Detection of cracked-shell eggs using acoustic signal and fuzzy recognition

In order to quickly find out and pick out cracked-shell eggs in the processing of eggs, the acoustics signals created by striking the eggshells are acquired by an electrict microphone and a sound card and transformed into digital signals. Through analyzing those signals, it is found that the normal-shell eggs, cracked-shell eggs, hard-shell eggs and unequal-shell eggs are different with their signal decayed time, their minimum peak resonant frequencies and their maximum difference of the peak resonant frequencies from four points on the egg shell. The boundaries of these differences are fuzzy. By use of the principle of the max membership function to make fuzzy recognition, the accurate recognition ratio for cracked-shell eggs is up to 95 percent.