Flexible circuit board image area identification method based on differential geometry

Abstract

The invention discloses a flexible circuit board image area identification method based on differential geometry. The flexible circuit board image area identification method comprises the following steps: S1, collecting an FPC surface image as a to-be-classified image; S2, extracting the contour of the to-be-classified image based on a region growing method of adaptively selecting an initial seedpoint; S3, selecting a standard template contour, calculating the curvature of the standard template contour, and converting the curvature into a histogram; S4, calculating the discrete curvature of the contour of the to-be-classified image, and converting the discrete curvature into a histogram with the same group distance as the contour of the standard template; S5, evaluating the similarity between the contour of the to-be-classified image and the contour of the standard template by adopting an EMD distance; and S6 identification profile. According to the invention, the requirement of defect detection on a single FPC component in actual detection is met.

Description

technical field [0001] The invention relates to the field of FPC image processing, in particular to a differential geometry-based image region recognition method for a flexible circuit board. Background technique [0002] Flexible printed circuit board (Flexible Printed Circuit, FPC) is a relatively high-end product in the rigid printed circuit board (Printed Circuit Board, PCB) industry. For the quality of FPC, find and eliminate defective products as early as possible to avoid waste of raw materials, time and labor costs. [0003] Automatic Optical Inspection (AOI) is based on the principle of optical inspection, which can measure the physical parameters of the FPC surface and detect surface defects without contact. Compared with electrical inspection, it will not cause secondary damage to the FPC board. Compared with manual inspection, the detection efficiency and accuracy have been greatly improved, and it has the advantages of automatic, efficient, and multi-scale. ...

AI Technical Summary

Problems solved by technology

[0005]Because the defect types and detection standards of each component of FPC are different in practical applications, and most algorithms have the problem of only locating and identifying a single FPC component, so It is necessary to perform area recognition on the FPC image and adopt corresponding defect detection algorithms for different areas of the FPC

However, the existing FPC image processing technology often skips the recognition step and directly collects images of different parts in the implementation, which does not meet the actual detection requirements. Therefore, the present invention proposes an FPC image area recognition method based on differential geometry theory

Images