Method, apparatus, acupuncture robot, and storage medium for recognizing ear acupoint reflex zones
AssigneeJianghan University
InventorsQIANG HE, HONGXING ZHANG, QIAN TU
Life of this patent
Estimating the term…
Loading patent…
AssigneeJianghan University
InventorsQIANG HE, HONGXING ZHANG, QIAN TU
Estimating the term…
This invention provides a method, apparatus, acupuncture robot, and storage medium for recognizing ear acupoint reflex zones. The method comprises: performing coarse-grained segmentation on the ear image based on the coarse-grained segmentation module to obtain an ear structure segmentation map and an ear functional area segmentation map; determining the accuracy of the ear functional area segmentation map based on the ear structure segmentation map; when the ear functional area segmentation map is accurate, performing fine-grained segmentation on the ear functional area segmentation map based on the fine-grained segmentation module to obtain the multiple ear acupoint reflex zones. This invention utilizes the relationship between the ear's own structure and functional areas to verify the accuracy of the ear functional area segmentation map, obtaining ear acupoint reflex zones when the ear functional area segmentation map is determined to be accurate, the accuracy of the determined ear acupoint reflex zones is ensured.
A method for recognizing ear acupoint reflex zones, which is used to recognize an ear image based on a hierarchical deep convolutional network model to obtain multiple ear acupoint reflex zones, wherein the hierarchical deep convolutional network model comprises a coarse-grained segmentation module and a fine-grained segmentation module;
An apparatus for recognizing ear acupoint reflex zones, which is used to recognize an ear image based on a hierarchical deep convolutional network model to obtain multiple ear acupoint reflex zones, wherein the hierarchical deep convolutional network model comprises a coarse-grained segmentation module and a fine-grained segmentation module;
Dependencies are inferred from the claim text.