Research on Chicken Wings Quality Detection Based on Machine Vision

Currently, classification of chicken’s quality is used generally by manual work. The method takes time and energy, have a lower efficiency and easily influenced by subjective factors. To guarantee poultry classification processing quality and im-prove the level of poultry processing automation, this study aims to design a method of detecting chicken wing’s quality based on machine vision technology. First, extracting color features from RGB, HSI and Lab color models respectively, choosing B, H, S, a and b as color recognition vectors, and extracting the features of the percentage of congestion area in the images. Combining these two kinds of features as effective vectors of congested wings. Then, using three layers Back-Propagation neural network to classify and predict. Experiments showed that the classification accuracy of the method for detecting quality of chicken wings can reach above 98%. The study verifies that the method of distinguishing colors and de-tecting the quality of chicken wings based on machine vision technology is feasible. This method can be further expanded to field of the health care and daily diet.