Running Demo Codes

This example will demonstrate defect detection based on image recognition. The principle is to locate and highlight the positions of defects on the surface of a product by identifying connected regions that are too large.

The running method is as the following:

Step:

To run C++ application:

Perform the following step under the user directory on VisionFive 2 Debian to run the C++ demo:

example_3rd_imgproc_defect_detection

Result:

  • The HDMI monitor will display the original image of the product, as well as the processed result image that is marked with the detected defect areas;
  • The terminal will display the serial number and area of the connected region to which the defect area belongs.
Figure 1. Original Product Image (Left) and Detection Result Image (Right)