| 摘要 |
A method is disclosed for analysing colour image data relating to a target object, particularly an animal carcase, to derive or predict a property of t he object of which colour is an indicator, such as meat yield. The method includes the step of processing the colour data to derive "intensity normalised" or light intensity independent measures of colour values, follow ed by the step of calculating the property of the object utilising the light intensity independent colour measures in a predictive equation in which the light intensity independent colour measures are variables and the property o f the object is calculated from solving the predictive equation. The predictiv e equation can be developed from data gathered during a data gathering experiment using images captured for real target objects, and correlating th e light intensity independent colour measures obtained from these data with th e actual measured property of each of the real target objects to derive the predictive equation by statistical analysis techniques to best fit the data. For meat carcase analysis, the property predicted can be the "yield", "conformation", or "fat score" of a carcase in a standard carcase grading system, or can be the "yield grade" or "quality grade" of meat from a carcas e in a standard meat grading system.
|
