The invention belongs to the technical field of agricultural product detection, and particularly relates to an
infrared-based
rice oil content detection method which comprises the following steps: S1, acquiring
infrared spectrum data and a
projection image of a to-be-detected rice sample, and calculating the average length, the average width, the spectrum
baseline drift distance and the total full-band
absorbance of the to-be-detected rice sample; s2, constructing a morphological scattering
coupling index according to the ratio of the average length to the average width, the spectral
baseline drift amount and the total full-band
absorbance, and calculating an
adaptive wavelet denoising threshold by using the morphological scattering
coupling index; and S3, carrying out denoising
processing on the
infrared spectrum data by utilizing the self-
adaptive wavelet denoising threshold. According to the method, the mapping relation between the morphological characteristics and the
signal processing parameters is established, scattering
noise generated by particulate matter physical morphology is effectively eliminated, and the accuracy and stability of
oil content detection of the slender grain type rice are remarkably improved.