Background: In civil aviation information monitoring system, optimization of image
recognition is applied to promote monitoring of and control over passenger mobility. The traditional
image recognition by video surveillance cannot effectively detect abnormal behaviors or explosives,
as described in various patents.
Method: In this paper, the author proposes a method for the optimization of surveillance image
recognition in civil aviation airport based on contourlet domain edge detection. Firstly, an overall
model of surveillance image recognition is established and statistically significant probability analysis
and other data integration methods are employed to realize comprehensive treatment of visual images.
In order to enhance the light-and-shade contrast of moving regions in the images and make images
smoother, we must evaluate edge position information of surveillance images, extract the lowfrequency
parts and signals to enhance contrast and promote image recognition capability.
Results: Simulation experiment proved that this method produced better image recognition results
and could effectively detect abnormal behaviors and violent terrorists.
Conclusion: It is a superior algorithm, which is of great importance to ensure the safety of airports.