Purified egg white is an important ingredient in a number of baked and confectionary foods because of its foaming properties. However, yolk contamination in amounts as low as 0.01% can impede the foaming ability of egg white. In this study, we used Raman spectroscopy to evaluate the hypothesis that yolk contamination in egg white could be detected based on its molecular optical properties. Yolk contaminated egg white samples (n = 115) with contamination levels ranging from 0% to 0.25% (on weight basis) were prepared. The samples were excited with a 785 nm laser and Raman spectra from 250 to 3,200 cm(-1) were recorded. The Raman spectra were baseline corrected using an optimized piecewise cubic interpolation on each spectrum and then normalized with a standard normal variate transformation. Samples were randomly divided into calibration (n = 77) and validation (n = 38) data sets. A partial least squares regression (PLSR) model was developed to predict yolk contamination levels, based on the Raman spectral fingerprint. Raman spectral peaks, in the spectral region of 1,080 and 1,666 cm(-1), had the largest influence on detecting yolk contamination in egg white. The PLSR model was able to correctly predict yolk contamination levels with an R-2 = 0.90 in the validation data set. These results demonstrate the capability of Raman spectroscopy for detection of yolk contamination at very low levels in egg white and present a strong case for development of an on-line system to be deployed in egg processing plants.