| 摘要 |
PURPOSE:To accurately perform teaching without operating an industrial robot actually and to easily limit a range of malfunction when the supply of components is performed erroneously by performing a feature value extraction processing based on the detection image of the components, identifying the components based on an extracted feature value, and displaying an identification result with the detection image. CONSTITUTION:This method and device is equipped with an image detecting part 4 consisting of a CCD camera, etc., and an image processing part 5 which performs binarization processing, the feature value extraction processing, component identification processing. etc., setting an image detection signal from the image detecting part 4 as input and displays a binary image and a component identification result on a display 5a visually, etc. In the component identification processing, the binarization processing is applied to a fetched image, and the binary image at every component is extracted by performing connectivity analysis based on the binary image, and the feature values of an area value, peripheral length, circumscribing square length, and the number of holes, etc., can be obtained basing on the binary image, then, it is discriminated whether or not the component is the one of identification target basing on the obtained feature value and corresponding threshold value. |
