Abstract
In a broiler carcass production conveyor system, inspection, monitoring, and grading carcass and cuts based on computer vision techniques are challenging due to cuts segmentation and ambient light conditions issues. This study presents a depth image-based broiler carcass weight prediction system. An Active Shape Model was developed to segment the carcass into 4 cuts (drumsticks, breasts, wings, and head and neck). Five regression models were developed based on the image features for each weight estimation (carcass and its cuts). The Bayesian-ANN model outperformed all other regression models at 0.9981 R(2) and 0.9847 R(2) in the whole carcass and head and neck weight estimation. The RBF-SVR model surpassed all the other drumstick, breast, and wings weight prediction models at 0.9129 R(2), 0.9352 R(2), and 0.9896 R(2), respectively. This proposed technique can be applied as a nondestructive, nonintrusive, and accurate on-line broiler carcass production system in the automation of chicken carcass and cuts weight estimation.