A novel edge detection method with application to the fat content prediction in marbled meat

Intramuscular fat is an important quality criterion, notably juiciness, in meat grading. But traditional visual inspectors are time consuming and destructive. However, edge detection techniques characterize meat surface in consistence, rapid, and non-destructive approach. In this paper, novel edge detection method applied on intramuscular fat is presented based on the energy and skewness as two smoothed versions of the image. Parametric analyses were investigated and the method was tested on several images, producing minimum improvements of 6.451%, 1.667% and 7.826% in signal to noise ratio, mean square error and edges localization, respectively, in comparison to Roberts, Prewitt, Sobel, and Canny detectors.