Recognition of a Cracked Hen Egg Image Using a Sequenced Wave Signal Extraction and Identification Algorithm

Abstract

In order to develop a new recognition method for cracked hen egg with high accuracy and adoption, images with different crack width of the hen eggs were captured. After that, according to the change regulation of the local gray value of the crack area in the egg image, a sequenced wave signal extraction and identification algorithm was developed. This algorithm composed of wave signal extraction, wave signal connection, and sequenced wave signal identification. Results showed that, the sequenced wave signals extracted from the egg image were due to cracks and translucent areas of the egg shell. The highest length-width ratio of the segmented area (R max) and gray value change index (D) were two parameters extracted from the sequenced wave signal, and could be used to identify the sequenced wave signals caused by the cracks from other sequenced wave signals. A hen egg image with at least one crack-caused sequenced wave signal was considered as a cracked egg image. Using this method, recognition accuracy of hen eggs with a crack of 0.06–1.13 mm width was 98.9%, and that of intact eggs was 96%. The sequenced wave signal extraction and identification algorithm may have application potential to recognize cracked hen eggs on-line.