Estimation of intramuscular level of marbling among Whiteheaded Mutton Sheep lambs. (January 2016)

• Record Type: Journal Article
• Authors: Przybylak, A.; Boniecki, P.; Koszela, K.; Ludwiczak, A.; Zaborowicz, M.; Lisiak, D.; Stanisz, M.; Ślósarz, P.
• Is Part Of: Journal of food engineering. Volume 168(2016:Jan.)
• Page Start: 199
• Page End: 204
• Publication Date: 2016-01
• Subjects: USG image analysis -- Marbling classification -- Neural modeling; Food industry and trade -- Periodicals; Food -- Analysis -- Periodicals; Aliments -- Industrie et commerce -- Périodiques; Aliments -- Analyse -- Périodiques; Aliments -- Recherche -- Périodiques; 664.005
• DOI: 10.1016/j.jfoodeng.2015.07.035
• Languages: English
• ISSNs: 0260-8774

Abstract

Highlights: The study was based on neural network modeling methods, including image analysis. The suggested procedure allowed to perform non-invasive identification. ANN should be considered an effective classification instrument. Abstract: The aim of this work was to develop a non-invasive method to estimate the degree of the intramuscular fat in the Whiteheaded Mutton Sheep lambs by means of the USG technology and the neural image analysis. The classification process was based on the muscles USG images acquired on the hot carcass just post slaughter in three scanning points of 63 lamb carcasses: the longissimus muscle – over the last rib and the 3rd lumbar vertebrae, and the leg ( musculus semimembranosus ). The total of 568 USG images were obtained. The image characteristics were used to learn the artificial neural networks to recognize and classify the level of marbling in lamb meat. From among different tested neural networks, the PNN (Probabilistic Neural Network) type with the structure 13-404-5-1 was found to have the best classifying capability.