Dual-energy XRT image segmentation method, target classification method and system
The invention discloses a dual-energy XRT image segmentation method and a target classification method and system, and the segmentation method and the target classification method both update a high-energy image by using a high-low energy model constructed by the invention, the contrast of the updat...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a dual-energy XRT image segmentation method and a target classification method and system, and the segmentation method and the target classification method both update a high-energy image by using a high-low energy model constructed by the invention, the contrast of the updated high-energy image is increased, the detail information of the image is more highlighted, and the image classification efficiency is improved. Therefore, the segmentation precision and the target classification and recognition precision can be improved. Besides, the segmentation method and the target classification method provided by the invention are both based on the visual characteristics of an HSV color space, the resolution capability of human eyes to a color image is stronger than that of a grayscale image, and an updated high-energy image is converted to the HSV color space, so that the recognition of an algorithm and the improvement of segmentation precision are promoted, and the improvement of the classi |
---|