Research on medical mask detection method based on fast Fourier transform and linear Gauss

Abstract

Medical mask is a common protective device. Its health and safety are directly related to the health of users. In this study, fast Fourier transform (FFT) and linear Gaussian (LGM) are applied to detect the defect of medical masks. The real-time detection and classification of rectangular length and width of mask, aluminum strip length, tooth arrangement defects and stains are realized. The experimental results show that the software system based on shape matching, two-dimensional measurement, fast Fourier transform and linear Gaussian can reduce the influence of embossing background on stain detection, and improve the detection accuracy effectively. The average measurement accuracy of mask width, ear band length and aluminum strip length are 0.6875mm, 2.6588mm and 0.2450mm respectively.