Search

Curve matching plays an important role in many applications, such as image registration, 3D reconstruction, object recognition and video understanding. However, compared with other features(such as point, region) matching, it has made little progress in recent years. In this paper, we investigate the problem of automatic curve matching only from their neighborhood appearance. A novel descriptor called HMCD descriptor is proposed for this purpose, which is constructed by the following three steps: (1) Curve neighborhood is divided into a series of overlapped sub-regions with the same size; (2) Curve description matrix (CDM) is formed by characterizing each sub-region into a vector; (3) HMCD descriptor is built by computing the first four order Moments of CDM column vectors. Experimental results show that HMCD descriptor is highly distinctive and very robust for curve matching on real images. [ABSTRACT FROM AUTHOR]

Based on flexible pneumatic bending joint and flexible pneumatic spherical joint, a kind of flexible pneumatic 5-DOF finger is proposed, which is composed of two bending joints and a spherical joint. The mathematic model of flexible pneumatic spherical joint is further analyzed. On the researching foundation of flexible pneumatic bending joint and flexible pneumatic spherical joint, the kinematics equation of the 5-DOF finger is deduced. And the redundancy problem of the inverse kinematics solution is resolved by genetic algorithm. The simulation experiment illustrates that genetic algorithm for solving of inverse kinematics is feasible and effective. [ABSTRACT FROM AUTHOR]