Analysis of correlation between carcass and viscera for chicken eviscerating based on machine vision technology

作者：Yan Chen, Hui Ai, Shuo Li · 发表于：Journal of Food Process Engineering · 年份：2020 · DOI：10.1111/jfpe.13592 · 被引用次数：9 · 研究领域：Smart Agriculture and AI、Image Processing Techniques and Applications、Industrial Vision Systems and Defect Detection

Abstract In the poultry evisceration, the inconsistent position of visible carcass and invisible viscera may be one of the most neglected problems, which increase the level of visceral damage by gripping manipulator. In order to detect the position of the chicken carcass and viscera, a computer vision‐based automation system is developed to extract the region of interest from each chicken in the image acquisition system. The segmentation method of carcass is proposed by applying the color space transformation and the threshold segmentation. This method combines with several operations of morphology and reconstruction to remove the other regions such as wings and legs. After a midline abdominal incision of the chicken, the viscera is segmented using the active contour algorithm. Following data analysis, the change trend of relative position is presented between carcass and viscera. The average longitudinal deviation value of weighting 1,000–1,500 g and 1,500–2000 g chickens were 22.9 and 32.4 mm, separately. These results indicate that the relative position is significantly changed between carcass and viscera with chicken size in the longitudinal direction. In this study, machine vision technology can be satisfactorily applied to predict the position of chicken viscera, which can provide technical support for poultry processing. Practical applications For a long time, avian influenza virus and various pathogenic microorganism have been threatening the breeding and slaughtering...