Geometric 2D image analysis for automatic visual inspection

We propose two novel algorithms to analyse the motion parameters and structural data of filter components for quality inspection in a manufacturing line. The algorithms are based on geometrical properties of image correspondence vectors providing a closed form solution to all parameters of interest making full use of the distance between feature points and angle information. For comparison purposes, we also implemented Tsai and Huang's (1984) calibration algorithm based on epipolar geometry. Experimental results show that the proposed algorithms are in general more accurate than Tsai and Huang's and that they perform well in the presence of noise.