Automatic shape analysis of crystal glasses

Abstract

This paper presents an efficient algorithm as part of a programme of research in automatic shape inspection of quality crystal glasses. The shape of these glasses can vary since they are usually hand made and is important because they are often sold in matching sets. Shape analysis concerns the match of the outline of glass to a reference (or master) shape. An algorithm was developed to provide the offset by which the current outline needs to be translated and the factor by which it needs to be scaled, in order to register the outlines to provide the best leastsquares match between the current outline and the master shape. Results are included which demonstrate the accuracy of the algorithm both in a simulated environment and when applied to real pictures. The difference data from the best match appears inadequate to grade glasses of the same type but can be used to sort different gl assesreliably.An efficient algorithm has therefore been developed to provide the best starting point from which shape comparison can ensue, and research is in progress to capitalise on this technique.

Automatic detection of micro-crack in solar wafers and cells: a review

“…Therefore, there is a need for advanced image processing software for accurate detection and analysis. Computer vision is an important tool that utilizes image processing techniques to solve a wide range of vision-based problems (Abdullah et al, 2005; Nixon, 1989; Ponsa et al, 2011). Recently, Tsai et al (2010) proposed a simple machine vision-based system for capturing the image of a solar wafer by using a front light emitting diode (LED) and an off-the-shelf CCD camera.…”