Silk ingot appearance forming defect detection and grading method, storage medium and equipment
The invention discloses a wire ingot appearance forming defect detection and grading method, a storage medium and equipment, and the method comprises the following steps: segmenting and unfolding an effective region of a wire ingot; wire ingot forming defect detection; and grading silk ingot forming...
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 wire ingot appearance forming defect detection and grading method, a storage medium and equipment, and the method comprises the following steps: segmenting and unfolding an effective region of a wire ingot; wire ingot forming defect detection; and grading silk ingot forming defects. According to the method, an image processing and circular ring unfolding algorithm is applied to segment a circular ring effective area of a silk spindle and realize rectangular unfolding of the circular ring area, a 3 * 3 Haar-like feature extraction operator is introduced, edge detection and expansion convolution ideas are fused, multiple types of convolution kernels are constructed, and a deep separable convolution idea is combined, so that the convolution efficiency of the silk spindle is improved. Multi-channel feature extraction and fusion are carried out on the converted image by using the constructed convolution kernel, the feature extraction of the first convolution layer of the multilayer CNN mo |
---|