Image's concentric circle character matching based on lateral inhibition mechanism and application on scene matching

摘要

The lateral inhibition mechanism of biologic vision is introduced and applied on edge extraction of images. With the method, the image's original characters are unchanged. Furthermore, the edge extraction and image enhancement can be done effectively when the gray changes caused by varying illumination. For increasing the matching ability of resistance to geometric distortion, a new matching algorithm is established. The edges of the real-time and reference maps are extracted with the above-mentioned method based on lateral inhibition. Then the concentric circle characteristic vector of image is defined and the method of vector extraction is proposed. The concentric circle characteristic vectors of the realtime and reference maps are extracted. Finally they are matched according to the vectors. The resistance of geometric distortion is improved. A map of roadway in a city obtained by satellite is simulated. The results show that the influence of gray and geometric distortion on scene matching is effectively overcome. The algorithm is easily implemented with hardware. The operation speed of the algorithm is also fast. It's worth for the design of real-time scene matching system.