the process of dividing a digital image into mutu...
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 present application relates to an image segmentation method and an image similarity calculation method and device. The method includes: obtaining the predicted probability of each pixel point of the image, the predicted probability range is any value within 0-1; obtaining the gold standard value of each pixel point of the image, the gold standard value is 0 or 1; The predicted probability of each pixel and the gold standard value of each pixel are calculated to obtain a first value and a second value; based on the calculation of the first value and the second value, an image similarity is obtained. The above image segmentation method and image similarity calculation method and device, when using the Dice function to calculate the similarity of image segmentation, the parameter of the predicted probability of each pixel of the image is expanded from a binary parameter to any value within 0-1 , which makes the calculation process more convenient, the solution easier, and the operation speed of image segmentation and other operations is improved.
Description
technical field [0001] The present application relates to the technical field of image processing, in particular to an image segmentation method and an image similarity calculation method and device. Background technique [0002] In the current image processing processes such as image classification, image segmentation, and image registration, objective functions such as Euclidean Distance, Cross Entropy, and Dice are often used to perform image classification, image segmentation, and image registration. Calculate the similarity and accuracy. [0003] For the Dice function, the current parameters used in the calculation are binary parameters, that is, parameters that are either 0 or 1. Therefore, before the image segmentation operation, the numerical value is binarized first, and the amount of data processed in deep learning is huge, so for The binarization operation requires a large amount of computing resources. In addition, this calculation method makes the calculation p...
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 Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/10G06N3/04
CPCG06T7/0002G06T7/10G06T2207/20104G06T2207/10004G06T2207/20081G06N3/045
Inventor 高耀宗顾潇蒙李强
Owner SHANGHAI UNITED IMAGING INTELLIGENT MEDICAL TECH CO LTD