An Investigation in Image Retrieval for Analysing Welding Defects

The development of new approaches in image processing
and retrieval provides several opportunities in supporting
in different domains. The group of welding engineers frequently
needs to conduct visual inspections to assess the quality
of weldings. It is investigated, if this process can be supported
by different kinds of software. A generic CBIR system
has been successfully used to sort welding photographs
according to the severity of visual faults. Similar algorithms
were used to automatically spot and measure the diameter of
gas pores.