Non-destructive measurement of eggshell stiffness was carried out by means of acoustic resonance system. It was achieved by analysis of measured frequency response of eggshell excited with a light mechanical. Partial least squares (PLS), synergy interval PLS (si-PLS), genetic algorithm PLS (GA-PLS) and GA-siPLS algorithms were used comparatively to calibrate regression model. The performance of the final model was evaluated according to root mean square error of prediction (RMSEP) and correlation coefficient (R) in prediction set. Experimental results showed that GA-PLS and GA-siPLS models got acceptable performance with fewer frequency variables. The optimal GA-PLS model was achieved with R = 0.771 and RMSEP = 3.6, and the optimal GA-siPLS model was achieved with R = 0.7591 and RMSEP = 3.55 in prediction set. It will help to build a compact and robust model serving for on-line measurement of egg's stiffness. (C) 2010 Elsevier Ltd. All rights reserved.