Gray cloth defect on-line detecting system based on machine vision and achieving method

The invention relates to a gray cloth defect on-line detecting system based on machine vision and an achieving method. The gray cloth defect on-line detecting system comprises a cross beam device, a lighting device, industrial cameras, an industrial control host machine, a display control screen and an alarm indicating module. The cross beam device is installed right above or obliquely above gray cloth detected by a warp knitting machine just now and is used for fixing the lighting device and a round steel pipe, and a group of industrial cameras are fixedly connected to the round steel pipe. The display control screen is connected with the industrial control host machine, diameters of the system are set through the display control screen in a setting state, and defect shapes and regions with defects can be observed in an operating state. The alarm indicating module comprises an alarm indicating lamp and a light-emitting diode (LED) information indicating panel, wherein the alarm indicating lamp can alarm an operator in an acousto-optic signal mode when the defects exist, and the LED information indicating panel indicates whether machine detection is normal or not or the regions and positions where the defects exist. The achieving method has the advantages of overcoming the shortage of the method and being a novel method utilizing a machine vision technology in the field of detection of warp knitting defects.