A SYSTEM FOR ULTRASOUND IMAGE SEGMENTATION FOR LOIN EYE MEASUREMENTS IN SWINE

An image segmentation system was developed for detecting the muscle lo ngissimus thoraces (LT) in ultrasonic images of live pigs. The images have a low contrast, a high level of noise, and a high degree of varia nce in terms of texture and shape. The segmentation algorithm starts w ith a region growing process, which provides a rough approximation of the LT. Morphological operations and curve fitting eliminate unwanted noise. Finally, an active contour process refines the shape of the res ulting region. This system takes several segmentation techniques and b uilds a flow of information between them but does not rely on specific a priori information of the texture or the contrast. This is a first step towards automating the loin detection in ultrasonic images of liv e pigs. initial experiments provided encouraging results. It is a modu lar system so that different region growing and refinement algorithms can be easily substituted into the current design. This makes for a ge neral system that can be adapted to other segmentation tasks involving low contrast images. A series of three ultrasound images was made alo ng the dorsal surface of 30 live pigs. Using the images to estimate lo in volume, 64 and 70% of the variation in commercial loin weight and l ean yield of loin were predicted. Augmenting the model with backfat me asurements, the R-2 increased to 79 and 89%, respectively. These value s compare to 76 and 79%, respectively, from measurements made on the c arcass with the Hennessey Grading Probe.