NEURAL NETWORKS FOR PRECISE MEASUREMENT IN COMPUTER VISION SYSTEMS

Although computer vision systems have been successfully applied to som e inspection tasks, they were generally not considered as precise meas urement tools due to dimensional distortion and errors. This paper pre sents procedures to correct these errors for precise measurement. The first step is to formulate calibration models for image coordinate sys tems using neural networks. Then neural networks to model dimensional errors from the initial measurement are structured in a learning stage using standard parts. Finally these models are used to correct measur ement errors in measurement tasks. These proposed procedures are imple mented as an example.