Vision-based force measurement using geometric moment invariants

Abstract

This article presents a new vision-based force measurement method to measure microassembly forces without directly computing the deformation. The shape descriptor of geometric moment invariants is used as a feature vector to describe the implicit relationship between an applied force and the deformation. Then, a standard library is established to map the corresponding relationship between the deformed cantilever under known forces and a set of feature vectors. Finally, a support vector machine compares the feature vector of deformed cantilever under an unknown force with those in the standard library, implements multi-class classification and predicts the unknown force. The vision-based force measurement method is validated for eight simulated microcantilevers of different sizes. Both regional and boundary moment invariants are used to constitute the feature vector. Simulated results show that the force measurement precision varies with length, width and height of cantilevers. If length increases and width and height decrease, the precision is higher. This trend can provide a reference for mechanism design of microcantilevers and microgrippers.