Curvature-based two-dimensional target contour coding method

Abstract

The present invention discloses a curvature-based two-dimensional target contour coding method. According to the present invention, the discrete target contour pixel points are divided into 12 relative positions evenly and are designed with six code values, so that the curvature of a target contour is extracted by the coding method, and the relative position relationship between the adjacent pixel points is established. By the coding method, the situation that the conventional contour coding method enables the codes to change is avoided, at the same time, the calculation complexity is reduced, in the target matching, the plane curve contour matching can be carried out better, and the matching problem on the shielding condition can be solved very well.

Description

Technical field [0001] The invention relates to the field of object shape recognition in pattern recognition, in particular to a method for encoding a two-dimensional target contour based on curvature. Background technique [0002] In order to better recognize the shape of the target, the encoding method should not deform the rigid body of the target, and at the same time keep as much of the original information of the target as possible. At present, the commonly used coding methods include the coding method that uses position coordinates and chain codes to describe the contour information of the target object and the method based on the Fourier descriptor boundary description. However, the method of using position and chain code to describe the contour information of the target object will change greatly when the object undergoes a rigid body change, which will cause great obstacles to the reconstruction of the target; the boundary description method based on the Fourier descrip...

AI Technical Summary

Problems solved by technology

However, when the method of using position and chain code to describe the outline information of the target object occurs a rigid change in the object, the coding of the target will change greatly, which will cause great obstacles to the reconstruction of the target; The change of the rigid body of the object is invariant, but complex Fourier operations are required, and some information will be lost while normalizing the invariance, and will be affected by the selected starting point

In addition, the contour invariant moment description method, autoregressive model method, geometric correlation function method and neural network method can all describe the contour boundary information of the target object, but it will cause a large amount of information loss, which is not conducive to the restoration of the contour curve.

Images