The acquisition of particle microphysical information plays an important role in fuel combustion and atmospheric research. The particle morphology recognition algorithm based on interferometric particle imaging through Fourier transform and neighborhood pixel judgment is proposed. The interferometric defocus images are simulated from optical transfer matrix theory and experimentally captured through the IPI system. The preprocessed images are transformed from the time domain to the frequency domain by Fourier transform and a dynamic threshold selection method based on empirical calculation is applied to binarize the spectrum. Then, each white pixel and the white pixels in its eight surrounding neighborhoods are marked as a whole and the number of white bright spots in the spectrum is traversed. The morphological recognition of spherical and non-spherical particles is achieved by determining whether it is a single bright spot or multiple bright spots. The experimental result shows that the error rate of this algorithm is less than 4%.