Air bubble in biaxially oriented polyester film(BOPET) directly affects the quality of the product

and accurate detection and quick recognition of bubble have important significance. This study presents a bubble inBOPET detection and identification method based on Learning Vector Quantization(LVQ) neural network. In this algorithm，the film images were processed and the outlines of the membrane defects were obtained. Through extracting the aspect ration，circularity，complexity and elongation，the characteristic values of membrane defects，whichfrom the image of film images after image processing，and then input to the bubble recognition system based on LVQneural network that had been trained. Finally the bubble was distinguished from the other membrane defects，andthe recognition system returned the location and area of the bubble in BOPET. Through the study of features of thebubbles in BOPET and extracted some quantities as character input of the LVQ neural network，then input somecharacteristic values as training value into the LVQ neural network to achieve the learning and prediction purpose，and the The design of the LVQ neural network was designed. The experiments show that

the proposed method canmeet the requirements analysis of air bubbles in BOPET film.