Chandraratne, Meegalla R.Samarasinghe, SandhyaKulasiri, Gamalathge D.Isherwood, PeterBekhit, A. E. D.Bickerstaffe, Roy2009-04-232003-081174-669605/2003https://hdl.handle.net/10182/1012As a result of constantly growing consumer expectations for meat quality, the meat industry is placing more and more emphasis on quality assurance issues. Fat content in meat influences some important meat quality parameters and meat marketability. Visible fat includes marbling (intramuscular) and intermuscular fat. Chemical analysis is currently used to determine the fat percentage in meat. However, this is a tedious, expensive and time-consuming method. Some measurements, like the number, size distribution and spatial distribution of marbling, are totally impossible by chemical analysis. For the meat industry, it is very useful to have an accurate, reliable, cost effective, fast and nondestructive technique to determine the fat content. Computer vision has enormous potential for evaluating meat quality because image processing and analysis techniques can quantitatively and consistently characterize complex geometric, colour and textural properties. The objectives of the present study were: a) to apply image processing techniques to quantify fat content of beef and lamb steaks; b) to develop a relationship between the chemical fat content and the fat content measured by image analysis.8enimage analysiscomputer visiontexture featuresmeat qualityartificial neural networksfat contentReportMarsden::280200 Artificial Intelligence and Signal and Image ProcessingMarsden::290100 Industrial Biotechnology and Food SciencesANZSRC::0801 Artificial Intelligence and Image ProcessingANZSRC::0908 Food Sciences