Acquisition And Management Technology Of The Effective Information From Real-time Weld Image

With the development of X-ray detection and image processing technology,weld defects detection gradually transits from artificial detection to computer intelligence recognition.Analysis and recognition digitized weld image by computer is approved by the people in detection efficiency,economic profits,convenient and pragmatic, etc.This research is based on the actual project demand,design and develop the system of acquisition and management technology of the effective information from real-time weld image.This system include three module,they are image processing, defects recognition and image browsing.According to weld image's chatacteristic,divided image pretreatment into image enhancement,threshold segmentation,noisy reducing and edge detection. Becouse the constrast of gathered weld image is comparatively low,this paper enhance image in histogram equalization.Then division weld area from background by improvement slide threshold segmentation.Thirdly,use median filter algorithm filter the noise.Lastly, introduction genetic algorithm to gradient operators to extraction weld's edge.Choosing feature parameter is defects recognition's premise.This paper determin the feature parameter which can reflect defects's essential characteristic.Then reallize defects's recognition and classification by tree classifier.Weld image's whole browsing is added to X-ray weld detection system,which is proposed by experts and scholars.Firstly,according to the characteristic of continua frame weld image's overlap area is quite big,this paper posed a strong image matching tractics,then use weighted mean method blending mosaic trace,and mosaic continua frame weld image into a big visual angles image.Usually,digitized image is saved as BMP format,thus oprate system is complex to big visual angles image.This system firstly conversion image from BMP format to AVI format,then broadcast this image,provides operator more directly,more convenient and more quickly browser mode.Experiments are proved that the plan in image pretreatment, defects detection and image's whole browsing is feasible.,Soft system which programed by Visual Basic6.0,operation is simply and has practical value.