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.

Measurement of Deformation and Force for Microcantilevers Based on Feature Point Matching and Digital Image Correlation

“…(10)(11)(12) There are several force sensing methods for microcantilevers, such as piezoelectric, (5) piezoresistive, (6) capacitive, (7) and optical methods. (13)(14)(15)(16)(17)(18)(19) Optical techniques are highly promising owing to their electromagnetic immunity and high resolution. In optical techniques, the deformation of microcantilevers is derived from images captured before and after the loading of external forces.…”

“…The inteferometric techniques (16,17) require complex equipment, which is expensive and sophisticated to implement. Hu and coworkers (18,19) reduced the force measurement problem to that of pattern recognition using a support vector machine (SVM) to classify the feature vector of moment invariants and to predict the applied force. A large number of training samples need to be established in order to obtain accurate results for this method.…”