Vision-based force measurement using pseudo-zernike moment invariants

• A new vision-based force measurement method is proposed to measure microforces.
• The method gets rid of mechanical models and is not limited to the object shape.
• The method can reliably measure microforces applied on elastic cantilevers.
• The measurement precision varies with dimensions of cantilevers.

A new vision-based force measurement (VBFM) method is proposed to measure microassembly forces through analyzing pseudo-zernike moment invariants (PZMIs). First, a feature vector of PZMIs is used to describe the deformed cantilever shape in microassembly. This description indicates a function between the applied force and the feature vector of PZMIs. Then, a training set is established to map the relationship between the deformed cantilever under known forces and feature vectors; likewise, a testing set is established to map the relationship between the deformed cantilever under unknown forces and feature vectors. Finally, a support vector machine (SVM) compares feature vectors in the testing set with those ones in the training set, implements multi-class classification and estimates unknown applied forces in the testing set. Experiments on four microcantilevers of different sizes validate the proposed method. Herein, both regional and boundary PZMIs are used to constitute the feature vector. Experimental results show that if the flexural stiffness gets smaller, sensing the change of object deformation gets easier and the force measurement precision gets higher. This trend can provide a reference for mechanism design of microcantilevers and microgrippers.