Bubble defects are a common type of tire quality defect, which are difficult to detect directly with the naked eye or using X-ray methods. This paper employs electronic shearography to non-destructively detect internal bubble defects in tires. Addressing the issues of low efficiency and poor accuracy in manual image recognition, as well as the inability to assess bubble defect sizes, a machine vision-based method for detecting tire bubble defects is proposed. Utilizing sine-cosine transform, least squares phase unwrapping, contrast-based and RANSAC edge detection algorithms, combined with deep learning techniques, this method achieves a comprehensive solution from automatic identification to false detection screening, and then to the assessment of bubble defect sizes based on out-of-plane displacement, providing a quality rating for tires. Experimental validation on actual samples demonstrates that the method achieves a missed detection rate and false detection rate of less than 2%, meeting the required accuracy standards for detection.