Size inspection method for prefabricated box girder reinforcing mesh

The invention relates to the technical field of building construction, in particular to a size inspection method for a prefabricated box girder reinforcing mesh, which comprises the following steps: S1, acquiring a color image of the prefabricated box girder reinforcing mesh, inputting the acquired image into a neural convolutional network, and performing redundant wavelet transform on image data by the neural convolutional network to obtain a color image of the prefabricated box girder reinforcing mesh; obtaining a low-frequency approximate component and high-frequency detail components in three directions, and then multiplying the high-frequency detail components in the three directions by adjacent-scale wavelet coefficients to obtain a wavelet coefficient graph obtained by multiplying the wavelet coefficients in three different directions; s2, linear processing is carried out on the wavelet coefficient graph, after processing is completed, threshold processing is carried out on the wavelet coefficient grap