Open AccessEgg freshness recognition based on a fuzzy radial-basis-function neural network technology
Author(s) -
Hongmou Zhao,
Xianghong Zhou
Publication year - 2019
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/346/1/012084
Subject(s) - artificial neural network , artificial intelligence , hue , computer science , radial basis function , rgb color model , pattern recognition (psychology) , identification (biology) , botany , biology
There are often mobile, unconscientious vendors in China who sell stale or even rotten eggs in produce markets, earning money by dishonest means. To prevent the entry of substandard eggs into the market that endanger the health of consumers, we designed an egg freshness recognition system based on a fuzzy radial-basis-function (RBF) neural network. This system acquires the color characteristic parameters red (R), green (G), and blue (B) of the transmitted light of eggs through a computer vision device. The system converts the RGB values into HIS (hue, intensity, and saturation) values, uses the egg transmitted light color characteristic parameter HIS as an input value and employs the Huff value coding as an output. A test sample was used to verify the identification system. Our experimental results show that when using a fuzzy RBF neural network and simple RBF neural network algorithm, the average recognition accuracy of the system is 96.35% and 92.72%, respectively, both of which are higher than the average recognition accuracy of 88.14% when using the back propagation neural network algorithm. The feasibility and superiority of the identification system proposed in this paper were verified; therefore, this system may serve as a reference for future research on egg freshness recognition.