NDT model study of crown pear based on near infrared spectroscopy

With the growing area and production of pear, as well people for fruit quality requirements are growing. The traditional methods pear inspection expensive less accurate, cannot be done every pear. In response to current environment market demand, a rapid non-destructive method testing is explored, using near infrared spectroscopy establish prediction model crown main indicators pears soluble solids (SSC) hardness, NIR hardness build spectral measurement system. was measure images in band (400nm 1050nm). spectra were pre-processed with multiple scattering correction (MSC) standard normal variables exchange (SNV) eliminate influence extraneous factors, then downscaled by continuous projection algorithm (SPA) principal component analysis (PCA) extract number factors respectively. Partial Least Squares (PLS) used regression predict hardness. best developed SNV + correlation coefficient 0.64116 0.73566.