The study on robot eviscerating technology and visceral contour recognition based on image processing for poultry

Abstract

Abstract In this study, robot eviscerating technology was used in the poultry slaughter industry. The poultry viscera were grabbed by the manipulation with the guidance of machine vision technology. A machine-vision-based method of locating the viscera of poultry carcasses was described. The threshold segmentation method, sobel operator and image operations were used to segment the images of poultry viscera. Subsequently, the visceral contour was extracted and its position was detected for common poultry such as Three-Yellow Chicken. The identification rates of this visceral contour recognition system were 95.3%, suggesting that the proposed image recognition algorithm could achieve the accuracy required for poultry visceral contour detection. Therefore, the traditional artificial poultry eviscerating would be replaced by robot eviscerating technology, and the new technology exhibited higher automation program and better eviscerated effect, the location prediction of viscera and the positioning of the machine vision system could be designed, the new technical means were provided for subsequent research on the conveyor chain of poultry eviscerated.