Fingerprint segmentation model training method and device, fingerprint segmentation method and device, equipment and medium
A technology of segmentation model and training method, which is applied in the field of image processing, can solve problems such as poor accuracy of fingerprint segmentation, and achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0040] figure 1 A schematic diagram of the fingerprint segmentation model training process provided by the embodiment of the present invention, the process includes the following steps:
[0041] S101: Input the sample images in the training set into the fingerprint segmentation model, and perform convolution processing on the sample images based on the convolution sub-module of the fingerprint segmentation model to obtain a first feature map.
[0042] S102: Perform feature extraction on the first feature map based on the channel attention submodule in the fingerprint segmentation model to obtain a second feature map; based on the spatial attention submodule in the fingerprint segmentation model, perform feature extraction on the first feature map performing feature extraction on the feature map to obtain a third feature map; merging the second feature map and the third feature map to obtain a fourth feature map.
[0043] S103: Determine the training fingerprint position infor...
Embodiment 2
[0088] Figure 7 A schematic diagram of the fingerprint segmentation process provided by the embodiment of the present invention, the process includes the following steps:
[0089] S201: Acquire an image to be segmented.
[0090] S202: Input the image to be segmented into a fingerprint segmentation model, and perform convolution processing on the image to be segmented based on the convolution sub-module of the fingerprint segmentation model to obtain a seventh feature map.
[0091] S203: Perform feature extraction on the seventh feature map based on the channel attention submodule in the fingerprint segmentation model to obtain an eighth feature map; based on the spatial attention submodule in the fingerprint segmentation model, perform feature extraction on the seventh feature map performing feature extraction on the feature map to obtain a ninth feature map; merging the eighth feature map and the ninth feature map to obtain a tenth feature map; determining the fingerprint i...
Embodiment 3
[0095] Figure 8 A schematic structural diagram of a fingerprint segmentation model training device provided by an embodiment of the present invention, the device includes:
[0096] The convolution processing module 81 is used to input the sample images in the training set into the fingerprint segmentation model, and perform convolution processing on the sample images based on the convolution sub-module of the fingerprint segmentation model to obtain the first feature map;
[0097] The attention processing module 82 is used to perform feature extraction on the first feature map based on the channel attention sub-module in the fingerprint segmentation model to obtain a second feature map; based on the spatial attention sub-module in the fingerprint segmentation model The module performs feature extraction on the first feature map to obtain a third feature map; merges the second feature map and the third feature map to obtain a fourth feature map;
[0098] The training module 8...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More