Image Segmentation and Verification Based on Machine Learning for Vision Inspection of Chicken Slaughtering

Abstract

According to the Islamic Law, one of the procedures in halal slaughtering of chicken is the step of severing the trachea, esophagus and both the carotid arteries and jugular veins to accelerate the chicken’s bleeding and death. Syariah Compliance Automated Chicken Processing System (SYCUT) uses the Vision Inspection Technology to detect and classify whether a chicken is halal or not. The lack of quality and halal assurance in chicken processing industry made it a need to produce such technology. The system implements image processing techniques and artificial intelligence approach, particularly the Viola and Jones object detection framework for esophagus detection. The results of the experiment from two different sites are 81.8% and 55% respectively. The detection module shows a result of 95.6% and 93.5% also from two different sites which are accuracy as good as a human personnel.