Image determination method and device, equipment and storage medium
A determination method and image technology, applied in the field of image processing, can solve the problems of low extraction accuracy, the region of interest in the macular region is susceptible to light, and fundus damage, etc., and achieve the effect of improving the accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0028] figure 1 It is a flowchart of an image determination method provided by Embodiment 1 of the present invention. This method can be performed by the image determination device provided in the embodiment of the present invention, specifically including the following:
[0029] S101. Extract a first image region in an image to be processed.
[0030] Wherein, the image to be processed is a complete image, and the image includes at least two image regions. Since different image regions are affected by environmental factors and other factors, the difficulty of extraction is different, and the region with easier extraction difficulty is used as the first image region. Regions that are more difficult to extract are used as the second image region. Taking the image to be processed as an example of the fundus image, the image to be processed includes the optic disc image area and the macular area image area. Correspondingly, since the optic disc area is bright and not easily affe...
Embodiment 2
[0039] Figure 2A is a flow chart of an image determination method provided in Embodiment 2 of the present invention, Figure 2B It is a schematic diagram of a macular region image area provided by Embodiment 2 of the present invention. This embodiment is based on the first embodiment above, taking the image to be processed as a fundus image, the first image area as an optic disc image area, and the second image area as a macular area image area as an example, and provides a specific implementation manner. The method can be performed by the image determining device provided in the embodiment of the present invention, and the method can specifically include the following:
[0040] S201. Extract the video disc image area in the image to be processed.
[0041] Optionally, the fundus image is used as the input of the image extraction model to obtain the optic disc image area. Wherein, the image extraction model is based on a deep learning network, and is trained according to th...
Embodiment 3
[0052] image 3 It is a schematic structural diagram of an image determination device provided in Embodiment 3 of the present invention, which can execute the image determination method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. Such as image 3 As shown, the device may include:
[0053] The first image area extraction module 31 is used to extract the first image area in the image to be processed;
[0054] The second characteristic parameter determination module 32 is configured to determine the characteristic parameters of the second image region in the image to be processed according to the characteristic parameters of the first image region;
[0055] The second image area determination module 33 is configured to determine the second image area in the image to be processed according to the characteristic parameters of the second image area.
[0056] On the basis of the abov...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


