Research On Visual Measuring Method Of Internal Thread Pitch

Internal thread is a kind of commonly used mechanical connection structure.In order to meet the requirements of the coupling property and the strength of the joint,the internal thread size is highly standardized in the industrial production.At present,the measurement of thread parameters in China is mainly done by mechanical testing method.The detection speed is slow and the measurement accuracy is low.In view of the problems existing in the traditional method for detecting the internal thread pitch,a non-contact measurement method based on machine vision technology is presented in this paper.In this paper,the imaging model of the industrial endoscope camera is established,and the internal thread image is calibrated by Tsai two-step calibration method.The edge feature in thread surface images is weak,texture is complex,and the contrast is not obvious,thus it is difficult to directly extract the crest region information.This paper uses SIFT template matching algorithm to extract two adjacent thread crest regions of the image,the experimental results show that the algorithm of tooth top image matching and localization has fast speed and high precision.For the problem of extracting the tooth top image axis,the paper uses binarization and median filtering method to remove image noise,uses the expansion algorithm of mathematical morphology to fill the holes of the crest of the image area,and use skeleton extraction algorithm of mathematical morphology to extract information in two axis tooth top image.Based on the camera calibration,the measurement of the inner thread pitch is realized.The experimental results show that the proposed method has the advantages of high efficiency,high precision,automation and no damage.It can meet the requirements of the efficiency and precision of the industrial production.