A Character Inspection Method For Tire Mold Based On Machine Vision

Tire mold is the tire vulcanization molding equipment in the assembly line.The characters on the tire mold imply the product information,which is very important for tire manufacturers.Because the tire mold is too expensive,the economic loss will inevitably occur if any character is added,deleted,or otherwise modified in the mold.So,the careful inspection of the characters for the tire mold is a vital step in the production of the tire mold.Nowadays,almost all the manufactures manually implement this inspection task with the human vision.It is a consuming-time task for the quality control worker.To in-crease the production of the tire mold,many quality control workers devote themselves to this inspection task.However,it results in high labor costs for the manufacturer.Moreover,the efficiency and reliability of the inspection task will be dramatically reduced because the inevitable visual fatigue occurs when the quality control worker works for a long time.Recently,with the development of artificial intelligence,machine vision is more and more used in industry inspection,and it achieved good results.To implement the automatic inspection for the characters on the tire mould,a characters inspection method for tire mould is proposed based on machine vision in this paper.An automatic inspection equipment is designed according to the features of the tire mould.Then,the corresponding image processing methods are designed,which include image preprocessing,image location and character inspection.Image preprocessing mainly contains fitting the contours of the ac-quired tire mold images and those of the CAD as the arcs of two circles and polar transformation of the acquired images and the CAD.Then,we propose a novel framework to locate the acquired images into the corresponding parts of the CAD.Final-ly,a character inspection scheme is proposed by combining a based character recognition method based on neural networks and a string match-ing approach.At the stages of image locating and character inspection,image mosaic is simultaneously employed to label the defects in the CAD,which is based on the histograms-of-gradients(HOG)features.The experimental results indicate that the designed automatic inspection system can inspect the characters on the tire mold with a high accuracy at a reasonable consuming time.The designed automatic inspection system can detect the carving faults for the characters in the tire molds,which are the cases that the characters are wrongly added,deleted,or modified in the tire mold.To the best of our knowledge,this is the first automatic vision-based inspection system for the characters in the tire mold.An inspection equipment is designed and many novel image processing methods are proposed to implement the inspection task.The designed system can be widely applied in the industry.