Sequenced wave signal extraction and classification algorithm for duck egg crack on-line detection
2017
Sun, Ke | Ma, Long | Pan, Leiqing | Tu, Kang
A method to detect the shell cracks in translucent images of duck eggs and salted duck eggs is presented. The method consists of a sequenced wave signal extraction algorithm to extract the sequenced wave signals from the translucent images of duck eggs. Furthermore, the characteristic parameters of the extracted sequenced wave signals are calculated and analyzed. The analysis results showed that, the sequenced wave signals extracted from egg translucent images are caused by three factors: (i) egg cracks; (ii) air cell membrane of eggs; and (iii) shell texture. The sequenced wave signals caused by egg air cell membrane and shell texture are eliminated by using characteristic parameters of the sequenced wave signals. After the elimination, a classification algorithm is used on the translucent images of eggs. In the conducted experiments, the classification algorithm achieved an accuracy of 92.5% and 93.1% for duck eggs and salted duck eggs, respectively.
显示更多 [+] 显示较少 [-]