An improved image acquisition method for measuring hot forgings using machine vision

Machine vision has already been used for measuring the dimensions of hot forgings. However, the features of hot forgings are not sufficiently clear to be extracted robustly and efficiently because of the poor image quality caused by the radiation that the hot forgings emit. Therefore, to obtain clear images, an improved image acquisition method for the measurement of hot forgings using machine vision is proposed in this paper. Firstly, an image evaluation model based on the Signal to Noise Ratio (SNR) of the Region of Interest (ROI) is established. Then, main interference factors that affect the quality of image, such as the forgings radiation light and laser light, are analysed. Next, the compensation parameters for clear image acquisition in spite of time-varying temperature are obtained. Finally, the laboratory experiments indicate that the quality of the forging images with the laser strips is improved effectively. Meanwhile, three hot parts with different heights are measured in laboratory, and the absolute error is less than 0.32 mm, the relative error is less than 0.27%. The dimensional measurement of the hot forging in a workshop is also conducted to verify the effectiveness of the presented system.